{ "apify_query_funnels": [ { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Budapest, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.4442, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": { "construction_services": 12, "unresolved": 4 }, "current_ready": 12, "eligible_candidates": 16, "email_attempt_state_counts": { "completed": 16 }, "email_attempted_all": 16, "email_result_counts_attempted_only": { "catch_all": 4, "ok": 12 }, "model_attempted_candidates": 12, "model_generation_in_row": 12, "no_row_yet": 0, "observed_email_model_order": { "email_completed_before_model_dispatch": 12 }, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 16, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 12, "email_held": 4 }, "rows_in_sqlite": 16, "scrape_evidence_saved_all_candidates": 16, "supported_fit_within_valid_scraped_processed": 12, "supported_personalization_fit_all": 12, "terminal_outcome_count": 16, "usable_scrape_all_candidates": 16, "usable_scrape_within_valid_processed": 12, "valid_email_all": 12, "valid_email_pending": 0, "valid_email_within_processed": 12 }, "dataset_id": "gNWcdFpwUTxLhynSY", "done_receipt": { "appended": 16, "at": "2026-10-04T00:53:48.572773+00:00", "cost_usd": 0.4442, "email_candidates": 16, "raw": 111 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T00:52:51.178Z", "id": "apify:yfflKN6jM1Ff9BfTD", "index": 0, "kind": "apify_query", "label": "generálkivitelezés · Budapest, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 16, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 111, "raw_record_count": 111, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 111, "raw_unique_website_domains": 104, "run_id": "yfflKN6jM1Ff9BfTD", "saved_scrape_matches": 41, "saved_usable_scrape_matches": 30, "scrape_file_timing_counts": { "written_during_this_acquisition": 41, "written_during_this_acquisition_usable": 30 }, "stages": [ { "count": 111, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 30, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 16, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 16, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 16, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 12, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 12, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 12, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 12, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T00:51:27.682Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Debrecen, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.0882, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": { "construction_services": 2 }, "current_ready": 2, "eligible_candidates": 2, "email_attempt_state_counts": { "completed": 2 }, "email_attempted_all": 2, "email_result_counts_attempted_only": { "ok": 2 }, "model_attempted_candidates": 2, "model_generation_in_row": 2, "no_row_yet": 0, "observed_email_model_order": { "email_completed_before_model_dispatch": 2 }, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 2, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 2 }, "rows_in_sqlite": 2, "scrape_evidence_saved_all_candidates": 2, "supported_fit_within_valid_scraped_processed": 2, "supported_personalization_fit_all": 2, "terminal_outcome_count": 2, "usable_scrape_all_candidates": 2, "usable_scrape_within_valid_processed": 2, "valid_email_all": 2, "valid_email_pending": 0, "valid_email_within_processed": 2 }, "dataset_id": "eeVk8V0AoVhBgCroY", "done_receipt": { "appended": 2, "at": "2026-10-04T00:56:14.758059+00:00", "cost_usd": 0.0882, "email_candidates": 2, "raw": 22 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T00:56:01.192Z", "id": "apify:7xfov3lMMB0GeIsi0", "index": 1, "kind": "apify_query", "label": "generálkivitelezés · Debrecen, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 2, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 22, "raw_record_count": 22, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 22, "raw_unique_website_domains": 20, "run_id": "7xfov3lMMB0GeIsi0", "saved_scrape_matches": 6, "saved_usable_scrape_matches": 3, "scrape_file_timing_counts": { "written_during_this_acquisition": 6, "written_during_this_acquisition_usable": 3 }, "stages": [ { "count": 22, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 3, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 2, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 2, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 2, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 2, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 2, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 2, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 2, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T00:55:15.272Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Győr, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.11620000000000001, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "dataset_id": "Nak8aAy6L9LotAoq0", "done_receipt": { "appended": 0, "at": "2026-10-04T00:58:27.594755+00:00", "cost_usd": 0.11620000000000001, "email_candidates": 0, "raw": 29 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T00:57:43.242Z", "id": "apify:RZ0J5Xn3smjybjLm9", "index": 2, "kind": "apify_query", "label": "generálkivitelezés · Győr, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 0, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 29, "raw_record_count": 29, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 29, "raw_unique_website_domains": 28, "run_id": "RZ0J5Xn3smjybjLm9", "saved_scrape_matches": 9, "saved_usable_scrape_matches": 3, "scrape_file_timing_counts": { "written_during_this_acquisition": 9, "written_during_this_acquisition_usable": 3 }, "stages": [ { "count": 29, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 3, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 0, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T00:56:44.153Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Pécs, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.0522, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": { "construction_services": 1 }, "current_ready": 1, "eligible_candidates": 1, "email_attempt_state_counts": { "completed": 1 }, "email_attempted_all": 1, "email_result_counts_attempted_only": { "ok": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 1, "no_row_yet": 0, "observed_email_model_order": { "email_completed_before_model_dispatch": 1 }, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 1, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 1 }, "rows_in_sqlite": 1, "scrape_evidence_saved_all_candidates": 1, "supported_fit_within_valid_scraped_processed": 1, "supported_personalization_fit_all": 1, "terminal_outcome_count": 1, "usable_scrape_all_candidates": 1, "usable_scrape_within_valid_processed": 1, "valid_email_all": 1, "valid_email_pending": 0, "valid_email_within_processed": 1 }, "dataset_id": "TGkUTtfwf8imsC1HJ", "done_receipt": { "appended": 1, "at": "2026-10-04T00:59:26.988902+00:00", "cost_usd": 0.0522, "email_candidates": 1, "raw": 13 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T00:59:06.527Z", "id": "apify:LkSiaLEmZfaT9GcII", "index": 3, "kind": "apify_query", "label": "generálkivitelezés · Pécs, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 1, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 13, "raw_record_count": 13, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 13, "raw_unique_website_domains": 13, "run_id": "LkSiaLEmZfaT9GcII", "saved_scrape_matches": 4, "saved_usable_scrape_matches": 2, "scrape_file_timing_counts": { "written_during_this_acquisition": 4, "written_during_this_acquisition_usable": 2 }, "stages": [ { "count": 13, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 2, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 1, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 1, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 1, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 1, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 1, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 1, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 1, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T00:58:28.993Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Szeged, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.1242, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": { "construction_services": 3 }, "current_ready": 3, "eligible_candidates": 3, "email_attempt_state_counts": { "completed": 3 }, "email_attempted_all": 3, "email_result_counts_attempted_only": { "ok": 3 }, "model_attempted_candidates": 3, "model_generation_in_row": 3, "no_row_yet": 0, "observed_email_model_order": { "email_completed_before_model_dispatch": 3 }, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 3, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 3 }, "rows_in_sqlite": 3, "scrape_evidence_saved_all_candidates": 3, "supported_fit_within_valid_scraped_processed": 3, "supported_personalization_fit_all": 3, "terminal_outcome_count": 3, "usable_scrape_all_candidates": 3, "usable_scrape_within_valid_processed": 3, "valid_email_all": 3, "valid_email_pending": 0, "valid_email_within_processed": 3 }, "dataset_id": "TNwFtOfKHncUyLAZ4", "done_receipt": { "appended": 3, "at": "2026-10-04T01:04:03.580188+00:00", "cost_usd": 0.1242, "email_candidates": 3, "raw": 31 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T01:03:37.092Z", "id": "apify:l2LRkZZMh5de61t03", "index": 4, "kind": "apify_query", "label": "generálkivitelezés · Szeged, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 3, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 31, "raw_record_count": 31, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 31, "raw_unique_website_domains": 31, "run_id": "l2LRkZZMh5de61t03", "saved_scrape_matches": 10, "saved_usable_scrape_matches": 7, "scrape_file_timing_counts": { "written_during_this_acquisition": 10, "written_during_this_acquisition_usable": 7 }, "stages": [ { "count": 31, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 7, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 3, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 3, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 3, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 3, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 3, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 3, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 3, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T01:00:24.733Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Miskolc, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.0402, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "dataset_id": "4G6EA9GmUgck2sM1A", "done_receipt": { "appended": 0, "at": "2026-10-04T01:05:41.506725+00:00", "cost_usd": 0.0402, "email_candidates": 0, "raw": 10 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T01:05:22.048Z", "id": "apify:tuYff5f8G4mOD3aWq", "index": 5, "kind": "apify_query", "label": "generálkivitelezés · Miskolc, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 0, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 10, "raw_record_count": 10, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 10, "raw_unique_website_domains": 10, "run_id": "tuYff5f8G4mOD3aWq", "saved_scrape_matches": 1, "saved_usable_scrape_matches": 0, "scrape_file_timing_counts": { "written_during_this_acquisition": 1 }, "stages": [ { "count": 10, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 0, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 0, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T01:04:39.060Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Székesfehérvár, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.07220000000000001, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "dataset_id": "NwyZ1r0xJfFVgAlDh", "done_receipt": { "appended": 0, "at": "2026-10-04T01:07:02.993561+00:00", "cost_usd": 0.07220000000000001, "email_candidates": 2, "raw": 18 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T01:06:31.127Z", "id": "apify:mcZEuRzLfauYUvjQk", "index": 6, "kind": "apify_query", "label": "generálkivitelezés · Székesfehérvár, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 2, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 18, "raw_record_count": 18, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 18, "raw_unique_website_domains": 18, "run_id": "mcZEuRzLfauYUvjQk", "saved_scrape_matches": 5, "saved_usable_scrape_matches": 4, "scrape_file_timing_counts": { "written_during_this_acquisition": 5, "written_during_this_acquisition_usable": 4 }, "stages": [ { "count": 18, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 4, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 2, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T01:05:42.828Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Kecskemét, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.08420000000000001, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": { "construction_services": 1 }, "current_ready": 1, "eligible_candidates": 1, "email_attempt_state_counts": { "completed": 1 }, "email_attempted_all": 1, "email_result_counts_attempted_only": { "ok": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 1, "no_row_yet": 0, "observed_email_model_order": { "email_completed_before_model_dispatch": 1 }, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 1, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 1 }, "rows_in_sqlite": 1, "scrape_evidence_saved_all_candidates": 1, "supported_fit_within_valid_scraped_processed": 1, "supported_personalization_fit_all": 1, "terminal_outcome_count": 1, "usable_scrape_all_candidates": 1, "usable_scrape_within_valid_processed": 1, "valid_email_all": 1, "valid_email_pending": 0, "valid_email_within_processed": 1 }, "dataset_id": "ckcefsRVIqLHP7lAS", "done_receipt": { "appended": 1, "at": "2026-10-04T01:08:31.973473+00:00", "cost_usd": 0.08420000000000001, "email_candidates": 2, "raw": 21 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T01:07:39.541Z", "id": "apify:cL4oFvbUs14PcymkF", "index": 7, "kind": "apify_query", "label": "generálkivitelezés · Kecskemét, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 2, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 21, "raw_record_count": 21, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 21, "raw_unique_website_domains": 21, "run_id": "cL4oFvbUs14PcymkF", "saved_scrape_matches": 7, "saved_usable_scrape_matches": 3, "scrape_file_timing_counts": { "written_during_this_acquisition": 7, "written_during_this_acquisition_usable": 3 }, "stages": [ { "count": 21, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 3, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 2, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 1, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 1, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 1, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 1, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 1, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 1, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T01:07:04.340Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Nyíregyháza, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.0602, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": { "construction_services": 3 }, "current_ready": 3, "eligible_candidates": 3, "email_attempt_state_counts": { "completed": 3 }, "email_attempted_all": 3, "email_result_counts_attempted_only": { "ok": 3 }, "model_attempted_candidates": 3, "model_generation_in_row": 3, "no_row_yet": 0, "observed_email_model_order": { "email_completed_before_model_dispatch": 3 }, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 3, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 3 }, "rows_in_sqlite": 3, "scrape_evidence_saved_all_candidates": 3, "supported_fit_within_valid_scraped_processed": 3, "supported_personalization_fit_all": 3, "terminal_outcome_count": 3, "usable_scrape_all_candidates": 3, "usable_scrape_within_valid_processed": 3, "valid_email_all": 3, "valid_email_pending": 0, "valid_email_within_processed": 3 }, "dataset_id": "HHfVuS28Nz8JGUs34", "done_receipt": { "appended": 3, "at": "2026-10-04T01:10:24.846808+00:00", "cost_usd": 0.0602, "email_candidates": 3, "raw": 15 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T01:10:02.624Z", "id": "apify:LJW1zXvP7T8qRJKDN", "index": 8, "kind": "apify_query", "label": "generálkivitelezés · Nyíregyháza, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 3, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 15, "raw_record_count": 15, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 15, "raw_unique_website_domains": 15, "run_id": "LJW1zXvP7T8qRJKDN", "saved_scrape_matches": 6, "saved_usable_scrape_matches": 5, "scrape_file_timing_counts": { "written_during_this_acquisition": 6, "written_during_this_acquisition_usable": 5 }, "stages": [ { "count": 15, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 5, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 3, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 3, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 3, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 3, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 3, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 3, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 3, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T01:09:14.334Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Szombathely, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.044199999999999996, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "dataset_id": "SHOfpFJexOzpKOZoh", "done_receipt": { "appended": 0, "at": "2026-10-04T01:12:19.749518+00:00", "cost_usd": 0.044199999999999996, "email_candidates": 0, "raw": 11 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T01:11:37.954Z", "id": "apify:2t8AxPDKQBwaVytbc", "index": 9, "kind": "apify_query", "label": "generálkivitelezés · Szombathely, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 0, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 11, "raw_record_count": 11, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 11, "raw_unique_website_domains": 11, "run_id": "2t8AxPDKQBwaVytbc", "saved_scrape_matches": 7, "saved_usable_scrape_matches": 3, "scrape_file_timing_counts": { "written_during_this_acquisition": 7, "written_during_this_acquisition_usable": 3 }, "stages": [ { "count": 11, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 3, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 0, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T01:11:07.795Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Veszprém, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.044199999999999996, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": { "construction_services": 4 }, "current_ready": 4, "eligible_candidates": 4, "email_attempt_state_counts": { "completed": 4 }, "email_attempted_all": 4, "email_result_counts_attempted_only": { "ok": 4 }, "model_attempted_candidates": 4, "model_generation_in_row": 4, "no_row_yet": 0, "observed_email_model_order": { "email_completed_before_model_dispatch": 4 }, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 4, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 4 }, "rows_in_sqlite": 4, "scrape_evidence_saved_all_candidates": 4, "supported_fit_within_valid_scraped_processed": 4, "supported_personalization_fit_all": 4, "terminal_outcome_count": 4, "usable_scrape_all_candidates": 4, "usable_scrape_within_valid_processed": 4, "valid_email_all": 4, "valid_email_pending": 0, "valid_email_within_processed": 4 }, "dataset_id": "5Xee57WmTxnSsCkBh", "done_receipt": { "appended": 4, "at": "2026-10-04T01:13:48.494520+00:00", "cost_usd": 0.044199999999999996, "email_candidates": 4, "raw": 11 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T01:12:59.601Z", "id": "apify:tVsz57fiYnv2a4uUO", "index": 10, "kind": "apify_query", "label": "generálkivitelezés · Veszprém, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 4, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 11, "raw_record_count": 11, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 11, "raw_unique_website_domains": 11, "run_id": "tVsz57fiYnv2a4uUO", "saved_scrape_matches": 7, "saved_usable_scrape_matches": 5, "scrape_file_timing_counts": { "written_during_this_acquisition": 7, "written_during_this_acquisition_usable": 5 }, "stages": [ { "count": 11, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 5, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 4, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 4, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 4, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 4, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 4, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 4, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 4, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T01:12:21.044Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Zalaegerszeg, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.0242, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": { "construction_services": 2, "unresolved": 1 }, "current_ready": 2, "eligible_candidates": 3, "email_attempt_state_counts": { "completed": 3 }, "email_attempted_all": 3, "email_result_counts_attempted_only": { "catch_all": 1, "ok": 2 }, "model_attempted_candidates": 2, "model_generation_in_row": 2, "no_row_yet": 0, "observed_email_model_order": { "email_completed_before_model_dispatch": 2 }, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 3, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 2, "email_held": 1 }, "rows_in_sqlite": 3, "scrape_evidence_saved_all_candidates": 3, "supported_fit_within_valid_scraped_processed": 2, "supported_personalization_fit_all": 2, "terminal_outcome_count": 3, "usable_scrape_all_candidates": 3, "usable_scrape_within_valid_processed": 2, "valid_email_all": 2, "valid_email_pending": 0, "valid_email_within_processed": 2 }, "dataset_id": "ezIkgnl7f4gZcVSrg", "done_receipt": { "appended": 3, "at": "2026-10-04T01:15:11.286458+00:00", "cost_usd": 0.0242, "email_candidates": 3, "raw": 6 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T01:14:50.522Z", "id": "apify:RwUaFumJQTRXvWMJH", "index": 11, "kind": "apify_query", "label": "generálkivitelezés · Zalaegerszeg, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 3, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 6, "raw_record_count": 6, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 6, "raw_unique_website_domains": 6, "run_id": "RwUaFumJQTRXvWMJH", "saved_scrape_matches": 4, "saved_usable_scrape_matches": 3, "scrape_file_timing_counts": { "written_during_this_acquisition": 4, "written_during_this_acquisition_usable": 3 }, "stages": [ { "count": 6, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 3, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 3, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 3, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 3, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 2, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 2, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 2, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 2, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T01:14:14.806Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Kaposvár, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.0162, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "dataset_id": "d0gW5V2hsGB6UTHJp", "done_receipt": { "appended": 0, "at": "2026-10-04T01:16:35.986374+00:00", "cost_usd": 0.0162, "email_candidates": 0, "raw": 4 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T01:16:10.154Z", "id": "apify:Htc1cFBin9RNUypRy", "index": 12, "kind": "apify_query", "label": "generálkivitelezés · Kaposvár, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 0, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 4, "raw_record_count": 4, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 4, "raw_unique_website_domains": 4, "run_id": "Htc1cFBin9RNUypRy", "saved_scrape_matches": 2, "saved_usable_scrape_matches": 1, "scrape_file_timing_counts": { "written_during_this_acquisition": 2, "written_during_this_acquisition_usable": 1 }, "stages": [ { "count": 4, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 1, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 0, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T01:15:37.470Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Eger, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.0242, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": { "unresolved": 1 }, "current_ready": 0, "eligible_candidates": 1, "email_attempt_state_counts": { "completed": 1 }, "email_attempted_all": 1, "email_result_counts_attempted_only": { "ok": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": { "email_completed_before_model_dispatch": 1 }, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 1, "processed_without_email_attempt": 0, "processing_status_counts": { "uncertain_paid_held": 1 }, "rows_in_sqlite": 1, "scrape_evidence_saved_all_candidates": 1, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 1, "usable_scrape_all_candidates": 1, "usable_scrape_within_valid_processed": 1, "valid_email_all": 1, "valid_email_pending": 0, "valid_email_within_processed": 1 }, "dataset_id": "1SO2cARqc0fXmVZ47", "done_receipt": { "appended": 1, "at": "2026-10-04T01:17:26.606982+00:00", "cost_usd": 0.0242, "email_candidates": 1, "raw": 6 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T01:17:02.646Z", "id": "apify:56MvJcTtLPPZkrvKJ", "index": 13, "kind": "apify_query", "label": "generálkivitelezés · Eger, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 1, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 6, "raw_record_count": 6, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 6, "raw_unique_website_domains": 6, "run_id": "56MvJcTtLPPZkrvKJ", "saved_scrape_matches": 2, "saved_usable_scrape_matches": 1, "scrape_file_timing_counts": { "written_during_this_acquisition": 2, "written_during_this_acquisition_usable": 1 }, "stages": [ { "count": 6, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 1, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 1, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 1, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 1, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 1, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 1, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T01:16:37.600Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Tatabánya, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.0162, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": { "construction_services": 1 }, "current_ready": 1, "eligible_candidates": 1, "email_attempt_state_counts": { "completed": 1 }, "email_attempted_all": 1, "email_result_counts_attempted_only": { "ok": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 1, "no_row_yet": 0, "observed_email_model_order": { "email_completed_before_model_dispatch": 1 }, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 1, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 1 }, "rows_in_sqlite": 1, "scrape_evidence_saved_all_candidates": 1, "supported_fit_within_valid_scraped_processed": 1, "supported_personalization_fit_all": 1, "terminal_outcome_count": 1, "usable_scrape_all_candidates": 1, "usable_scrape_within_valid_processed": 1, "valid_email_all": 1, "valid_email_pending": 0, "valid_email_within_processed": 1 }, "dataset_id": "rzsGdwqE81lIF2T4s", "done_receipt": { "appended": 1, "at": "2026-10-04T03:13:54.416782+00:00", "cost_usd": 0.0162, "email_candidates": 1, "raw": 4 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T03:13:40.831Z", "id": "apify:1lLQgl3lFB6wGhp2L", "index": 14, "kind": "apify_query", "label": "generálkivitelezés · Tatabánya, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 1, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 4, "raw_record_count": 4, "raw_repeat_place_occurrences_from_prior_queries": 0, "raw_unique_place_ids": 4, "raw_unique_website_domains": 4, "run_id": "1lLQgl3lFB6wGhp2L", "saved_scrape_matches": 3, "saved_usable_scrape_matches": 2, "scrape_file_timing_counts": { "written_during_this_acquisition": 3, "written_during_this_acquisition_usable": 2 }, "stages": [ { "count": 4, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 2, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 1, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 1, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 1, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 1, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 1, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 1, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 1, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T03:12:59.160Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Budapest, Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "építőipari kivitelező" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "actual_usd": 0.8002, "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "counts": { "category_counts_rows_only": { "construction_services": 8, "other_services": 1, "unresolved": 23 }, "current_ready": 9, "eligible_candidates": 61, "email_attempt_state_counts": { "completed": 32 }, "email_attempted_all": 32, "email_result_counts_attempted_only": { "catch_all": 3, "invalid": 5, "ok": 21, "unknown": 3 }, "model_attempted_candidates": 10, "model_generation_in_row": 9, "no_row_yet": 29, "observed_email_model_order": { "email_completed_before_model_dispatch": 9 }, "pending_total": 35, "pending_with_row": 6, "personalized_but_not_ready": 0, "processed": 26, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 9, "email_held": 11, "no_result_status": 29, "pending": 6, "worker_held": 6 }, "rows_in_sqlite": 32, "scrape_evidence_saved_all_candidates": 61, "supported_fit_within_valid_scraped_processed": 9, "supported_personalization_fit_all": 9, "terminal_outcome_count": 26, "usable_scrape_all_candidates": 61, "usable_scrape_within_valid_processed": 15, "valid_email_all": 21, "valid_email_pending": 6, "valid_email_within_processed": 15 }, "dataset_id": "9UW9NrbjSQrrogaoD", "done_receipt": { "appended": 61, "at": "2026-10-04T03:16:44.978994+00:00", "cost_usd": 0.8002, "email_candidates": 61, "raw": 200 }, "family_id": "fresh_maps", "finished_at": "2026-10-04T03:15:11.007Z", "id": "apify:vL5Sbha1sd5ygFtuV", "index": 15, "kind": "apify_query", "label": "építőipari kivitelező · Budapest, Magyarország", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.61, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "own_site_email_candidates": 61, "provenance": "Exact stored actor-input.json, actor-run.json, records.json and done.json receipts. No provider API call performed by audit.", "raw_first_attributed_places": 169, "raw_record_count": 200, "raw_repeat_place_occurrences_from_prior_queries": 31, "raw_unique_place_ids": 200, "raw_unique_website_domains": 196, "run_id": "vL5Sbha1sd5ygFtuV", "saved_scrape_matches": 100, "saved_usable_scrape_matches": 81, "scrape_file_timing_counts": { "written_before_this_acquisition": 4, "written_before_this_acquisition_usable": 3, "written_during_this_acquisition": 96, "written_during_this_acquisition_usable": 78 }, "stages": [ { "count": 200, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 81, "key": "saved_usable_site", "label": "Saved usable site", "note": "Matching saved evidence within this raw dataset. May include cached sites from earlier queries. Per-query raw scopes overlap and must not be added as unique companies.", "status": "verified" }, { "count": 61, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 61, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 26, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 15, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 15, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 9, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 9, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "started_at": "2026-10-04T03:14:39.396Z", "status": "SUCCEEDED" } ], "cost_by_service": { "apify": { "actual_completed_usd": 2.0512, "attempts": 16, "unsettled_exposure_usd": 0 }, "millionverifier": { "actual_completed_usd": 3.092699999999948, "attempts": 796, "unsettled_exposure_usd": 0.011699999999999999 }, "model": { "actual_completed_usd": 0.3642407000000001, "attempts": 121, "unsettled_exposure_usd": 0.057720320000000006 } }, "execution_plan": { "actor": "compass/crawler-google-places", "build": "0.14.759", "executed_queries": 16, "not_executed_steps": [ { "city": "Debrecen", "index": 16, "query": "építőipari kivitelező" }, { "city": "Győr", "index": 17, "query": "építőipari kivitelező" }, { "city": "Pécs", "index": 18, "query": "építőipari kivitelező" }, { "city": "Szeged", "index": 19, "query": "építőipari kivitelező" }, { "city": "Miskolc", "index": 20, "query": "építőipari kivitelező" }, { "city": "Székesfehérvár", "index": 21, "query": "építőipari kivitelező" }, { "city": "Kecskemét", "index": 22, "query": "építőipari kivitelező" }, { "city": "Nyíregyháza", "index": 23, "query": "építőipari kivitelező" }, { "city": "Szombathely", "index": 24, "query": "építőipari kivitelező" }, { "city": "Veszprém", "index": 25, "query": "építőipari kivitelező" }, { "city": "Zalaegerszeg", "index": 26, "query": "építőipari kivitelező" }, { "city": "Kaposvár", "index": 27, "query": "építőipari kivitelező" }, { "city": "Eger", "index": 28, "query": "építőipari kivitelező" }, { "city": "Tatabánya", "index": 29, "query": "építőipari kivitelező" }, { "city": "Budapest", "index": 30, "query": "tetőfedés" }, { "city": "Debrecen", "index": 31, "query": "tetőfedés" }, { "city": "Győr", "index": 32, "query": "tetőfedés" }, { "city": "Pécs", "index": 33, "query": "tetőfedés" }, { "city": "Szeged", "index": 34, "query": "tetőfedés" }, { "city": "Miskolc", "index": 35, "query": "tetőfedés" }, { "city": "Székesfehérvár", "index": 36, "query": "tetőfedés" }, { "city": "Kecskemét", "index": 37, "query": "tetőfedés" }, { "city": "Nyíregyháza", "index": 38, "query": "tetőfedés" }, { "city": "Szombathely", "index": 39, "query": "tetőfedés" }, { "city": "Veszprém", "index": 40, "query": "tetőfedés" }, { "city": "Zalaegerszeg", "index": 41, "query": "tetőfedés" }, { "city": "Kaposvár", "index": 42, "query": "tetőfedés" }, { "city": "Eger", "index": 43, "query": "tetőfedés" }, { "city": "Tatabánya", "index": 44, "query": "tetőfedés" }, { "city": "Budapest", "index": 45, "query": "épületgépészet" }, { "city": "Debrecen", "index": 46, "query": "épületgépészet" }, { "city": "Győr", "index": 47, "query": "épületgépészet" }, { "city": "Pécs", "index": 48, "query": "épületgépészet" }, { "city": "Szeged", "index": 49, "query": "épületgépészet" }, { "city": "Miskolc", "index": 50, "query": "épületgépészet" }, { "city": "Székesfehérvár", "index": 51, "query": "épületgépészet" }, { "city": "Kecskemét", "index": 52, "query": "épületgépészet" }, { "city": "Nyíregyháza", "index": 53, "query": "épületgépészet" }, { "city": "Szombathely", "index": 54, "query": "épületgépészet" }, { "city": "Veszprém", "index": 55, "query": "épületgépészet" }, { "city": "Zalaegerszeg", "index": 56, "query": "épületgépészet" }, { "city": "Kaposvár", "index": 57, "query": "épületgépészet" }, { "city": "Eger", "index": 58, "query": "épületgépészet" }, { "city": "Tatabánya", "index": 59, "query": "épületgépészet" }, { "city": "Budapest", "index": 60, "query": "nyílászáró beépítés" }, { "city": "Debrecen", "index": 61, "query": "nyílászáró beépítés" }, { "city": "Győr", "index": 62, "query": "nyílászáró beépítés" }, { "city": "Pécs", "index": 63, "query": "nyílászáró beépítés" }, { "city": "Szeged", "index": 64, "query": "nyílászáró beépítés" }, { "city": "Miskolc", "index": 65, "query": "nyílászáró beépítés" }, { "city": "Székesfehérvár", "index": 66, "query": "nyílászáró beépítés" }, { "city": "Kecskemét", "index": 67, "query": "nyílászáró beépítés" }, { "city": "Nyíregyháza", "index": 68, "query": "nyílászáró beépítés" }, { "city": "Szombathely", "index": 69, "query": "nyílászáró beépítés" }, { "city": "Veszprém", "index": 70, "query": "nyílászáró beépítés" }, { "city": "Zalaegerszeg", "index": 71, "query": "nyílászáró beépítés" }, { "city": "Kaposvár", "index": 72, "query": "nyílászáró beépítés" }, { "city": "Eger", "index": 73, "query": "nyílászáró beépítés" }, { "city": "Tatabánya", "index": 74, "query": "nyílászáró beépítés" }, { "city": "Budapest", "index": 75, "query": "szigetelés" }, { "city": "Debrecen", "index": 76, "query": "szigetelés" }, { "city": "Győr", "index": 77, "query": "szigetelés" }, { "city": "Pécs", "index": 78, "query": "szigetelés" }, { "city": "Szeged", "index": 79, "query": "szigetelés" }, { "city": "Miskolc", "index": 80, "query": "szigetelés" }, { "city": "Székesfehérvár", "index": 81, "query": "szigetelés" }, { "city": "Kecskemét", "index": 82, "query": "szigetelés" }, { "city": "Nyíregyháza", "index": 83, "query": "szigetelés" }, { "city": "Szombathely", "index": 84, "query": "szigetelés" }, { "city": "Veszprém", "index": 85, "query": "szigetelés" }, { "city": "Zalaegerszeg", "index": 86, "query": "szigetelés" }, { "city": "Kaposvár", "index": 87, "query": "szigetelés" }, { "city": "Eger", "index": 88, "query": "szigetelés" }, { "city": "Tatabánya", "index": 89, "query": "szigetelés" }, { "city": "Budapest", "index": 90, "query": "kertépítés" }, { "city": "Debrecen", "index": 91, "query": "kertépítés" }, { "city": "Győr", "index": 92, "query": "kertépítés" }, { "city": "Pécs", "index": 93, "query": "kertépítés" }, { "city": "Szeged", "index": 94, "query": "kertépítés" }, { "city": "Miskolc", "index": 95, "query": "kertépítés" }, { "city": "Székesfehérvár", "index": 96, "query": "kertépítés" }, { "city": "Kecskemét", "index": 97, "query": "kertépítés" }, { "city": "Nyíregyháza", "index": 98, "query": "kertépítés" }, { "city": "Szombathely", "index": 99, "query": "kertépítés" }, { "city": "Veszprém", "index": 100, "query": "kertépítés" }, { "city": "Zalaegerszeg", "index": 101, "query": "kertépítés" }, { "city": "Kaposvár", "index": 102, "query": "kertépítés" }, { "city": "Eger", "index": 103, "query": "kertépítés" }, { "city": "Tatabánya", "index": 104, "query": "kertépítés" }, { "city": "Budapest", "index": 105, "query": "ipari építés" }, { "city": "Debrecen", "index": 106, "query": "ipari építés" }, { "city": "Győr", "index": 107, "query": "ipari építés" }, { "city": "Pécs", "index": 108, "query": "ipari építés" }, { "city": "Szeged", "index": 109, "query": "ipari építés" }, { "city": "Miskolc", "index": 110, "query": "ipari építés" }, { "city": "Székesfehérvár", "index": 111, "query": "ipari építés" }, { "city": "Kecskemét", "index": 112, "query": "ipari építés" }, { "city": "Nyíregyháza", "index": 113, "query": "ipari építés" }, { "city": "Szombathely", "index": 114, "query": "ipari építés" }, { "city": "Veszprém", "index": 115, "query": "ipari építés" }, { "city": "Zalaegerszeg", "index": 116, "query": "ipari építés" }, { "city": "Kaposvár", "index": 117, "query": "ipari építés" }, { "city": "Eger", "index": 118, "query": "ipari építés" }, { "city": "Tatabánya", "index": 119, "query": "ipari építés" }, { "city": "Budapest", "index": 120, "query": "lakásfelújítás" }, { "city": "Debrecen", "index": 121, "query": "lakásfelújítás" }, { "city": "Győr", "index": 122, "query": "lakásfelújítás" }, { "city": "Pécs", "index": 123, "query": "lakásfelújítás" }, { "city": "Szeged", "index": 124, "query": "lakásfelújítás" }, { "city": "Miskolc", "index": 125, "query": "lakásfelújítás" }, { "city": "Székesfehérvár", "index": 126, "query": "lakásfelújítás" }, { "city": "Kecskemét", "index": 127, "query": "lakásfelújítás" }, { "city": "Nyíregyháza", "index": 128, "query": "lakásfelújítás" }, { "city": "Szombathely", "index": 129, "query": "lakásfelújítás" }, { "city": "Veszprém", "index": 130, "query": "lakásfelújítás" }, { "city": "Zalaegerszeg", "index": 131, "query": "lakásfelújítás" }, { "city": "Kaposvár", "index": 132, "query": "lakásfelújítás" }, { "city": "Eger", "index": 133, "query": "lakásfelújítás" }, { "city": "Tatabánya", "index": 134, "query": "lakásfelújítás" }, { "city": "Budapest", "index": 135, "query": "klímaszerelés" }, { "city": "Debrecen", "index": 136, "query": "klímaszerelés" }, { "city": "Győr", "index": 137, "query": "klímaszerelés" }, { "city": "Pécs", "index": 138, "query": "klímaszerelés" }, { "city": "Szeged", "index": 139, "query": "klímaszerelés" }, { "city": "Miskolc", "index": 140, "query": "klímaszerelés" }, { "city": "Székesfehérvár", "index": 141, "query": "klímaszerelés" }, { "city": "Kecskemét", "index": 142, "query": "klímaszerelés" }, { "city": "Nyíregyháza", "index": 143, "query": "klímaszerelés" }, { "city": "Szombathely", "index": 144, "query": "klímaszerelés" }, { "city": "Veszprém", "index": 145, "query": "klímaszerelés" }, { "city": "Zalaegerszeg", "index": 146, "query": "klímaszerelés" }, { "city": "Kaposvár", "index": 147, "query": "klímaszerelés" }, { "city": "Eger", "index": 148, "query": "klímaszerelés" }, { "city": "Tatabánya", "index": 149, "query": "klímaszerelés" }, { "city": "Budapest", "index": 150, "query": "könyvelőiroda" }, { "city": "Debrecen", "index": 151, "query": "könyvelőiroda" }, { "city": "Győr", "index": 152, "query": "könyvelőiroda" }, { "city": "Pécs", "index": 153, "query": "könyvelőiroda" }, { "city": "Szeged", "index": 154, "query": "könyvelőiroda" }, { "city": "Miskolc", "index": 155, "query": "könyvelőiroda" }, { "city": "Székesfehérvár", "index": 156, "query": "könyvelőiroda" }, { "city": "Kecskemét", "index": 157, "query": "könyvelőiroda" }, { "city": "Nyíregyháza", "index": 158, "query": "könyvelőiroda" }, { "city": "Szombathely", "index": 159, "query": "könyvelőiroda" }, { "city": "Veszprém", "index": 160, "query": "könyvelőiroda" }, { "city": "Zalaegerszeg", "index": 161, "query": "könyvelőiroda" }, { "city": "Kaposvár", "index": 162, "query": "könyvelőiroda" }, { "city": "Eger", "index": 163, "query": "könyvelőiroda" }, { "city": "Tatabánya", "index": 164, "query": "könyvelőiroda" }, { "city": "Budapest", "index": 165, "query": "fogászat" }, { "city": "Debrecen", "index": 166, "query": "fogászat" }, { "city": "Győr", "index": 167, "query": "fogászat" }, { "city": "Pécs", "index": 168, "query": "fogászat" }, { "city": "Szeged", "index": 169, "query": "fogászat" }, { "city": "Miskolc", "index": 170, "query": "fogászat" }, { "city": "Székesfehérvár", "index": 171, "query": "fogászat" }, { "city": "Kecskemét", "index": 172, "query": "fogászat" }, { "city": "Nyíregyháza", "index": 173, "query": "fogászat" }, { "city": "Szombathely", "index": 174, "query": "fogászat" }, { "city": "Veszprém", "index": 175, "query": "fogászat" }, { "city": "Zalaegerszeg", "index": 176, "query": "fogászat" }, { "city": "Kaposvár", "index": 177, "query": "fogászat" }, { "city": "Eger", "index": 178, "query": "fogászat" }, { "city": "Tatabánya", "index": 179, "query": "fogászat" }, { "city": "Budapest", "index": 180, "query": "autószerviz" }, { "city": "Debrecen", "index": 181, "query": "autószerviz" }, { "city": "Győr", "index": 182, "query": "autószerviz" }, { "city": "Pécs", "index": 183, "query": "autószerviz" }, { "city": "Szeged", "index": 184, "query": "autószerviz" }, { "city": "Miskolc", "index": 185, "query": "autószerviz" }, { "city": "Székesfehérvár", "index": 186, "query": "autószerviz" }, { "city": "Kecskemét", "index": 187, "query": "autószerviz" }, { "city": "Nyíregyháza", "index": 188, "query": "autószerviz" }, { "city": "Szombathely", "index": 189, "query": "autószerviz" }, { "city": "Veszprém", "index": 190, "query": "autószerviz" }, { "city": "Zalaegerszeg", "index": 191, "query": "autószerviz" }, { "city": "Kaposvár", "index": 192, "query": "autószerviz" }, { "city": "Eger", "index": 193, "query": "autószerviz" }, { "city": "Tatabánya", "index": 194, "query": "autószerviz" }, { "city": "Budapest", "index": 195, "query": "szállítmányozás" }, { "city": "Debrecen", "index": 196, "query": "szállítmányozás" }, { "city": "Győr", "index": 197, "query": "szállítmányozás" }, { "city": "Pécs", "index": 198, "query": "szállítmányozás" }, { "city": "Szeged", "index": 199, "query": "szállítmányozás" }, { "city": "Miskolc", "index": 200, "query": "szállítmányozás" }, { "city": "Székesfehérvár", "index": 201, "query": "szállítmányozás" }, { "city": "Kecskemét", "index": 202, "query": "szállítmányozás" }, { "city": "Nyíregyháza", "index": 203, "query": "szállítmányozás" }, { "city": "Szombathely", "index": 204, "query": "szállítmányozás" }, { "city": "Veszprém", "index": 205, "query": "szállítmányozás" }, { "city": "Zalaegerszeg", "index": 206, "query": "szállítmányozás" }, { "city": "Kaposvár", "index": 207, "query": "szállítmányozás" }, { "city": "Eger", "index": 208, "query": "szállítmányozás" }, { "city": "Tatabánya", "index": 209, "query": "szállítmányozás" }, { "city": "Budapest", "index": 210, "query": "ipari gép javítás" }, { "city": "Debrecen", "index": 211, "query": "ipari gép javítás" }, { "city": "Győr", "index": 212, "query": "ipari gép javítás" }, { "city": "Pécs", "index": 213, "query": "ipari gép javítás" }, { "city": "Szeged", "index": 214, "query": "ipari gép javítás" }, { "city": "Miskolc", "index": 215, "query": "ipari gép javítás" }, { "city": "Székesfehérvár", "index": 216, "query": "ipari gép javítás" }, { "city": "Kecskemét", "index": 217, "query": "ipari gép javítás" }, { "city": "Nyíregyháza", "index": 218, "query": "ipari gép javítás" }, { "city": "Szombathely", "index": 219, "query": "ipari gép javítás" }, { "city": "Veszprém", "index": 220, "query": "ipari gép javítás" }, { "city": "Zalaegerszeg", "index": 221, "query": "ipari gép javítás" }, { "city": "Kaposvár", "index": 222, "query": "ipari gép javítás" }, { "city": "Eger", "index": 223, "query": "ipari gép javítás" }, { "city": "Tatabánya", "index": 224, "query": "ipari gép javítás" } ], "note": "Planned city/query combinations are configuration only. No rows or spend are attributed to the 209 unused combinations.", "total_planned_queries": 225, "unused_planned_queries": 209 }, "input_pools": [ { "current_admitted": 1578, "current_processed": 735, "current_ready": 50, "metadata": { "candidates_sha256": "80a50b2892ba98b26c0a946bb19a84f0b2c494fb1809543f769284e412e89527", "created_at": "2026-09-22T17:13:46.369060+00:00", "exclusions_receipt_id": "a3ac96bb9b2b9e0afb416a521b66f513d91dcf016422eb2d43ad5ae54c47ec0d", "model": "google/gemini-2.5-flash", "recovered": 4000, "requested": 4000, "selection": "Hungarian contractor/home-service candidate pool; current workspace and historic exclusions; unique company/email/domain; downstream fit required" }, "path": "production-20260922/source-pool.json", "priority": 0, "raw_occurrence_count": 4000, "raw_unique_source_ids": 4000, "records": 4000, "sha256": "dc26fb465e636ee5e76621bcf9f59471eca97d7e198925f15b744e4c12123f8d" }, { "current_admitted": 383, "current_processed": 5, "current_ready": 3, "metadata": { "append_after_frozen_pool_sha256": "80a50b2892ba98b26c0a946bb19a84f0b2c494fb1809543f769284e412e89527", "candidates_sha256": "28b831b15e83e979e4fdfabe571927bf4a155b00974beec0e95ff459d8227158", "created_at": "2026-09-23T08:29:02.036570+00:00", "exclusions_receipt_id": "a3ac96bb9b2b9e0afb416a521b66f513d91dcf016422eb2d43ad5ae54c47ec0d", "model": "google/gemini-2.5-flash", "recovered": 385, "requested": 2000, "selection": "APPEND STAGING ONLY: remaining source-niche or strong trade signal candidates; actual website fit and deliverability unverified", "source_db_sha256": "2c8c58b7959bb9dfcc3e60cd778065fdfa08a0688be3f629e2f5d9219e4e7f5a", "status": "STAGED_NOT_LIVE_NOT_VERIFIED" }, "path": "production-extension-20260923/source-pool.json", "priority": 1, "raw_occurrence_count": 385, "raw_unique_source_ids": 385, "records": 385, "sha256": "a33759eb4d4cb0dc611e2c9ea962140b3c6e1b8c843b3b1a92223395cca09579" }, { "current_admitted": 70, "current_processed": 0, "current_ready": 0, "metadata": { "append_after_frozen_pool_sha256": "80a50b2892ba98b26c0a946bb19a84f0b2c494fb1809543f769284e412e89527", "candidates_sha256": "8c669f1132d0e8337815984599eba403b9a0b1703718a01ab012b7f271556b8c", "created_at": "2026-09-23T08:38:26.548880+00:00", "exclusions_receipt_id": "a3ac96bb9b2b9e0afb416a521b66f513d91dcf016422eb2d43ad5ae54c47ec0d", "model": "google/gemini-2.5-flash", "recovered": 2000, "requested": 2000, "selection": "APPEND STAGING ONLY: additional unused identity-safe prospects; weak lexical ranking is NOT fit evidence; actual website fit and deliverability unverified", "source_db_sha256": "2c8c58b7959bb9dfcc3e60cd778065fdfa08a0688be3f629e2f5d9219e4e7f5a", "status": "STAGED_NOT_LIVE_NOT_VERIFIED" }, "path": "prospecting-extension-20260923/source-pool.json", "priority": 2, "raw_occurrence_count": 2000, "raw_unique_source_ids": 2000, "records": 2000, "sha256": "32288040ec1f6e5b246870012c8c6ff660ff52e8003c6b321bd24f23488bdc7d" }, { "current_admitted": 0, "current_processed": 0, "current_ready": 0, "metadata": { "created_at": "2026-09-23T16:03:06.937874+00:00", "owner": "maps-wave2-20260923" }, "path": "maps-wave2-20260923/reservations.json", "priority": 3, "raw_occurrence_count": 309, "raw_unique_source_ids": 309, "records": 309, "sha256": "aad63c762559d2eee5a62c7039605785548969d28460cef9dbad445046376097" }, { "current_admitted": 0, "current_processed": 0, "current_ready": 0, "metadata": { "candidates_sha256": "93109cc1a036222a8dfe3b3db2636b5ae70911aa06a390d494be169a30e5c653", "created_at": "2026-09-23T09:32:47.284440+00:00", "exclusions_receipt_id": "025e8322384c6625281db3cf3002cb425d085256578ce543182c7411774a4b5e", "model": "openai/gpt-5.6-luna", "recovered": 29, "requested": 29, "selection": "Exact native- and Luna-accepted Maps pilot candidates, email changes separately source-proven" }, "path": "maps-extension-20260923/source-pool.json", "priority": 4, "raw_occurrence_count": 29, "raw_unique_source_ids": 29, "records": 29, "sha256": "a4e05918bfdee18a90904308f8ea0e0847e73665b57df5fbbd7d3afd7d836674" } ], "legacy_historical_provenance": { "current_bank_candidate_contribution": 0, "current_bank_counts": { "companies": 0, "domains": 0, "emails": 0, "source_occurrences": 0 }, "current_bank_note": "The current canonical lead-bank source_occurrences table is empty at audit time. The retained source-pool files supply the 2,031 admitted legacy candidates. Every admitted legacy occurrence matches the separate dated source-bank snapshot by ID, source and checksum.", "prior_maps_receipts": [ { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Budapest, Magyarország", "maxCrawledPlacesPerSearch": 100, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos", "vízvezeték szerelő", "szobafestő" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "1FEQB1T7kZYIeOmak", "finished_at": "2026-09-23T10:35:27.835Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 2.41, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 586, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-00-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-00-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-00-actor-run.json" }, "run_id": "pWzaexJUN8vX87tiU", "started_at": "2026-09-23T10:33:51.641Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Debrecen, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "bcrNW3dKr83SOpIoi", "finished_at": "2026-09-23T11:49:20.642Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 87, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-01-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-01-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-01-actor-run.json" }, "run_id": "GnC1xrHs4H7o1Uw3s", "started_at": "2026-09-23T11:47:34.424Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Győr, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "VhzKbuze8xyvQ1VjN", "finished_at": "2026-09-23T12:00:09.016Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 70, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-02-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-02-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-02-actor-run.json" }, "run_id": "q51Pa5GBR4YfzWlfa", "started_at": "2026-09-23T11:58:34.901Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Pécs, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "hRhbu7S1XJh2NJulW", "finished_at": "2026-09-23T12:14:04.539Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 52, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-03-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-03-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-03-actor-run.json" }, "run_id": "YDqhUQutgruxVadWK", "started_at": "2026-09-23T12:12:30.603Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Szeged, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "ujGSMGPg15Zygp5Jv", "finished_at": "2026-09-23T12:25:27.570Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 67, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-04-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-04-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-04-actor-run.json" }, "run_id": "wmiCcX8Sy5hLcVIot", "started_at": "2026-09-23T12:23:42.680Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Miskolc, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "TWoiDPMkcUUdlYBvF", "finished_at": "2026-09-23T12:35:25.909Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 44, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-05-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-05-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-05-actor-run.json" }, "run_id": "tVgl53jpQWG8gHlKR", "started_at": "2026-09-23T12:33:53.256Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Székesfehérvár, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "7PigdDsQ0izTaNDZD", "finished_at": "2026-09-23T12:43:33.703Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 61, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-06-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-06-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-06-actor-run.json" }, "run_id": "PZ5HNJdakZbCgmkrD", "started_at": "2026-09-23T12:41:56.366Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Kecskemét, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "yf4wNhmhrRfV9GpQD", "finished_at": "2026-09-23T12:56:28.185Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 42, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-07-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-07-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-07-actor-run.json" }, "run_id": "QMwiOEGDkM3ctCao2", "started_at": "2026-09-23T12:54:17.314Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Nyíregyháza, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "tMcWZXzyTrebv6ovP", "finished_at": "2026-09-23T13:24:36.970Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 55, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-08-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-08-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-08-actor-run.json" }, "run_id": "aAxS9VtIYZ19KWr8b", "started_at": "2026-09-23T13:21:46.051Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Szombathely, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "8PGirekhXtNiramYo", "finished_at": "2026-09-23T13:35:50.373Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 35, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-09-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-09-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-09-actor-run.json" }, "run_id": "anpZyFqQmLQoGTiUA", "started_at": "2026-09-23T13:33:17.479Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Magyarország", "maxCrawledPlacesPerSearch": 60, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "vízvezeték szerelő Debrecen", "szobafestő Debrecen", "vízvezeték szerelő Győr", "szobafestő Győr", "vízvezeték szerelő Pécs", "szobafestő Pécs", "vízvezeték szerelő Szeged", "szobafestő Szeged", "vízvezeték szerelő Miskolc", "szobafestő Miskolc", "vízvezeték szerelő Székesfehérvár", "szobafestő Székesfehérvár", "vízvezeték szerelő Kecskemét", "szobafestő Kecskemét", "vízvezeték szerelő Nyíregyháza", "szobafestő Nyíregyháza", "vízvezeték szerelő Szombathely", "szobafestő Szombathely" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "WupQAmJqDGZUFpgj4", "finished_at": "2026-09-23T13:54:16.053Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 4.33, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 892, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-10-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-10-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-10-actor-run.json" }, "run_id": "0mMImGh8mGlXU2OER", "started_at": "2026-09-23T13:39:33.805Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "burkoló Debrecen", "klímaszerelő Debrecen", "burkoló Győr", "klímaszerelő Győr", "burkoló Pécs", "klímaszerelő Pécs", "burkoló Szeged", "klímaszerelő Szeged", "burkoló Miskolc", "klímaszerelő Miskolc" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "egAiz3RhNVv2HKH3Z", "finished_at": "2026-09-23T14:44:34.494Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 2.01, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 372, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-11-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-11-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-11-actor-run.json" }, "run_id": "3vvOgHTx35wiDc65b", "started_at": "2026-09-23T14:32:29.631Z", "status": "SUCCEEDED" }, { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "tetőfedő", "villanyszerelő" ], "skipClosedPlaces": false, "website": "allPlaces" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "0xfgKoCAJP2fNLLxG", "finished_at": "2026-09-23T09:19:37.981Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.5, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 400, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/actor-run.json" }, "run_id": "noV86emu3XLEDnOF2", "started_at": "2026-09-23T09:19:04.390Z", "status": "SUCCEEDED" } ], "prior_purchased_datasets": [ { "below_retrieval_limit": true, "bytes": 1255061, "dataset_id": "xqRqADT0wWoWv6nIc", "observed_country_codes": [ "HU", "None" ], "observed_search_strings": [ "csomagolóanyag gyártás", "elektronikai gyártás", "vegyipari gyártás", "építőanyag gyártás" ], "original_actor_input": null, "original_actor_run_receipt": null, "path": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/purchased-xqRqADT0wWoWv6nIc.json", "raw_stage_semantics": "Retained purchased dataset file. Original actor input/run not recovered by this audit.", "record_count": 400, "records_type": "list", "retrieval_code_path": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/pilot.py", "retrieval_code_sha256": "d71be00b3cd96ce85fd36edbf226ee6147f8e85140a23b10c1cb3bb78628085f", "sha256": "fc265bdf972537ed39cc71edebc3d6ee6e2349e0849b73cf33427bc76a7878cd", "stored_retrieval_limit": 1100 }, { "below_retrieval_limit": true, "bytes": 282213, "dataset_id": "mS7tXRgpO3yRpFpHp", "observed_country_codes": [ "HU", "None" ], "observed_search_strings": [ "bútorgyártás" ], "original_actor_input": null, "original_actor_run_receipt": null, "path": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/purchased-mS7tXRgpO3yRpFpHp.json", "raw_stage_semantics": "Retained purchased dataset file. Original actor input/run not recovered by this audit.", "record_count": 100, "records_type": "list", "retrieval_code_path": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/pilot.py", "retrieval_code_sha256": "d71be00b3cd96ce85fd36edbf226ee6147f8e85140a23b10c1cb3bb78628085f", "sha256": "737d85e1575e3f55d720a56a48249dfe2dd26654851dffec17b84765fa4d6bd1", "stored_retrieval_limit": 1100 } ], "semantics": "Stored imported occurrences in the dated 2026-09-23 lead-bank snapshot. These are not original scraped records, may duplicate one company across sources/versions, and are not the current-run input denominator.", "snapshot_date": "2026-09-23", "sources": [ { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Belgium", "Budapest", "Debrecen", "Germany", "Hungary", "Netherlands", "United Kingdom", "United States", "mixed" ], "imported_distinct_companies": 1336, "imported_distinct_domains": 1331, "imported_distinct_emails": 1569, "imported_occurrences": 3043, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "1462n8bFK61jYMlA_OSo98Lm6zxiszEnIFVVorS4DtyE", "stored_niches": [ "Accounting", "Adatelemzés és üzleti intelligencia", "Adatintelligencia és üzleti elemzés", "Alkoholtermékek forgalmazása", "Animation", "Apparel & Fashion", "Architecture & Planning", "Automotive", "Autóipari technológia", "Autóipari és gépipari alkatrészgyártás", "Autóipari és épületfólia-forgalmazás", "Autóvegyszerek és autókozmetika", "Banking", "Befektetési és üzleti szolgáltatások", "Bor- és szeszesital-kereskedelem", "Building Materials", "Chemicals", "Civil Engineering", "Computer Hardware", "Construction", "Consumer Goods", "Consumer Services", "Design", "Digitális marketing és stratégiai tanácsadás", "Digitális reklám és média", "Digitális transzformáció és adatkezelés", "Digitális ügynökség és szoftverfejlesztés", "E-kereskedelem és informatika", "E-learning", "Education Management", "Egészségügy", "Electrical/electronic Manufacturing", "Entertainment", "Environmental Services", "Events Services", "Farming", "Felhőalapú kapcsolati központ (CCaaS) szoftver", "Felnőttképzés és üzleti oktatás", "Financial Services", "Fogyasztói elektronika nagykereskedelem", "Food & Beverages", "Food Production", "Fémipar", "Fémipar és gépipar", "Fémöntészet és fémfeldolgozás", "Gambling & Casinos", "Glass, Ceramics & Concrete", "Graphic Design", "Gyógyszeripar", "Gyógyszeripar és biotechnológia", "Health, Wellness & Fitness", "Higher Education", "Hospitality", "Human Resources", "Humánerőforrás szolgáltatások", "Humánerőforrás-szolgáltatás", "Háztartásigép-alkatrész kereskedelem és szerviz", "IT biztonság és hálózat", "IT szolgáltatások", "IT szolgáltatások és digitális transzformáció", "IT szolgáltatások és tanácsadás", "IT szolgáltatások, pénzügyi és biztosítási szektor", "IT tanácsadás", "IT és digitális technológia", "IT és pénzügyi toborzás", "IT és telekommunikációs megfelelőség", "IT és távközlés", "Ideiglenes épületinfrastruktúra és konténertechnológia", "Industrial Automation", "Informatika", "Informatika / Szoftverfejlesztés", "Informatika és automatizálás", "Informatika és szoftverfejlesztés", "Informatika és vállalatirányítás", "Informatika és épületinformatika", "Informatikai szolgáltatások", "Information Services", "Information Technology", "Information Technology & Services", "Információtechnológia", "Ingatlan", "Ingatlanfejlesztés", "Ingatlanfejlesztés és -befektetés", "Ingatlanfejlesztés és befektetés", "Insurance", "Internet", "Investment Management", "Ipari automatizálás és gépgyártás", "Ipari beszállítás és gépészet", "Ipari gyártás és anyagmozgatás", "Ipari gépgyártás és energetika", "Ipari lézeres anyagmegmunkálás", "Ipari takarító- és kommunális gépgyártás", "Ipari és kereskedelmi HVAC berendezések", "Irodaellátás", "Jog és szellemi tulajdon", "Játék- és szórakoztatóipar", "Kerékpár-nagykereskedelem", "Kiberbiztonság", "Kontrakt bútor és belsőépítészet", "Kozmetikai forgalmazás", "Kreatív ügynökség", "Lakberendezés és kertészet", "Leisure, Travel & Tourism", "Logistics & Supply Chain", "Logisztika és futárszolgálat", "Logisztika és szállítmányozás", "Luxus bútor és belsőépítészet", "Légiközlekedési szolgáltatások", "Machinery", "Management Consulting", "Marketing & Advertising", "Marketing és kommunikációs szolgáltatások", "Marketing és reklámügynökség", "Marketing ügynökség", "Mechanical Or Industrial Engineering", "Megújuló energia", "Mezőgazdaság és állattenyésztés", "Mérnöki szoftverek és tanácsadás", "Mérnöki szolgáltatások", "Mérnöki szolgáltatások (épületgépészet, épületvillamosság)", "Mérnöki és IT szolgáltatások", "Nemzetközi kereskedelem és logisztika", "Oil & Energy", "Okos mobilitás és forgalomirányítás", "Okosotthon és épületautomatizálás", "Online Media", "Online marketing", "Online reklámügynökség", "Online társkeresés", "Package/freight Delivery", "Packaging & Containers", "Paper & Forest Products", "Pharmaceuticals", "Plastics", "Precíziós szerszámgyártás", "Printing", "Professional Training & Coaching", "Pályázatírók", "Pénzügyi szolgáltatások", "Pénzügyi technológia (FinTech)", "Real Estate", "Recreational Facilities & Services", "Reklám és marketing", "Rendezvényszervezés és humánerőforrás", "Rendezvényszervezés és utazás", "Renewables & Environment", "Retail", "Semiconductors", "Sports", "Staffing & Recruiting", "Szállítmányozás és logisztika", "Szépségipar", "Szórakoztatás", "Szórakoztatás és rendezvényszervezés", "Technológia és kreatívipar", "Technológiai szolgáltatások", "Telecommunications", "Tetőfedő anyagok", "Think Tanks", "Transportation/trucking/railroad", "Turizmus és utazás", "Távközlés és energiaipar", "Távközlés és ipari automatizálás", "Tömítés- és szigeteléstechnika", "Utilities", "Vegyi anyagok nagykereskedelme", "Vegyipar", "Vendéglátás és kávékereskedelem", "Vendéglátás és turizmus", "Venture Capital & Private Equity", "Vezetési és IT tanácsadás", "Videójáték fejlesztés", "Villamosipar és energetika", "Világítástechnika és elektromos szerelés", "Vizuális effektek (VFX)", "Warehousing", "Wholesale", "Wireless", "accounting", "apparel & fashion", "architecture & planning", "automotive", "aviation & aerospace", "banking", "chemicals", "civic & social organization", "construction", "consumer services", "dairy", "design", "dísznövénykereskedelem és tájépítészet", "education management", "egészségügy", "entertainment", "environmental services", "events services", "facilities services", "food & beverages", "food production", "furniture", "gyógyszeripar", "gépgyártás", "health, wellness & fitness", "hospitality", "human resources", "informatikai szolgáltatások", "information technology & services", "játékfejlesztés és szoftverfejlesztés", "legal services", "leisure, travel & tourism", "logistics & supply chain", "machinery", "management consulting", "market research", "marketing & advertising", "mechanical or industrial engineering", "média és kiadás", "mérnöki", "nagykereskedelem", "nonprofit organization management", "nukleáris medicina / radiogyógyszerek", "nyelvi szolgáltatások", "oktatástechnológia", "pharmaceuticals", "printing", "professional training & coaching", "pénzügyi technológia (fintech)", "real estate", "retail", "semiconductors", "sporting goods", "sportruházat", "staffing & recruiting", "szoftverfejlesztés", "szoftverfejlesztő", "szépségipar", "technológia", "telecommunications", "translation & localization", "transportation/trucking/railroad", "unclassified", "vegyipar", "wholesale", "Élelmiszeripar és mezőgazdaság", "Élelmiszeripar, fogyasztási cikkek", "Építőanyag kereskedelem és kivitelezés", "Építőanyag-gyártás", "Építőipar", "Építőipar (válaszfalrendszerek és üveg megoldások)", "Építőipar, tervezés (AEC)", "Építőipar, épületszerkezetek", "Étkeztetés / Franchise", "Éttermi vendéglátás", "Ügyvédi iroda", "építőipari technológia", "Űripar / űrtechnológia" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Alap", "Budakeszi", "Budaoers", "Budapest", "Debrecen", "Erd", "Goedoello", "Gyermely", "Gyor", "Hatvan", "Hungary", "Kecskemet", "Marbella", "Miskolc", "Nagytarcsa", "Pecs", "Roeszke", "Siofok", "Szeged", "Szekesfehervar", "Szentendre", "Szentes", "Szombathely", "Telki", "Veszprem", "mixed" ], "imported_distinct_companies": 3203, "imported_distinct_domains": 3199, "imported_distinct_emails": 6657, "imported_occurrences": 13308, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "17aN3vEQ2eVfs4zQ76dZSBGT48POxf5Zns2lODVv3SwU", "stored_niches": [ "A B2B technology company specializing in providing and supporting advanced engineering and R&D software solutions, acting as an official reseller and service partner for products like MATLAB, Simulink, and COMSOL.", "Accounting", "Adatelemzés és üzleti intelligencia", "Adatintelligencia és üzleti elemzés", "Airlines/aviation", "Alkoholtermékek forgalmazása", "Animation", "Apparel & Fashion", "Applied Research and Development Institute, providing R&D, consulting, and analytical services.", "Architecture & Planning", "Arts & Crafts", "Automotive", "Autóipari és épületfólia-forgalmazás", "Aviation & Aerospace", "B2B Software company specializing in business management software (accounting, payroll, invoicing) for small and medium-sized enterprises (SMEs).", "B2B professional services firm specializing in tax consulting, accounting, and business advisory.", "Banking", "Befektetési és üzleti szolgáltatások", "Biotechnology", "Building Materials", "Chemicals", "Civic & Social Organization", "Civil Engineering", "Computer & Network Security", "Computer Games", "Computer Hardware", "Computer Networking", "Construction", "Consumer Electronics", "Consumer Goods", "Consumer Services", "Cosmetics", "Dairy", "Design", "Digitális marketing és stratégiai tanácsadás", "Digitális reklám és média", "E-kereskedelem és informatika", "E-learning", "Education Management", "Egészségügy", "Electrical/electronic Manufacturing", "Enterprise IT services company specializing in custom software development, process automation, and business intelligence.", "Entertainment", "Environmental Services", "Events Services", "Executive Office", "Facilities Services", "Farming", "Felhőalapú kapcsolati központ (CCaaS) szoftver", "Financial Services", "Financial Services, specifically asset financing and leasing for vehicles, agricultural machinery, and equipment.", "Fintech company providing B2B software solutions for the financial services industry, specializing in credit management.", "Fishery", "Food & Beverages", "Food Production", "Fund-raising", "Furniture", "Fémipar", "Fémöntészet és fémfeldolgozás", "Gambling & Casinos", "Glass, Ceramics & Concrete", "Government Administration", "Graphic Design", "Gyógyszeripar", "HR", "Health, Wellness & Fitness", "Higher Education", "Hospital & Health Care", "Hospitality", "Human Resources", "Humánerőforrás szolgáltatások", "Háztartásigép-alkatrész kereskedelem és szerviz", "IT szolgáltatás", "IT szolgáltatások", "IT szolgáltatások, pénzügyi és biztosítási szektor", "IT tanácsadás", "IT és pénzügyi toborzás", "IT és telekommunikációs megfelelőség", "Ideiglenes épületinfrastruktúra és konténertechnológia", "Import & Export", "Indeterminable. The provided website content is a technical prerequisite message ('You need to enable JavaScript to run this app') and offers no information about the company's industry or niche.", "Industrial Automation", "Industrial Manufacturing, specializing in the production and servicing of transformers and electric rotating machines.", "Informatika", "Informatika / Szoftverfejlesztés", "Informatika és szoftverfejlesztés", "Informatikai szolgáltatások", "Information Services", "Information Technology", "Information Technology & Services", "Information Technology / Digital Media. Specifically, they develop and operate a large network of high-traffic web properties focused on live streaming technology and online payment systems.", "Információtechnológia", "Ingatlan", "Insurance", "International Affairs", "International Trade & Development", "Internet", "Investment Banking", "Investment Management", "Ipari automatizálás és gépgyártás", "Ipari beszállítás és gépészet", "Ipari gyártás és anyagmozgatás", "Irodaellátás", "Kontrakt bútor és belsőépítészet", "Legal Services", "Leisure, Travel & Tourism", "Logistics & Supply Chain", "Luxury Goods & Jewelry", "Luxus bútor és belsőépítészet", "Machinery", "Management Consulting", "Market Research", "Marketing & Advertising", "Marketing és kommunikációs szolgáltatások", "Marketing és reklámügynökség", "Mechanical Or Industrial Engineering", "Media Production", "Medical Devices", "Medical Practice", "Megújuló energia", "Mezőgazdaság és állattenyésztés", "Mining & Metals", "Museums & Institutions", "Mérnöki szolgáltatások", "Mérnöki és IT szolgáltatások", "Nonprofit Organization Management", "Oil & Energy", "Okosotthon és épületautomatizálás", "Online Media", "Online marketing", "Online reklámügynökség", "Outsourcing/offshoring", "Package/freight Delivery", "Packaging & Containers", "Paper & Forest Products", "Pharmaceuticals", "Plastics", "Printing", "Professional Training & Coaching", "Public Policy", "Public Relations & Communications", "Publishing", "Pályázatírók", "Pénzügyi szolgáltatások", "Railroad Manufacture", "Real Estate", "Recreational Facilities & Services", "Rendezvényszervezés és humánerőforrás", "Rendezvényszervezés és utazás", "Renewables & Environment", "Research", "Restaurants", "Retail", "Semiconductors", "Sporting Goods", "Sports", "Staffing & Recruiting", "Szállítmányozás és logisztika", "Szórakoztatás", "Szórakoztatás és rendezvényszervezés", "Technology/Software company specializing in translation and localization management solutions.", "Technológiai szolgáltatások", "Telecommunications", "Textiles", "Think Tanks", "Tobacco", "Translation & Localization", "Transportation/trucking/railroad", "Távközlés és energiaipar", "Tömítés- és szigeteléstechnika", "Utilities", "Vendéglátás és turizmus", "Venture Capital & Private Equity", "Vezetési és IT tanácsadás", "Warehousing", "Wholesale", "Wireless", "accounting", "additív gyártóipar", "airlines/aviation", "animation", "apparel & fashion", "architecture & planning", "automatizálási", "automotive", "autóipar", "autóipari", "autóipari alkatrészek gyártása", "aviation & aerospace", "banking", "betongyártás", "bicikligyártás", "building materials", "chemicals", "civic & social organization", "computer & network security", "computer games", "computer hardware", "computer networking", "construction", "consumer services", "csiszolóanyag-gyártás", "csomagolóanyag-gyártás", "dairy", "darugépgyártás", "design", "e-kereskedelmi", "e-learning", "education management", "egészségügyi", "electrical/electronic manufacturing", "elektronikai", "energetikai", "entertainment", "environmental services", "events services", "facilities services", "financial services", "food & beverages", "food production", "fund-raising", "furniture", "fémipar", "fémipari", "gyártás", "gyártó", "gyógyszergyártás", "gyógyszeripar", "gyógyszeripari", "gépeséggyártás", "gépgyártás", "gépipar", "gépipari", "health, wellness & fitness", "hirdetési", "hospitality", "human resources", "industrial automation", "informatika", "informatikai", "informatikai szolgáltatások", "information services", "information technology & services", "ingatlanpiaci", "ingatlanüzemeltetés", "insurance", "international affairs", "international trade & development", "internet", "intralogisztika", "investment banking", "investment management", "ipari", "izotópgyártás", "jogi", "juttatási", "játékfejlesztés és szoftverfejlesztés", "játékipari", "kereskedelem", "kereskedelmi", "kiadói", "kutatás", "kutatás-fejlesztési", "kutatási", "kémiai ipar", "környezetvédelmi", "közlekedési", "legal services", "leisure, travel & tourism", "logistics & supply chain", "logisztikai", "légiipari", "létesítménygazdálkodási", "machinery", "management consulting", "market research", "marketing", "marketing & advertising", "mechanical or industrial engineering", "medical devices", "medical practice", "mezőgazdaság", "mezőgazdasági", "mezőgazdasági eszközgyártás", "mezőgazdasági gépgyártás", "mining & metals", "média", "mérnöki", "műanyagipar", "nagykereskedelem", "nagykereskedelmi", "nonprofit organization management", "nukleáris medicina / radiogyógyszerek", "nyomdafesték-gyártás", "nyomdaipari", "oil & energy", "oktatási", "oktatástechnológia", "outsourcing/offshoring", "packaging & containers", "paper & forest products", "pharmaceuticals", "plastics", "printing", "professional training & coaching", "public policy", "public relations & communications", "pénzügy", "pénzügyi", "pénzügyi technológia (fintech)", "real estate", "recreational facilities & services", "rendezvényipari", "rendezvényszervező", "renewables & environment", "retail", "semiconductors", "sporting goods", "sportruházat", "sports", "staffing & recruiting", "szerszámgyártás", "szoftverfejlesztés", "szoftverfejlesztő", "szolgáltató", "szépségipar", "sörgyártás", "söripar", "tanácsadó", "technológia", "technológiai", "telecommunications", "textiles", "think tanks", "translation & localization", "transportation/trucking/railroad", "turisztikai", "távközlési", "unclassified", "utilities", "vegyipar", "vegyipari eszközgyártás", "vegyipari technológiafejlesztés", "vendéglátás", "venture capital & private equity", "villamosipar", "világítástechnika", "városgazdálkodás", "warehousing", "wholesale", "writing & editing", "Élelmiszeripar, fogyasztási cikkek", "Építőanyag kereskedelem és kivitelezés", "Építőipar", "Építőipar (válaszfalrendszerek és üveg megoldások)", "Éttermi vendéglátás", "élelmiszer-nagykereskedelem", "élelmiszeripar", "élelmiszeripari", "építőipar", "építőipari", "építőipari technológia", "étkeztetés", "éttermi szolgáltatás", "ügyfélszolgálati", "üvegelemző ipar" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Belgium", "Budapest", "Canada", "France", "Gyermely", "Hungary", "Ireland", "Luxembourg", "Magyarország", "Netherlands", "Németország", "Spanyolország", "USA", "United Kingdom", "United States", "Vietnam" ], "imported_distinct_companies": 3931, "imported_distinct_domains": 3929, "imported_distinct_emails": 5728, "imported_occurrences": 10741, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "18l-qTgDfskAs5CgJX27wJXuCWk-SfyaPrYOwkBX3FAo", "stored_niches": [ "A B2B Business Process Outsourcing (BPO) company specializing in multilingual customer contact center services, enhanced with AI technology.", "A B2B technology company specializing in providing and supporting advanced engineering and R&D software solutions, acting as an official reseller and service partner for products like MATLAB, Simulink, and COMSOL.", "A full-service digital agency providing integrated services in creative communication, digital product development, performance marketing, and data solutions.", "A full-service, integrated marketing and communications agency.", "A multi-disciplinary business consulting and outsourcing group providing a wide range of professional services including finance, IT, HR, and management consulting.", "Accounting", "Advertising and Marketing. More specifically, a global marketing, communication, and digital transformation holding company.", "Airlines/aviation", "Alcoholic beverage manufacturer and distributor. They produce their own iconic Hungarian spirits and also distribute major international brands.", "Alcoholic beverage producer and distributor. They manufacture their own iconic Hungarian spirits and also distribute major international brands in Hungary.", "Apparel & Fashion", "Applied Research and Development Institute, providing R&D, consulting, and analytical services.", "Architecture & Planning", "Automotive", "Automotive / Car Dealership. This is inferred from the company name ('Autó' means 'Car'), as the provided website content is a default NGINX server page and contains no information about the company's business.", "Automotive / Transportation, specifically in the car rental services niche.", "Automotive and Transportation Technology, specializing in V2X (Vehicle-to-Everything) communication solutions for smart infrastructure and connected vehicles.", "Automotive industry, specifically a large car dealership network that sells new and used cars, offers fleet management services, and provides vehicle maintenance.", "Automotive industry, specifically a large-scale car dealership and service center for new and used vehicles.", "Automotive industry, specifically a multi-brand car dealership and service center.", "Automotive industry, specifically a multi-brand dealership (Volvo, Ford, Hyundai, MG, Kawasaki etc.) and service center that also provides vehicle rental and fleet management.", "Aviation & Aerospace", "B2B Manufacturing of industrial components, specializing in enclosures, HMI systems, and mechanical systems.", "B2B SaaS (Software as a Service) company in the Tax Technology (TaxTech) niche, providing automated global tax compliance solutions.", "B2B SaaS (Software as a Service) company specializing in cloud contact center software.", "B2B Software company providing business management, accounting, and payroll software.", "B2B Software company specializing in business management software (accounting, payroll, invoicing) for small and medium-sized enterprises (SMEs).", "B2B professional services firm specializing in tax consulting, accounting, and business advisory.", "B2B supplier of promotional products and corporate gifts.", "B2B/B2G Management and IT Consulting firm.", "Biotechnology", "Biotechnology / AI in Drug Discovery. They provide a specialized AI-powered cell simulation platform for the pharmaceutical industry, specifically focused on oncology drug discovery and development.", "Blockchain Technology / Fintech, specializing in institutional cryptocurrency staking services (Staking-as-a-Service).", "Building Materials", "Business Process Outsourcing (BPO) / Contact Center Services, specializing in multilingual customer support, sales outsourcing, and AI-enhanced solutions.", "Business Process Outsourcing (BPO), specializing in multilingual and AI-enhanced contact center services.", "Catering / Food Services. Specifically, public and corporate catering (canteens/cafeterias), likely as a brand or division of Hungast.", "Chemical/Pharmaceutical industry. Specifically, a Contract Development and Manufacturing Organization (CDMO) providing R&D, pilot, and large-scale manufacturing services for APIs and intermediates.", "Chemicals", "Civil Engineering", "Civil Engineering and Construction, specializing as a civil contractor for large-scale infrastructure projects.", "Computer & Network Security", "Computer Games", "Construction", "Construction and Real Estate Development, specializing in architecture, project management, and general contracting for large-scale projects.", "Consumer Electronics", "Consumer Goods", "Consumer Services", "Corporate training and consulting company, specializing in organizational development, leadership training, and grant application management.", "Design", "Digital solutions and custom software development agency, specializing in IT systems, e-commerce, and AI development.", "E-commerce/Retail, specializing in beauty products, perfumes, fashion accessories, and jewelry.", "E-learning", "Education Management", "Education Technology (EdTech), specializing in interactive digital content and presentation software for the K-12 market.", "Education Technology (EdTech), specifically providing interactive digital educational software, content, and solutions for the K-12 market.", "Education. A private institute providing supplementary, English-language academic programs for high school students to prepare them for admission to elite international universities.", "Electrical/electronic Manufacturing", "Electronics manufacturing and engineering, specializing in Radio Frequency (RF) and Microwave solutions for the telecommunications, space, and defense sectors.", "Energy / Utilities, specializing in natural gas distribution.", "Energy / Utilities, specifically a natural gas transmission system operator (TSO).", "Energy/Utilities, specifically providing electricity and natural gas to non-residential customers.", "Enterprise IT services company specializing in custom software development, process automation, and business intelligence.", "Entertainment", "Environmental Services", "Events Services", "Events and Exhibitions industry, specifically providing venue rental, event organization, and related services.", "FMCG / Food & Beverage Manufacturing, specializing in snack foods.", "Farming", "Financial Services", "Financial Services / Banking. Niche: State-owned Export-Import Bank providing financing and credit insurance.", "Financial Services / InsurTech, specializing as an online insurance comparison and brokerage platform.", "Financial Services / Insurance. The company is a major insurance provider in Hungary, operating as the local subsidiary of the German SIGNAL IDUNA group.", "Financial Services / Insurtech, specializing as an online insurance comparison and brokerage platform.", "Financial Services, specializing in asset financing and leasing for vehicles, agricultural machinery, and other equipment.", "Financial Services, specializing in providing credit guarantees and suretyship for businesses.", "Financial Services, specializing in vehicle and production equipment leasing and financing.", "Financial Services, specifically Asset and Fund Management.", "Financial Services, specifically a credit guarantee institution.", "Financial Services, specifically a state-owned export credit agency (ECA) providing banking and insurance services.", "Financial Services, specifically an independent financial advisory and brokerage firm serving both individual (B2C) and corporate (B2B) clients.", "Financial Services, specifically asset financing and leasing for vehicles, agricultural machinery, and equipment.", "Financial Services, specifically investment services, asset management, and corporate finance.", "Financial Services, specifically providing credit guarantees and suretyship.", "Financial Technology (FinTech / WealthTech) company providing investment and wealth management software solutions.", "Financial Technology (Fintech) company providing national payment and interbank clearing system infrastructure.", "Financial Technology (Fintech) specializing in Buy Now, Pay Later (BNPL) solutions.", "Financial consulting and brokerage, specializing in insurance, pensions, and investments.", "Financial services, specializing in providing credit guarantees.", "Financial services, specifically an independent financial advisory and brokerage firm.", "Fintech company providing B2B software solutions for the financial services industry, specializing in credit management.", "Food & Beverages", "Food Production", "Furniture", "Glass, Ceramics & Concrete", "Global provider of professional information, software solutions, and services for the legal, tax & accounting, health, finance, and compliance sectors.", "Government Agency - International Trade and Development, focused on export promotion for Hungarian businesses.", "Government-related non-profit organization specializing in national spatial data management, geoinformatics, and e-construction systems.", "Governmental/Non-profit organization specializing in national geospatial data management and e-government services for public administration.", "Health, Wellness & Fitness", "Healthcare Technology (HealthTech), specifically providing enterprise-level virtual care platforms.", "Healthcare and Social Services, specializing in elderly care, housing, and social activities.", "High-end interior design and furnishing, providing both products (lighting, furniture) and services (procurement, design).", "Higher Education, specifically a University of Art and Design.", "Hospital & Health Care", "Hospitality", "Hospitality / Food & Beverage. Specifically, a fast-casual Asian (Thai) restaurant chain.", "Hospitality, specifically a hotel chain focusing on wellness, spa, and conference hotels.", "Human Resources", "Human Resources (HR) Services, specializing in labor leasing, recruitment, and payroll outsourcing.", "Human Resources (HR) Services, specializing in staffing, recruitment, and payroll outsourcing.", "Human Resources / Staffing. Specifically, a school cooperative (Iskolaszövetkezet) that provides student workers for companies.", "Human Resources / Staffing. Specifically, a school cooperative that provides student workers for temporary and part-time positions to businesses.", "Human Resources Services, specializing in staffing, recruitment, and payroll outsourcing.", "Human Resources and Staffing, specializing in student work placement (Iskolaszövetkezet / School Cooperative).", "Human resources development and consulting, specializing in corporate training, organizational development, and grant writing services.", "IT / SaaS company specializing in automated cloud cost management for Google Cloud Platform (GCP), and providing related data analytics and infrastructure solutions.", "IT / Software, specifically a Low-Code Business Process Automation (BPA) platform.", "IT Consulting and Services, specializing in custom software development, business process automation (RPA, BI), and Industry 4.0 solutions.", "IT Consulting and Software company specializing in Enterprise Resource Planning (ERP) systems for manufacturing and logistics industries.", "IT Services & Consulting, specializing in custom software development, AI solutions, and digital transformation, with a strong focus on the Fintech/Banking sector.", "IT Services / Software Development, specializing in enterprise-level Digital Experience Platforms (DXP) and B2B commerce solutions.", "IT Services and Software Development. Specifically, they provide custom software solutions, team outsourcing, and DevOps services.", "IT Services and Technology Consulting, specializing in custom software development, Microsoft Dynamics 365 implementation, Business Intelligence (BI), and AI solutions.", "IT Services and Technology Consulting, with a niche in AI-driven digital transformation and solutions for the Telecom and BFSI sectors.", "IT Services, specializing in Software Quality Assurance (QA), AI solutions, and business process automation.", "IT and Business Consulting, specializing in SAP solutions, business process outsourcing, and consulting for financial institutions.", "IT and Project Management Consulting, specializing in government-funded digital transformation programs (B2G).", "IT and Software Development company specializing in Enterprise Resource Planning (ERP) systems, IT services, and e-commerce solutions.", "IT consulting and services company specializing in business process automation, custom software development, and cloud solutions.", "IT services and consulting, specializing in Google Cloud Platform solutions.", "IT services and consulting, specializing in cloud-native solutions and application modernization.", "IT services and solutions provider, specializing in IT infrastructure, custom development, and cybersecurity.", "IT solutions and consulting company specializing in AI development, digital transformation, and infrastructure, with a strong focus on the banking and financial sector.", "IT szolgáltatás", "Import & Export", "Independent financial advisory and insurance brokerage firm.", "Indeterminable. The provided website content is a technical prerequisite message ('You need to enable JavaScript to run this app') and offers no information about the company's industry or niche.", "Industrial Automation", "Industrial Manufacturing, specializing in the production and servicing of transformers and electric rotating machines.", "Informatika és szoftverfejlesztés", "Informatika és vállalatirányítás", "Information Services", "Information Technology & Services", "Information Technology (IT) services and consulting, with a niche in solutions for the architecture, engineering, and construction (AEC) industry (BIM) and services for SMEs.", "Information Technology / Digital Media. Specifically, they develop and operate a large network of high-traffic web properties focused on live streaming technology and online payment systems.", "Information Technology and Cybersecurity, specializing in data protection, encrypted hardware, and data recovery services.", "Information Technology and Services, specializing in custom software development and IT consulting.", "Insurance", "Insurance provider offering a range of life and non-life insurance products.", "Insurance. Specifically, an online provider of personal insurance products.", "Insurance. The company is an online insurance provider.", "Internet", "Investment Banking", "Investment Management", "Legal Services", "Leisure, Travel & Tourism", "Logistics & Supply Chain", "Légiközlekedési szolgáltatások", "Machinery", "Management Consulting", "Management and IT consulting firm serving a wide range of sectors.", "Manufacturing company specializing in flooring and coverings for various sectors.", "Manufacturing company specializing in flooring and interior coverings.", "Manufacturing industry, specializing in innovative and sustainable packaging solutions for B2B companies.", "Manufacturing, specifically building materials and healthcare industry products.", "Manufacturing, specifically power tools for forestry, agriculture, landscaping, construction, and garden care.", "Manufacturing, specifically producing specialized flooring and coverings.", "Market Research", "Marketing & Advertising", "Marketing & Advertising, specifically a full-service integrated communications agency.", "Marketing and Advertising. Specifically, a full-service, independent creative and communications agency.", "Marketing and Communications Agency specializing in PR, branding, and integrated campaigns for corporate clients.", "Marketing and Communications agency specializing in integrated PR, branding, and digital campaigns.", "Mechanical Or Industrial Engineering", "Media Distribution and Publishing Services, specializing in magazine distribution, sales, and marketing.", "Media Production", "Media and Publishing, with a specific focus on business and financial news.", "Medical / Healthcare. The specific niche is unclear from the name alone, but it is likely a B2B provider of medical products or services to other healthcare professionals or organizations.", "Medical Devices", "Medical Diagnostics / Biotechnology. Specifically, the company manufactures and distributes in-vitro diagnostic (IVD) products, including hematology and coagulation reagents, and laboratory equipment.", "Medical Diagnostics / Biotechnology. The company manufactures and distributes in-vitro diagnostic (IVD) reagents, control materials, and laboratory equipment.", "Medical Practice", "Megújuló energia", "Non-profit Copyright Collective / Performing Rights Organization in the music industry.", "Non-profit membership association for individuals with high IQs.", "Nonprofit IT service and software development provider for the Hungarian government.", "Oil & Energy", "Online Media", "Outsourcing/offshoring", "Package/freight Delivery", "Pharmaceutical / Biotechnology, specializing in the research, development, manufacturing, and global supply of radiopharmaceutical products for nuclear medicine.", "Pharmaceuticals", "Pharmaceuticals / Life Sciences, specializing in the development, manufacturing, and global supply of radiopharmaceuticals and nuclear medicine.", "Plastics", "Printing", "Printing industry, specializing in commercial printing, manufacturing and distribution of office/educational supplies, and stamp making.", "Professional Training & Coaching", "Public Utility company specializing in water and sewage services.", "Publishing", "Pályázatírók", "Pénzügyi szolgáltatások", "Real Estate", "Real Estate Services, specializing in integrated facility and property management for commercial and industrial properties.", "Renewable energy, specializing in the design, installation, wholesale, and servicing of solar panel and heat pump systems.", "Renewables & Environment", "Research", "Research and Consulting, specializing in political and economic analysis, public opinion polling, and strategic consulting for corporate and governmental clients.", "Restaurants", "Retail", "Retail and Automotive Services, specifically a chain of convenience stores, gas stations, and express car washes.", "Semiconductors", "Software development company specializing in administrative and management systems for the public sector.", "Sports", "Staffing & Recruiting", "Technology and AI solutions provider, specializing in custom software development, cloud services, and legacy modernization for B2B clients.", "Technology/Software company specializing in translation and localization management solutions.", "Telecommunications", "Telecommunications infrastructure provider, focusing on B2B services.", "Telecommunications provider offering internet, cable TV, and phone services.", "Telecommunications, specifically a government-designated provider of critical communication services (EDR - Unified Digital Radio System) for emergency and public safety organizations.", "The company operates in the Information Technology (IT) services industry, with a focus on managed IT services, IT consulting, custom application development, and Building Information Modeling (BIM) solutions.", "Translation & Localization", "Transportation/trucking/railroad", "Undeterminable. The website content is a default template for the 'Sitecore' digital experience platform and does not describe the company's actual business. The company name 'MVM CEEnergy' suggests the company is in the energy sector.", "Undeterminable. The website is a default Apache installation test page and contains no information about the company's business activities.", "Undetermined. The website is under construction and provides no information about the company's activities.", "Unidentifiable from website content. The website displays a default 'Welcome to nginx!' page, indicating it is not configured. Based on the name 'Schiller Autó Család' ('Autó' is Hungarian for 'car'), the industry is likely Automotive, specifically a car dealership.", "Unknown. The website displays a default nginx server page, which provides no information about the company's industry. Based on the name 'Schiller Autó Család' ('Autó' means 'Car'), the company is likely in the automotive industry, possibly a car dealership.", "Urban Development and Cultural Management, specializing in the management and promotion of a major public park and its cultural institutions.", "Utilities", "Venture Capital & Private Equity", "Vezetési és IT tanácsadás", "Warehousing", "Wholesale", "Wholesale and retail trade of electrical supplies, lighting, automation components, and related technical products.", "accounting", "alkoholipar", "architecture & planning", "autóipari alkatrészek gyártása", "banking", "betongyártás", "computer & network security", "computer hardware", "consumer services", "electrical/electronic manufacturing", "elektronikai ipar", "environmental services", "facilities services", "food production", "gyártás", "gyógyszeripar", "gépipar", "human resources", "informatika", "information technology & services", "ingatlanüzemeltetés", "intralogisztika", "izotópgyártás", "jogi", "játékipari", "kereskedelem", "kiadás", "kutatás", "logistics & supply chain", "machinery", "management consulting", "marketing", "marketing & advertising", "minőségellenőrzés", "média", "mérnöki", "nyomdafesték-gyártás", "pharmaceuticals", "public relations & communications", "pénzügy", "semiconductors", "szoftverfejlesztés", "szoftverfejlesztő", "technológia", "technológiai", "unclassified", "vegyipar", "vegyipari technológiafejlesztés", "vendéglátás", "világítástechnika", "warehousing", "wholesale", "élelmiszeripar", "építőipar" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Austria", "Belgium", "Budaoers", "Budapest", "Erd", "Germany", "Gyermely", "Hatvan", "Hungary", "Ireland", "Luxembourg", "Magyarország", "Netherlands", "Poland", "Romania", "Switzerland", "Szekesfehervar", "United Kingdom", "country", "mixed" ], "imported_distinct_companies": 15974, "imported_distinct_domains": 7459, "imported_distinct_emails": 13507, "imported_occurrences": 36487, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "1CkNd0uyZGudx-CJy-jg_wXLdQTXdpmVxxjCgmo5MmSE", "stored_niches": [ "Alkoholtermékek forgalmazása", "Apparel & Fashion", "Architecture & Planning", "Automotive", "Autóipari és épületfólia-forgalmazás", "Building Materials", "Business Services", "Bútorgyártás", "Bútoripar és lakberendezés", "Capital Markets", "Chemicals", "Civil Engineering", "Computer & Network Security", "Computer Games", "Computer Hardware", "Construction", "Consumer Goods", "Consumer Services", "Cosmetics", "Dairy", "Design", "Electrical/electronic Manufacturing", "Electronics", "Environmental Services", "FMCG", "Facilities Services", "Farming", "Financial Services", "Food & Beverages", "Food Production", "Glass, Ceramics & Concrete", "Health, Wellness & Fitness", "Hospitality", "Import & Export", "Industrial Automation", "Information Services", "Information Technology & Services", "International Trade & Development", "Internet", "Ipari automatizálás és gépgyártás", "Leisure, Travel & Tourism", "Logistics & Supply Chain", "Luxury Goods & Jewelry", "Machinery", "Management Consulting", "Manufacturing", "Maritime", "Market Research", "Marketing & Advertising", "Mechanical Or Industrial Engineering", "Media Production", "Mérnöki szolgáltatások", "NOT DEFINED", "Outsourcing/offshoring", "Package/freight Delivery", "Packaging & Containers", "Paper & Forest Products", "Pharmaceuticals", "Plastics", "Printing", "Publishing", "Real Estate", "Renewables & Environment", "Restaurants", "Retail", "Retail & Consumer", "Semiconductors", "Sporting Goods", "Sports", "Staffing & Recruiting", "Tech & Software", "Telecommunications", "Textiles", "Tobacco", "Transportation/trucking/railroad", "Warehousing", "Wholesale", "automotive", "autóipar", "autóipari alkatrészek gyártása", "betongyártás", "building materials", "bútorgyártás", "chemicals", "construction", "elektronikai ipar", "energiaipar", "food & beverages", "food production", "fémipar", "gyógyszeripar", "gépgyártás", "human resources", "industrial automation", "industry", "ipari automatizáció", "izotópgyártás", "izotópipar", "járműgyártás", "járműipar", "kiskereskedelem", "kémiai ipar", "logistics & supply chain", "logisztika", "mezőgazdaság", "mérőeszköz-gyártás", "műanyagfeldolgozás", "műanyaggyártás", "műanyagipari csomagolásgyártás", "nagykereskedelem", "nyomdafesték-gyártás", "papíripar", "retail", "szállitmányozás", "transportation/trucking/railroad", "unclassified", "vegyipar", "vegyipari eszközgyártás", "vegyipari technológiafejlesztés", "vegyészeti ipar", "warehousing", "wholesale", "Élelmiszeripar, fogyasztási cikkek", "Építőipar", "Éttermi vendéglátás", "általános gyártás", "édelmiszeripar", "élelmiszeripar", "építőanyag-gyártás", "építőipar", "étkeztetés", "étkezőipari szolgáltatás", "étkezőipari szolgáltatások", "éttermi szolgáltatás", "üdítőipar", "üdítőital-gyártás" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Austria", "Belgium", "Germany", "Hungary", "Liechtenstein", "Netherlands", "Switzerland", "United Arab Emirates", "mixed" ], "imported_distinct_companies": 4001, "imported_distinct_domains": 3998, "imported_distinct_emails": 5659, "imported_occurrences": 7635, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "1GIA9Sxt9J9HfFj0ZfZmqBucSnqqZPTGJo0q7vHIH5to", "stored_niches": [ "Automotive", "Construction", "Ipari takarító- és kommunális gépgyártás", "Machinery", "Real Estate", "Transportation/trucking/railroad", "automotive", "civil engineering", "construction", "industrial automation", "machinery", "mechanical or industrial engineering", "mining & metals", "plastics", "unclassified", "vegyipar", "wholesale" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Hungary" ], "imported_distinct_companies": 230, "imported_distinct_domains": 126, "imported_distinct_emails": 127, "imported_occurrences": 358, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "1GKPpi3PJBIfDL2YAF0VFVOutT7BFz8WmpNDrofarFlU", "stored_niches": [ "Automotive", "Building Materials", "Electrical/electronic Manufacturing", "Food Production", "Industrial Automation", "Machinery", "Mechanical Or Industrial Engineering", "building materials", "electrical/electronic manufacturing", "industrial automation", "machinery" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Alap", "Belgium", "Budakeszi", "Budapest", "Csehország", "Debrecen", "Egyesült Királyság", "Erd", "France", "Germany", "Goedoello", "Gyermely", "Gyor", "Hatvan", "Hungary", "Kecskemet", "Lengyelország", "Magyarország", "Magyarország / Ausztria", "Marbella", "Miskolc", "Netherlands", "Németország", "Németország, Hollandia, Magyarország", "Pecs", "Roeszke", "Románia", "Siofok", "Sopron", "Spanyolország", "Szeged", "Szentes", "Szombathely", "UK", "United Kingdom", "United States", "mixed" ], "imported_distinct_companies": 19804, "imported_distinct_domains": 7655, "imported_distinct_emails": 10440, "imported_occurrences": 33390, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "1IbQ0bg_X7JkHi0KWZ5Bu5-EHlSZmBjr4bpWhCnniN80", "stored_niches": [ "3D nyomtatás", "A B2B Business Process Outsourcing (BPO) company specializing in multilingual customer contact center services, enhanced with AI technology.", "A B2B technology company specializing in providing and supporting advanced engineering and R&D software solutions, acting as an official reseller and service partner for products like MATLAB, Simulink, and COMSOL.", "A full-service digital agency providing integrated services in creative communication, digital product development, performance marketing, and data solutions.", "A full-service, integrated marketing and communications agency.", "A multi-disciplinary business consulting and outsourcing group providing a wide range of professional services including finance, IT, HR, and management consulting.", "Accounting", "Adatelemzés és üzleti intelligencia", "Adatintelligencia és üzleti elemzés", "Advertising and Marketing. More specifically, a global marketing, communication, and digital transformation holding company.", "Airlines/aviation", "Alcoholic beverage manufacturer and distributor. They produce their own iconic Hungarian spirits and also distribute major international brands.", "Alcoholic beverage producer and distributor. They manufacture their own iconic Hungarian spirits and also distribute major international brands in Hungary.", "Animation", "Apparel & Fashion", "Applied Research and Development Institute, providing R&D, consulting, and analytical services.", "Architecture & Planning", "Automotive", "Automotive / Car Dealership. This is inferred from the company name ('Autó' means 'Car'), as the provided website content is a default NGINX server page and contains no information about the company's business.", "Automotive / Transportation, specifically in the car rental services niche.", "Automotive and Transportation Technology, specializing in V2X (Vehicle-to-Everything) communication solutions for smart infrastructure and connected vehicles.", "Automotive industry, specifically a large car dealership network that sells new and used cars, offers fleet management services, and provides vehicle maintenance.", "Automotive industry, specifically a large-scale car dealership and service center for new and used vehicles.", "Automotive industry, specifically a multi-brand car dealership and service center.", "Automotive industry, specifically a multi-brand dealership (Volvo, Ford, Hyundai, MG, Kawasaki etc.) and service center that also provides vehicle rental and fleet management.", "Autóipari technológia", "Autóipari és gépipari alkatrészgyártás", "Autóvegyszerek és autókozmetika", "Aviation & Aerospace", "B2B Manufacturing of industrial components, specializing in enclosures, HMI systems, and mechanical systems.", "B2B SaaS (Software as a Service) company in the Tax Technology (TaxTech) niche, providing automated global tax compliance solutions.", "B2B SaaS (Software as a Service) company specializing in cloud contact center software.", "B2B Software company providing business management, accounting, and payroll software.", "B2B Software company specializing in business management software (accounting, payroll, invoicing) for small and medium-sized enterprises (SMEs).", "B2B professional services firm specializing in tax consulting, accounting, and business advisory.", "B2B supplier of promotional products and corporate gifts.", "B2B/B2G Management and IT Consulting firm.", "Banking", "Biotechnology", "Biotechnology / AI in Drug Discovery. They provide a specialized AI-powered cell simulation platform for the pharmaceutical industry, specifically focused on oncology drug discovery and development.", "Blockchain Technology / Fintech, specializing in institutional cryptocurrency staking services (Staking-as-a-Service).", "Bor- és szeszesital-kereskedelem", "Building Materials", "Business Process Outsourcing (BPO) / Contact Center Services, specializing in multilingual customer support, sales outsourcing, and AI-enhanced solutions.", "Business Process Outsourcing (BPO), specializing in multilingual and AI-enhanced contact center services.", "Catering / Food Services. Specifically, public and corporate catering (canteens/cafeterias), likely as a brand or division of Hungast.", "Chemical/Pharmaceutical industry. Specifically, a Contract Development and Manufacturing Organization (CDMO) providing R&D, pilot, and large-scale manufacturing services for APIs and intermediates.", "Chemicals", "Civic & Social Organization", "Civil Engineering", "Civil Engineering and Construction, specializing as a civil contractor for large-scale infrastructure projects.", "Computer & Network Security", "Computer Games", "Computer Networking", "Construction", "Construction and Real Estate Development, specializing in architecture, project management, and general contracting for large-scale projects.", "Consumer Services", "Corporate training and consulting company, specializing in organizational development, leadership training, and grant application management.", "Cosmetics", "Dairy", "Design", "Digital solutions and custom software development agency, specializing in IT systems, e-commerce, and AI development.", "Digitális marketing és stratégiai tanácsadás", "Digitális reklám és média", "Digitális transzformáció és adatkezelés", "Digitális ügynökség és szoftverfejlesztés", "E-commerce/Retail, specializing in beauty products, perfumes, fashion accessories, and jewelry.", "E-kereskedelem és informatika", "E-learning", "Education Management", "Education Technology (EdTech), specializing in interactive digital content and presentation software for the K-12 market.", "Education Technology (EdTech), specifically providing interactive digital educational software, content, and solutions for the K-12 market.", "Education. A private institute providing supplementary, English-language academic programs for high school students to prepare them for admission to elite international universities.", "Egészségügy", "Electrical/electronic Manufacturing", "Electronics manufacturing and engineering, specializing in Radio Frequency (RF) and Microwave solutions for the telecommunications, space, and defense sectors.", "Energy / Utilities, specializing in natural gas distribution.", "Energy / Utilities, specifically a natural gas transmission system operator (TSO).", "Energy/Utilities, specifically providing electricity and natural gas to non-residential customers.", "Entertainment", "Environmental Services", "Events Services", "Events and Exhibitions industry, specifically providing venue rental, event organization, and related services.", "Executive Office", "FMCG / Food & Beverage Manufacturing, specializing in snack foods.", "Facilities Services", "Farming", "Felhőalapú kapcsolati központ (CCaaS) szoftver", "Felnőttképzés és üzleti oktatás", "Financial Services", "Financial Services / Banking. Niche: State-owned Export-Import Bank providing financing and credit insurance.", "Financial Services / InsurTech, specializing as an online insurance comparison and brokerage platform.", "Financial Services / Insurance. The company is a major insurance provider in Hungary, operating as the local subsidiary of the German SIGNAL IDUNA group.", "Financial Services / Insurtech, specializing as an online insurance comparison and brokerage platform.", "Financial Services, specializing in asset financing and leasing for vehicles, agricultural machinery, and other equipment.", "Financial Services, specializing in providing credit guarantees and suretyship for businesses.", "Financial Services, specializing in vehicle and production equipment leasing and financing.", "Financial Services, specifically Asset and Fund Management.", "Financial Services, specifically a credit guarantee institution.", "Financial Services, specifically a state-owned export credit agency (ECA) providing banking and insurance services.", "Financial Services, specifically an independent financial advisory and brokerage firm serving both individual (B2C) and corporate (B2B) clients.", "Financial Services, specifically asset financing and leasing for vehicles, agricultural machinery, and equipment.", "Financial Services, specifically investment services, asset management, and corporate finance.", "Financial Services, specifically providing credit guarantees and suretyship.", "Financial Technology (FinTech / WealthTech) company providing investment and wealth management software solutions.", "Financial Technology (Fintech) company providing national payment and interbank clearing system infrastructure.", "Financial Technology (Fintech) specializing in Buy Now, Pay Later (BNPL) solutions.", "Financial consulting and brokerage, specializing in insurance, pensions, and investments.", "Financial services, specializing in providing credit guarantees.", "Financial services, specifically an independent financial advisory and brokerage firm.", "Fintech company providing B2B software solutions for the financial services industry, specializing in credit management.", "Fishery", "Fogyasztói elektronika nagykereskedelem", "Food & Beverages", "Food Production", "Furniture", "Fémipar", "Fémipar és gépipar", "Fémöntészet és fémfeldolgozás", "Gambling & Casinos", "Glass, Ceramics & Concrete", "Global provider of professional information, software solutions, and services for the legal, tax & accounting, health, finance, and compliance sectors.", "Government Agency - International Trade and Development, focused on export promotion for Hungarian businesses.", "Government-related non-profit organization specializing in national spatial data management, geoinformatics, and e-construction systems.", "Governmental/Non-profit organization specializing in national geospatial data management and e-government services for public administration.", "Graphic Design", "Gyógyszeripar", "Gyógyszeripar és biotechnológia", "Health, Wellness & Fitness", "Healthcare Technology (HealthTech), specifically providing enterprise-level virtual care platforms.", "Healthcare and Social Services, specializing in elderly care, housing, and social activities.", "High-end interior design and furnishing, providing both products (lighting, furniture) and services (procurement, design).", "Higher Education", "Higher Education, specifically a University of Art and Design.", "Hospitality", "Hospitality / Food & Beverage. Specifically, a fast-casual Asian (Thai) restaurant chain.", "Hospitality, specifically a hotel chain focusing on wellness, spa, and conference hotels.", "Human Resources", "Human Resources (HR) Services, specializing in labor leasing, recruitment, and payroll outsourcing.", "Human Resources (HR) Services, specializing in staffing, recruitment, and payroll outsourcing.", "Human Resources / Staffing. Specifically, a school cooperative (Iskolaszövetkezet) that provides student workers for companies.", "Human Resources / Staffing. Specifically, a school cooperative that provides student workers for temporary and part-time positions to businesses.", "Human Resources Services, specializing in staffing, recruitment, and payroll outsourcing.", "Human Resources and Staffing, specializing in student work placement (Iskolaszövetkezet / School Cooperative).", "Human resources development and consulting, specializing in corporate training, organizational development, and grant writing services.", "Humánerőforrás-szolgáltatás", "Háztartásigép-alkatrész kereskedelem és szerviz", "IT / SaaS company specializing in automated cloud cost management for Google Cloud Platform (GCP), and providing related data analytics and infrastructure solutions.", "IT / Software, specifically a Low-Code Business Process Automation (BPA) platform.", "IT Consulting and Services, specializing in custom software development, business process automation (RPA, BI), and Industry 4.0 solutions.", "IT Consulting and Software company specializing in Enterprise Resource Planning (ERP) systems for manufacturing and logistics industries.", "IT Services & Consulting, specializing in custom software development, AI solutions, and digital transformation, with a strong focus on the Fintech/Banking sector.", "IT Services / Software Development, specializing in enterprise-level Digital Experience Platforms (DXP) and B2B commerce solutions.", "IT Services and Software Development. Specifically, they provide custom software solutions, team outsourcing, and DevOps services.", "IT Services and Technology Consulting, specializing in custom software development, Microsoft Dynamics 365 implementation, Business Intelligence (BI), and AI solutions.", "IT Services and Technology Consulting, with a niche in AI-driven digital transformation and solutions for the Telecom and BFSI sectors.", "IT Services, specializing in Software Quality Assurance (QA), AI solutions, and business process automation.", "IT and Business Consulting, specializing in SAP solutions, business process outsourcing, and consulting for financial institutions.", "IT and Project Management Consulting, specializing in government-funded digital transformation programs (B2G).", "IT biztonság és hálózat", "IT consulting and services company specializing in business process automation, custom software development, and cloud solutions.", "IT services and consulting, specializing in Google Cloud Platform solutions.", "IT services and consulting, specializing in cloud-native solutions and application modernization.", "IT services and solutions provider, specializing in IT infrastructure, custom development, and cybersecurity.", "IT szolgáltatás", "IT szolgáltatások", "IT szolgáltatások és digitális transzformáció", "IT szolgáltatások és tanácsadás", "IT szolgáltatások, pénzügyi és biztosítási szektor", "IT tanácsadás", "IT és pénzügyi toborzás", "IT és távközlés", "Import & Export", "Independent financial advisory and insurance brokerage firm.", "Indeterminable. The provided website content is a technical prerequisite message ('You need to enable JavaScript to run this app') and offers no information about the company's industry or niche.", "Industrial Automation", "Industrial Manufacturing, specializing in the production and servicing of transformers and electric rotating machines.", "Informatika", "Informatika és automatizálás", "Informatika és szoftverfejlesztés", "Informatika és vállalatirányítás", "Informatika és épületinformatika", "Informatikai szolgáltatások", "Information Services", "Information Technology", "Information Technology & Services", "Information Technology (IT) services and consulting, with a niche in solutions for the architecture, engineering, and construction (AEC) industry (BIM) and services for SMEs.", "Information Technology / Digital Media. Specifically, they develop and operate a large network of high-traffic web properties focused on live streaming technology and online payment systems.", "Information Technology and Cybersecurity, specializing in data protection, encrypted hardware, and data recovery services.", "Information Technology and Services, specializing in custom software development and IT consulting.", "Információtechnológia", "Ingatlan", "Ingatlanfejlesztés", "Ingatlanfejlesztés és -befektetés", "Ingatlanfejlesztés és befektetés", "Insurance", "Insurance provider offering a range of life and non-life insurance products.", "Insurance. Specifically, an online provider of personal insurance products.", "Insurance. The company is an online insurance provider.", "International Trade & Development", "Internet", "Investment Banking", "Investment Management", "Ipari beszállítás és gépészet", "Ipari gyártás és anyagmozgatás", "Ipari gépgyártás és energetika", "Ipari lézeres anyagmegmunkálás", "Ipari takarító- és kommunális gépgyártás", "Ipari és kereskedelmi HVAC berendezések", "Irodaellátás", "Jog és szellemi tulajdon", "Játék- és szórakoztatóipar", "Kerékpár-nagykereskedelem", "Kiberbiztonság", "Kontrakt bútor és belsőépítészet", "Kreatív ügynökség", "Lakberendezés és kertészet", "Legal Services", "Leisure, Travel & Tourism", "Logistics & Supply Chain", "Logisztika és futárszolgálat", "Logisztika és szállítmányozás", "Luxury Goods & Jewelry", "Luxus bútor és belsőépítészet", "Légiközlekedési szolgáltatások", "Machinery", "Management Consulting", "Management and IT consulting firm serving a wide range of sectors.", "Manufacturing company specializing in flooring and coverings for various sectors.", "Manufacturing company specializing in flooring and interior coverings.", "Manufacturing industry, specializing in innovative and sustainable packaging solutions for B2B companies.", "Manufacturing, specifically building materials and healthcare industry products.", "Manufacturing, specifically power tools for forestry, agriculture, landscaping, construction, and garden care.", "Manufacturing, specifically producing specialized flooring and coverings.", "Market Research", "Marketing & Advertising", "Marketing & Advertising, specifically a full-service integrated communications agency.", "Marketing and Advertising. Specifically, a full-service, independent creative and communications agency.", "Marketing and Communications Agency specializing in PR, branding, and integrated campaigns for corporate clients.", "Marketing and Communications agency specializing in integrated PR, branding, and digital campaigns.", "Marketing és kommunikációs szolgáltatások", "Marketing és reklámügynökség", "Marketing ügynökség", "Mechanical Or Industrial Engineering", "Media Distribution and Publishing Services, specializing in magazine distribution, sales, and marketing.", "Media Production", "Media and Publishing, with a specific focus on business and financial news.", "Medical / Healthcare. The specific niche is unclear from the name alone, but it is likely a B2B provider of medical products or services to other healthcare professionals or organizations.", "Medical Devices", "Medical Diagnostics / Biotechnology. Specifically, the company manufactures and distributes in-vitro diagnostic (IVD) products, including hematology and coagulation reagents, and laboratory equipment.", "Medical Diagnostics / Biotechnology. The company manufactures and distributes in-vitro diagnostic (IVD) reagents, control materials, and laboratory equipment.", "Medical Practice", "Megújuló energia", "Mining & Metals", "Mérnöki szoftverek és tanácsadás", "Mérnöki szolgáltatások (épületgépészet, épületvillamosság)", "Mérnöki és IT szolgáltatások", "Nemzetközi kereskedelem és logisztika", "Non-profit Copyright Collective / Performing Rights Organization in the music industry.", "Non-profit membership association for individuals with high IQs.", "Nonprofit IT service and software development provider for the Hungarian government.", "Nonprofit Organization Management", "Oil & Energy", "Okos mobilitás és forgalomirányítás", "Okosotthon és épületautomatizálás", "Online Media", "Online marketing", "Online társkeresés", "Outsourcing/offshoring", "Package/freight Delivery", "Packaging & Containers", "Paper & Forest Products", "Pharmaceutical / Biotechnology, specializing in the research, development, manufacturing, and global supply of radiopharmaceutical products for nuclear medicine.", "Pharmaceuticals", "Pharmaceuticals / Life Sciences, specializing in the development, manufacturing, and global supply of radiopharmaceuticals and nuclear medicine.", "Plastics", "Precíziós szerszámgyártás", "Printing", "Printing industry, specializing in commercial printing, manufacturing and distribution of office/educational supplies, and stamp making.", "Professional Training & Coaching", "Public Policy", "Public Relations & Communications", "Public Utility company specializing in water and sewage services.", "Publishing", "Pályázatírók", "Pénzügyi szolgáltatások", "Pénzügyi technológia (FinTech)", "Railroad Manufacture", "Real Estate", "Real Estate Services, specializing in integrated facility and property management for commercial and industrial properties.", "Recreational Facilities & Services", "Rendezvényszervezés és humánerőforrás", "Rendezvényszervezés és utazás", "Renewable energy, specializing in the design, installation, wholesale, and servicing of solar panel and heat pump systems.", "Renewables & Environment", "Research", "Research and Consulting, specializing in political and economic analysis, public opinion polling, and strategic consulting for corporate and governmental clients.", "Restaurants", "Retail", "Retail and Automotive Services, specifically a chain of convenience stores, gas stations, and express car washes.", "Semiconductors", "Software development company specializing in administrative and management systems for the public sector.", "Sporting Goods", "Sports", "Staffing & Recruiting", "Szállítmányozás és logisztika", "Szépségipar", "Szórakoztatás és rendezvényszervezés", "Technology and AI solutions provider, specializing in custom software development, cloud services, and legacy modernization for B2B clients.", "Technológia és kreatívipar", "Technológiai szolgáltatások", "Telecommunications", "Telecommunications infrastructure provider, focusing on B2B services.", "Telecommunications provider offering internet, cable TV, and phone services.", "Telecommunications, specifically a government-designated provider of critical communication services (EDR - Unified Digital Radio System) for emergency and public safety organizations.", "Tetőfedő anyagok", "Textiles", "The company operates in the Information Technology (IT) services industry, with a focus on managed IT services, IT consulting, custom application development, and Building Information Modeling (BIM) solutions.", "Think Tanks", "Translation & Localization", "Transportation/trucking/railroad", "Turizmus és utazás", "Távközlés és energiaipar", "Távközlés és ipari automatizálás", "Tömítés- és szigeteléstechnika", "Undeterminable. The website content is a default template for the 'Sitecore' digital experience platform and does not describe the company's actual business. The company name 'MVM CEEnergy' suggests the company is in the energy sector.", "Undeterminable. The website is a default Apache installation test page and contains no information about the company's business activities.", "Undetermined. The website is under construction and provides no information about the company's activities.", "Unidentifiable from website content. The website displays a default 'Welcome to nginx!' page, indicating it is not configured. Based on the name 'Schiller Autó Család' ('Autó' is Hungarian for 'car'), the industry is likely Automotive, specifically a car dealership.", "Unknown. The website displays a default nginx server page, which provides no information about the company's industry. Based on the name 'Schiller Autó Család' ('Autó' means 'Car'), the company is likely in the automotive industry, possibly a car dealership.", "Urban Development and Cultural Management, specializing in the management and promotion of a major public park and its cultural institutions.", "Utilities", "Vegyi anyagok nagykereskedelme", "Vegyipar", "Vendéglátás és kávékereskedelem", "Vendéglátás és turizmus", "Venture Capital & Private Equity", "Videójáték fejlesztés", "Villamosipar és energetika", "Világítástechnika és elektromos szerelés", "Vizuális effektek (VFX)", "Warehousing", "Wholesale", "Wholesale and retail trade of electrical supplies, lighting, automation components, and related technical products.", "accounting", "acélipar", "additív gyártóipar", "airlines/aviation", "animation", "apparel & fashion", "architecture & planning", "automatizálási", "automatizálási ipar", "automotive", "autóipar", "autóipari", "autóipari alkatrészek gyártása", "autóipari elektronika", "autóipari felépítménygyártás", "aviation & aerospace", "banking", "betongyártás", "bicikligyártás", "biotechnológiai ipar", "capital markets", "chemicals", "civic & social organization", "computer & network security", "computer games", "computer hardware", "computer networking", "construction", "consumer goods", "consumer services", "csiszolóanyag-gyártás", "csiszolóanyaggyártás", "csomagolóanyag-gyártás", "dairy", "darugépgyártás", "design", "dísznövénykereskedelem és tájépítészet", "e-learning", "education management", "egészségügy", "egészségügyi", "electrical/electronic manufacturing", "elektromos jármű töltőgyártás", "elektronikai", "elektronikai ipar", "elektrooptikai ipar", "elektrotechnika", "energetika", "energetikai", "energiaellátás", "entertainment", "environmental services", "events services", "facilities services", "faipar", "faipari gyártás", "festékgyártás", "filmipar", "financial services", "food & beverages", "food production", "furniture", "fémipar", "fémipari", "gumigyártás", "gumiipar", "gyártás", "gyártó", "gyógyszergyártás", "gyógyszeripar", "gyógyszeripari", "gyógyszeripari tanácsadás és szolgáltatások", "gépeséggyártás", "gépgyártás", "gépiipar", "gépipar", "gépipari", "gépipari alkatrészgyártás", "gépipari kereskedelem", "gépipari mérnöki szolgáltatás", "gépipari nagykereskedelem", "gépipari szolgáltatás", "gépjárműipari alkatrészgyártás", "gépmegmunkálás", "gépmesterség", "géptanipar", "hajtásátviteli ipar", "health, wellness & fitness", "hidraulikai ipar", "hidraulikaipar", "higher education", "hospitality", "human resources", "hőcserélő-gyártás", "hűtéstechnika", "industrial automation", "informatika", "informatikai", "informatikai ipar", "informatikai szolgáltatások", "information services", "information technology & services", "ingatlanüzemeltetés", "insurance", "international trade & development", "internet", "investment banking", "investment management", "ipari", "italipar", "italnagykereskedelem", "izotópgyártás", "jogi", "járműalkatrész-gyártás", "járműgyártás", "játékfejlesztés és szoftverfejlesztés", "kefegyártás", "kereskedelmi ipar", "kereskedelmi szektor", "kiadói", "kompozitgyártás", "kozmetikai ipar", "kozmetikaipar", "kutatás", "kutatás-fejlesztési", "kutatási", "kávéipar", "környezetvédelem", "környezetvédelmi", "kötőelemgyártás", "közlekedés", "közlekedési", "legal services", "leisure, travel & tourism", "logistics & supply chain", "logisztikai", "légkezelő- és szűrőtechnika", "létesítménygazdálkodási", "machinery", "management consulting", "market research", "marketing", "marketing & advertising", "mechanical or industrial engineering", "medical devices", "medical practice", "mezőgazdaság", "mezőgazdasági eszközgyártás", "mezőgazdasági gépgyártás", "mezőgazdasági és élelmiszeripari gépgyártás", "mining & metals", "minőségellenőrzés", "média", "média és kiadás", "mérnöki", "mérnöki szolgáltatások", "mérnökség", "mérő- és tesztelőeszköz-gyártás", "műanyagfeldolgozás", "műanyaggyártás", "műanyagipar", "műszergyártás", "nagykereskedelem", "nagykereskedelmi", "nagykereskedelmi szektor", "nonprofit organization management", "nukleáris medicina / radiogyógyszerek", "nyelvi szolgáltatások", "nyomdafesték-gyártás", "nyomdaipar", "nyomdaipari", "oil & energy", "oktatás", "orvosbiológiai és elektro-optikai ipar", "orvostechnikai ipar", "packaging & containers", "paper & forest products", "papíripar", "pharmaceuticals", "plastics", "printing", "professional training & coaching", "public policy", "pénzügyi", "pénzügyi technológia (fintech)", "real estate", "recreational facilities & services", "rendezvényipari", "rendezvényszervező", "renewables & environment", "retail", "semiconductors", "speciális gépgyártás", "sporting goods", "sportruházat", "sports", "staffing & recruiting", "szappan- és tisztítószer-gyártás", "szellőzőgép-gyártás", "szerelési ipar", "szerszámgyártás", "szigetelésgyártás", "szigetelőanyag-ipar", "szoftver- és mérnökiroda", "szoftverfejlesztés", "szoftverfejlesztő", "szoftveripar", "szolgáltató", "színpadtechnika", "szűrőgyártás", "sörgyártás", "söripar", "tanácsadó", "technológia", "telecommunications", "think tanks", "tisztítószer-gyártás", "translation & localization", "transportation/trucking/railroad", "turisztikai", "tömlőkereskedelem", "unclassified", "utilities", "vegyipar", "vegyipari technológiafejlesztés", "vendéglátás", "venture capital & private equity", "villamosipar", "villamosipari berendezésgyártás", "villamosipari gyártás", "villamosipari ipar", "villamossági ipar", "világítástechnika", "világítástechnikai ipar", "vákuumtechnika", "városgazdálkodás", "wholesale", "writing & editing", "Élelmiszeripar és mezőgazdaság", "Élelmiszeripar, fogyasztási cikkek", "Építőanyag kereskedelem és kivitelezés", "Építőanyag-gyártás", "Építőipar", "Építőipar, tervezés (AEC)", "Építőipar, épületszerkezetek", "Étkeztetés / Franchise", "Ügyvédi iroda", "árnyékolástechnika", "ásványvíz-ipar", "élelmiszer-nagykereskedelem", "élelmiszeripar", "élelmiszeripari", "építőanyag-gyártás", "építőanyagipar", "építőipar", "építőipari", "építőipari alkatrészgyártás", "építőipari technológia", "épületasztalos-ipar", "épületgépészet", "éttermi szolgáltatás", "öntvénygyártás", "üdítőital-gyártás", "ügyfélszolgálati", "üvegelemző ipar", "üvegipar", "Űripar / űrtechnológia" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Belgium", "Budapest", "Erd", "Finnország", "Gyermely", "Hungary", "India", "Japán", "Korea", "Magyarország", "Németország", "Olaszország", "Svájc (és Magyarország)", "USA", "mixed" ], "imported_distinct_companies": 4598, "imported_distinct_domains": 2760, "imported_distinct_emails": 7674, "imported_occurrences": 17802, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "1huAYSNvOu_9NAwnEKksbgtv3z-Y7jpEH9coulgZMT_M", "stored_niches": [ "Accounting", "Agriculture", "Airlines/aviation", "Animation", "Apparel & Fashion", "Architecture & Planning", "Arts & Crafts", "Automotive", "Automotive Supplier", "Aviation & Aerospace", "Banking", "Banking & Finance", "Biotechnology", "Building Materials", "Business Services", "Chemicals", "Civic & Social Organization", "Civil Engineering", "Computer & Network Security", "Computer Games", "Computer Hardware", "Computer Networking", "Construction", "Consulting & Audit", "Consumer Electronics", "Consumer Goods", "Consumer Services", "Cosmetics", "Dairy", "Defense & Space", "Design", "E-learning", "Education Management", "Electrical/electronic Manufacturing", "Electronics", "Energy & Utilities", "Entertainment", "Environmental Services", "Events Services", "Executive Office", "Facilities Services", "Farming", "Financial Services", "Fintech", "Food & Beverages", "Food Production", "Furniture", "Fémipar és gépipar", "Gambling & Casinos", "Glass, Ceramics & Concrete", "Government Administration", "Graphic Design", "Gyógyszeripar", "Gyógyszeripar és biotechnológia", "Health, Wellness & Fitness", "Higher Education", "Hospital & Health Care", "Hospitality", "Human Resources", "Humánerőforrás-szolgáltatás", "IT Services", "IT tanácsadás", "IT és digitális technológia", "IT és telekommunikációs megfelelőség", "Import & Export", "Industrial Automation", "Informatika és szoftverfejlesztés", "Information Services", "Information Technology & Services", "Információtechnológia", "Insurance", "International Affairs", "International Trade & Development", "Investment Banking", "Investment Management", "Kontrakt bútor és belsőépítészet", "Kozmetikai forgalmazás", "Kreatív ügynökség", "Law Practice", "Legal Services", "Leisure, Travel & Tourism", "Logistics", "Logistics & Supply Chain", "Luxus bútor és belsőépítészet", "Machinery", "Management Consulting", "Manufacturing", "Maritime", "Market Research", "Marketing & Advertising", "Mechanical Or Industrial Engineering", "Media & Entertainment", "Media & Publishing", "Media Production", "Medical Devices", "Medical Imaging", "Medical Practice", "Megújuló energia", "Mental Health Care", "Mezőgazdaság és állattenyésztés", "Mining & Metals", "Mining/Commodities", "Museums & Institutions", "Music", "Mérnöki és IT szolgáltatások", "Nemzetközi kereskedelem és logisztika", "Nonprofit Organization Management", "Oil & Energy", "Okos mobilitás és forgalomirányítás", "Online Media", "Online társkeresés", "Outsourcing/offshoring", "Package/freight Delivery", "Packaging & Containers", "Paper & Forest Products", "Performing Arts", "Pharma & Biotech", "Pharmaceuticals", "Plastics", "Primary/secondary Education", "Printing", "Professional Training & Coaching", "Public Relations & Communications", "Public Safety", "Publishing", "Pályázatírók", "Pénzügyi szolgáltatások", "Railroad Manufacture", "Real Estate", "Reklám és marketing", "Religious Institutions", "Renewables & Environment", "Research", "Restaurants", "Retail", "Retail & Consumer", "Security & Investigations", "Semiconductors", "Shipbuilding", "Sporting Goods", "Sports", "Staffing & Recruiting", "Tech & Software", "Tech & Telecom", "Telecommunications", "Textiles", "Tobacco", "Translation & Localization", "Transportation/trucking/railroad", "USA", "Utilities", "Venture Capital & Private Equity", "Warehousing", "Wholesale", "Wine & Spirits", "Wireless", "Writing & Editing", "architecture & planning", "automatizálási ipar", "baromfiipar", "chemicals", "csiszolóanyaggyártás", "csomagolóanyag-gyártás", "csomagolóipar", "egészségügy", "egészségügyi", "elektronikai", "energetikai", "environmental services", "food & beverages", "food production", "fémipar", "gyártás", "gyártó", "gyógyszergyártás", "gyógyszeripar", "gyógyszeripari", "gépgyártás", "gépipar", "géptanipar", "hidraulikai ipar", "hirdetési", "human resources", "hűtéstechnika", "informatika", "informatikai", "information technology & services", "ingatlanpiaci", "insurance", "ipari", "italgyártás", "izotópgyártás", "izotópipar", "jogi", "játékipari", "kiadás", "kiberbiztonság", "kozmetikai ipar", "kozmetikaipar", "kutatási", "kémiai ipar", "környezetvédelem", "közlekedés", "létesítménygazdálkodási", "machinery", "management consulting", "marketing", "marketing & advertising", "mezőgazdasági", "média", "mérnöki", "műanyaggyártás", "műanyagipar", "nagykereskedelmi", "nagykereskedelmi szektor", "nukleáris medicina / radiogyógyszerek", "nyelvi szolgáltatások", "nyomdafesték-gyártás", "packaging & containers", "papíripar", "pharmaceuticals", "plastics", "pénzügyi", "radiofarmakológiai ipar", "radiogyógyszeripar", "restaurants", "szerszámgyártás", "szoftverfejlesztés", "szoftverfejlesztő", "szolgáltató", "technológia", "technológiai", "turizmus", "távközlési", "unclassified", "vegyipar", "vegyipari eszközgyártás", "vegyipari technológiafejlesztés", "vendéglátás", "villamosipari ipar", "vákuumtechnika", "Éttermi vendéglátás", "állategészségügy", "édelmiszeripar", "élelmiszeripar", "építőipar", "építőipar és fémfeldolgozás", "épületgépészet", "étkeztetés", "éttermi szolgáltatás", "üdítőital-gyártás", "üzleti szolgáltatás" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Argentina", "Australia", "Austria", "Azerbaijan", "Bangladesh", "Belgium", "Bosnia and Herzegovina", "Brazil", "Bulgaria", "Canada", "China", "Czech Republic", "Czechia", "Denmark", "Egypt", "France", "Germany", "Greece", "Hungary", "India", "Indonesia", "Ireland", "Italy", "Mexico", "Netherlands", "Norway", "Poland", "Portugal", "Romania", "Russia", "Serbia", "Singapore", "Slovakia", "South Africa", "Spain", "Sweden", "Switzerland", "Taiwan", "Tuerkiye", "Turkey", "United Arab Emirates", "United Kingdom", "United States", "Zimbabwe", "country", "mixed" ], "imported_distinct_companies": 1593, "imported_distinct_domains": 1508, "imported_distinct_emails": 2619, "imported_occurrences": 3170, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "1k_iZ-fCNSUmqt0AyyyclI_OGAGc6fqb9QTxzNHvBGCY", "stored_niches": [ "Automotive", "Construction", "Machinery", "apparel & fashion", "architecture & planning", "automotive", "aviation & aerospace", "building materials", "chemicals", "civil engineering", "commercial real estate", "construction", "consumer services", "design", "electrical/electronic manufacturing", "entertainment", "environmental services", "events services", "furniture", "glass, ceramics & concrete", "import & export", "industrial automation", "industry", "information technology & services", "international trade & development", "logistics & supply chain", "machinery", "management consulting", "maritime", "mechanical or industrial engineering", "medical devices", "mining & metals", "nanotechnology", "oil & energy", "packaging & containers", "plastics", "printing", "professional training & coaching", "publishing", "railroad manufacture", "renewables & environment", "research", "retail", "semiconductors", "shipbuilding", "staffing & recruiting", "textiles", "think tanks", "transportation/trucking/railroad", "unclassified", "utilities", "vegyipar", "warehousing", "wholesale" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Argentina", "Asia and Europe", "Ausztria", "Ausztria, Magyarország", "Ausztrália", "Belgium", "Belgium (központ)", "Belgium, Németország, Svédország, Franciaország, Egyesült Királyság, Lengyelország, Szlovákia, Spanyolország", "Brazília", "Budapest", "Bulgária", "Canada", "Chile", "China", "Csehország", "Czech Republic", "Dánia", "Dél-Korea", "Dél-Korea (központ)", "ESPAÑA", "Egyesült Királyság", "Egyesült Királyság és Európa", "Egyesült Királyság, Magyarország, India", "Erd", "Európa", "Európa (központ)", "Európa (központ: Németország)", "Finnország", "Finnország (központ), Lengyelország, Észtország, Ausztria, Szlovákia, Franciaország, India", "Franciaország", "Franciaország (központ)", "Franciaország (székhely)", "Franciaország, Egyesült Királyság, Spanyolország, Szlovákia", "Franciaország, Magyarország, Szerbia, Kína, Mexikó", "Germany", "Globális (Európa, Ázsia, Dél-Amerika)", "Globális (központ: USA)", "Gyermely", "Gyor", "Görögország (központ), globális jelenlét", "Görögország, Magyarország", "Hollandia", "Hollandia (központ)", "Hollandia, Németország", "Horvátország", "Hungary", "India", "Izrael", "Izrael, Magyarország", "Japán", "Jemen", "Kanada", "Kanada (központ), 19 ország világszerte", "Korea", "Kína", "Kína (Globális központ)", "Kína / Indonézia / Vietnam", "Kína, Magyarország", "Lengyelország", "Lettország", "Litvánia", "Luxemburg", "Magyarország", "Magyarország (többek között)", "Magyarország / Ausztria", "Magyarország, Kanada, Koreai Köztársaság", "Magyarország, Németország", "Magyarország, Románia", "Mauritius", "Mexico", "Mexikó", "Moldova", "México", "Nemzetközi (13 telephely 8 országban)", "Németország", "Németország (központ)", "Németország (központ), Magyarország, Csehország", "Németország / Ausztria", "Németország, Hollandia, Magyarország", "Németország, Magyarország", "Németország, Spanyolország, Csehország, Magyarország", "Olaszország", "Oroszország", "Pakistan", "Paraguay", "Portugália", "Rep. of Korea", "Roeszke", "Románia", "Singapore", "Slovenia", "Sopron", "Spanyolország", "Spanyolország, Magyarország, Németország", "Svájc", "Svájc (és Magyarország)", "Svájc, Magyarország, India, USA", "Svájc, Olaszország, Németország, USA, Argentína", "Svédország", "Svédország (központ), Magyarország (gyártás)", "Svédország, Magyarország", "Switzerland", "Szaúd-Arábia", "Szekesfehervar", "Szerbia", "Szerbia, Magyarország", "Szlovákia", "Szlovénia", "Tajvan", "Turkey", "Törökország", "Türkiye", "UAE", "UK", "USA", "USA (székhely), globális jelenlét", "USA / Kanada", "USA, Magyarország, Kína", "USA, Olaszország", "Ukrajna", "United Kingdom", "United States", "Uruguay", "Vietnam", "mixed", "Írország", "Österreich", "Österreich, Deutschland, Südkorea, Vereinigte Arabische Emirate", "Česká republika" ], "imported_distinct_companies": 3984, "imported_distinct_domains": 3154, "imported_distinct_emails": 9613, "imported_occurrences": 19546, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "1kxRhcfPs41nEj2zazsD2olfrzmanIKtkp--NazmZHCY", "stored_niches": [ "3D nyomtatás", "Alkoholtermékek forgalmazása", "Architecture & Planning", "Automotive", "Building Materials", "Chemicals", "Civil Engineering", "Computer Hardware", "Construction", "Consumer Electronics", "Consumer Goods", "Cosmetics", "Electrical/electronic Manufacturing", "Food & Beverages", "Food Production", "Fémipar", "Glass, Ceramics & Concrete", "Gyógyszeripar", "Gyógyszeripar és biotechnológia", "Háztartásigép-alkatrész kereskedelem és szerviz", "Ideiglenes épületinfrastruktúra és konténertechnológia", "Import & Export", "Industrial Automation", "Information Technology & Services", "Ipari automatizálás és gépgyártás", "Ipari beszállítás és gépészet", "Ipari gyártás és anyagmozgatás", "LED-világítástechnika", "Machinery", "Management Consulting", "Mechanical Or Industrial Engineering", "Megújuló energia", "Mining & Metals", "Mérnöki szolgáltatások", "Packaging & Containers", "Pharmaceuticals", "Plastics", "Precíziós szerszámgyártás", "Pályázatírók", "Railroad Manufacture", "Real Estate", "Restaurants", "Semiconductors", "Telecommunications", "Textiles", "Távközlés és energiaipar", "Tömítés- és szigeteléstechnika", "Wholesale", "acélipar", "acélipari", "additív gyártás", "additív gyártóipar", "alkatrészgyártás", "alumínium újrahasznosítás", "alumíniumújrahasznosítás", "architecture & planning", "audioviziuális ipar", "audiovizuális ipar", "audiovizuális technológia", "audiovizuális technológiai ipar", "automatizálási", "automatizálási ipar", "automotive", "automotív biztonsági alkatrészgyártás", "autóalkatrész-gyártás", "autóbuszgyártás", "autóipar", "autóipari", "autóipari alkatrészek gyártása", "autóipari alkatrészgyártás", "autóipari biztonsági alkatrészgyártás", "autóipari elektronika", "autóipari elektronikai alkatrészgyártás", "autóipari felépítménygyártás", "autóipari járműgyártás", "autóipari kiegészítőgyártás", "autókereskedelem", "baromfiipar", "betongyártás", "betonipari", "betonipari gyártás", "bicikligyártás", "biotechnológiai ipar", "biztonsági ipar", "biztonsági szolgáltatások", "biztonságtechnika", "biztonságtechnikai ipar", "borászat", "building materials", "bútoripar", "bútoripari", "chemicals", "computer hardware", "construction", "csiszolóanyag-gyártás", "csiszolóanyaggyártás", "csomagolás", "csomagolástechnika", "csomagolóanyag-gyártás", "csomagolóanyag-ipar", "csomagolóipar", "csomagolóipari papíripar", "csőgyártás", "célgépgyártás", "darugépgyártás", "dróngyártás", "egészségügyi", "electrical/electronic manufacturing", "elektromechanikai ipar", "elektromos ipar", "elektromos jármű töltőgyártás", "elektromosipari", "elektromágneses alkatrészek gyártása", "elektronika", "elektronikai", "elektronikai ipar", "elektronikai tesztipar", "elektrooptikai ipar", "elektrotechnika", "elektrotechnikai ipar", "energetikai hűtéstechnika", "energetikai ipar", "energiaellátás", "energiaipari berendezésgyártás", "faipar", "faipari gyártás", "farmaceutikai gyártás", "felületkezelő ipar", "festékgyártás", "filmipar", "food & beverages", "food production", "fém- és műanyagipar", "fémgyártás", "fémipar", "fémmegmunkálás", "fűtéstechnika", "fűtőberendezés-gyártás", "gumigyártás", "gumiipar", "gumiipari", "gumiipari gyártás", "gyártás", "gyártástámogatás", "gyártó", "gyógyszergyártás", "gyógyszeripar", "gyógyszeripari", "gyógyszeripari tanácsadás és szolgáltatások", "gázipar", "gázpatron-gyártás", "gépegyártás", "gépeséggyártás", "gépgyártás", "gépiipar", "gépipar", "gépipari alkatrészgyártás", "gépipari elektronika", "gépipari kereskedelem", "gépipari mérnöki szolgáltatás", "gépipari nagykereskedelem", "gépipari szolgáltatás", "gépjárműipari alkatrészgyártás", "gépliftgyártás", "gépmegmunkálás", "gépmegmunkáló ipar", "gépmesterség", "gépszerelőipar", "géptanipar", "gépészati mérnöki szolgáltatások", "hajtástechnika", "hajtásátviteli ipar", "hidraulikai ipar", "hidraulikaipar", "human resources", "híradástechnikai ipar", "hőcserélő-gyártás", "hűtésrendszer-gyártás", "hűtéstechnika", "hűtőipari alkatrészek gyártása", "hűtőipari alkatrészgyártás", "industrial automation", "informatikai ipar", "information technology & services", "ipar elektronika", "ipari", "ipari automatizáció", "ipari automatizálás", "ipari gépgyártás", "ipari építészet", "ipari építőipar", "irodaipari cikkek gyártása", "italgyártás", "italipar", "italnagykereskedelem", "izotópgyártás", "izotópipar", "jármű-összeszerelésipar", "járműalkatrész-gyártás", "járműgyártás", "járműipar", "járműipari átalakítás", "kefegyártás", "kereskedelem", "kereskedelmi ipar", "kereskedelmi szektor", "kerámiai ipar", "kerámiaipar", "kerámiaipari", "kerámiaipra", "kiskereskedelem", "klímatechnikai ipar", "kompozitgyártás", "konténergyártás", "kozmetikai ipar", "kozmetikaipar", "kutatás-fejlesztési", "kutatási", "kábel- és vezetékgyártás", "kábelgyártás", "kábelipar", "kávéipar", "kémiai ipar", "könnyűfém csomagolóanyag-gyártás", "kötőelemgyártás", "logisztika", "légkezelő- és szűrőtechnika", "légtechnikai ipar", "lézertechnológiai ipar", "machinery", "marketing & advertising", "mechanical or industrial engineering", "mezőgazdaság", "mezőgazdasági eszközgyártás", "mezőgazdasági gépgyártás", "mezőgazdasági világítástechnika", "mezőgazdasági és élelmiszeripari gépgyártás", "mining & metals", "minőségbiztosítási szolgáltatások", "minőségellenőrzés", "minőségellenőrzési szolgáltatások", "mobilipar", "mobilkiegészítő-gyártás", "mérnöki ipar", "mérnöki szolgáltatások", "mérnöki tanácsadás és ipari szolgáltatások", "mérnöki tanácsadás és műszaki tervezés", "mérnökség", "mérő- és tesztelőeszköz-gyártás", "mérőeszköz-gyártás", "mérőműszer-gyártás", "mérőműszergyártás", "műanyagfeldolgozás", "műanyaggyártás", "műanyagipar", "műanyagipari", "műanyagipari csomagolásgyártás", "műanyagipari gépgyártás", "műszergyártás", "műszeripar", "nagykereskedelem", "nagykereskedelmi", "nagykereskedelmi szektor", "nukleáris medicina / radiogyógyszerek", "nyomdafesték-gyártás", "nyomdaipar", "orvosbiológiai és elektro-optikai ipar", "orvostechnikai ipar", "packaging & containers", "papír- és kartongyártás", "papíripar", "pharmaceuticals", "plastics", "poliolfin habgyártás", "poliolifin habgyártás", "poliolifin habszivacs gyártás", "radiofarmakológiai ipar", "radiogyógyszeripar", "rendezvényipari", "speciális gépgyártás", "szappan- és tisztítószer-gyártás", "szappan- és tisztítószer-ipar", "szellőztetéstechnika", "szellőzőgép-gyártás", "szellőzőtechnika", "szellőzőtechnikai ipar", "szerelési ipar", "szerszámgyártás", "szerszámgépgyártás", "szerszámkészítés és fémmegmunkálás", "szigetelésgyártás", "szigetelőanyag-ipar", "szilikoncső-gyártás", "szivattyúgyártás", "szoftver- és mérnökiroda", "szoftverfejlesztő", "szoftveripar", "szépségipar", "színpadtechnika", "szűrőgyártás", "sörfőzde", "sörgyártás", "söripar", "takarmányipar", "takarítószermesterelési ipar", "takarítószermesterítés", "technológia", "telekommunikáció", "telekommunikációs eszközgyártás", "textiles", "textilipar", "textilipari konfekció", "textilipár", "tisztítószer-gyártás", "tisztítószergyártás", "tisztítószeripar", "tárolóipari", "tárolókonténer-gyártás", "tömlőkereskedelem", "unclassified", "vasútipar", "vegyi ipar", "vegyipar", "vegyipari eszközgyártás", "vegyipari technológiafejlesztés", "vegyészeti ipar", "ventilációs és légkezelő rendszerek gyártása", "villamosipar", "villamosipari berendezésgyártás", "villamosipari gyártás", "villamosipari ipar", "villamossági ipar", "villanyszerelés", "világítástechnika", "világítástechnikai ipar", "vákuumtechnika", "vízkezelő ipar", "Élelmiszeripar, fogyasztási cikkek", "Építőanyag kereskedelem és kivitelezés", "Építőipar", "Éttermi vendéglátás", "állategészségügy", "árnyékolástechnika", "ásványvíz-ipar", "édelmiszeripar", "élelmiszer-nagykereskedelem", "élelmiszeripar", "építőanyag-gyártás", "építőanyag-kereskedelem", "építőanyagipar", "építőipar", "építőipar és fémfeldolgozás", "építőipar és gyártás", "építőipari", "építőipari alkatrészgyártás", "épületasztalos-ipar", "épületgépészet", "étkeztetés", "étkezőipari szolgáltatás", "étkezőipari szolgáltatások", "éttermi szolgáltatás", "öntvénygyártás", "útépítési ipar", "üdítőipar", "üdítőital-gyártás", "üvegelemző ipar", "üveggyártás", "üvegipar" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Erd", "Gyermely", "Hungary", "mixed" ], "imported_distinct_companies": 1090, "imported_distinct_domains": 1082, "imported_distinct_emails": 50, "imported_occurrences": 2224, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "1r1aczQGjxRP9KmJN5iu0xTRQgbkFTUrVXoVjZsdqOH0", "stored_niches": [ "Agriculture", "Apparel & Fashion", "Automotive", "Automotive Supplier", "Banking & Finance", "Business Services", "Chemicals", "Consulting & Audit", "Consumer Goods", "Electronics", "Energy & Utilities", "Farming", "Financial Services", "Food & Beverages", "Food Production", "IT Services", "Insurance", "Manufacturing", "Medical Devices", "Packaging & Containers", "Paper & Forest Products", "Pharma & Biotech", "Pharmaceuticals", "Plastics", "Printing", "Real Estate", "Restaurants", "Retail & Consumer", "Tech & Software", "Tech & Telecom", "Telecommunications", "Wholesale", "food production", "gyártás", "mezőgazdaság", "unclassified", "vegyipar", "élelmiszeripar" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Belgium", "Budaoers", "Budapest", "Canada", "Debrecen", "Erd", "France", "Gyermely", "Hatvan", "Hungary", "Kecskemet", "Magyarország", "Miskolc", "Nagytarcsa", "Németország", "Pecs", "Siofok", "Spanyolország", "Svájc", "Szekesfehervar", "Szentendre", "Telki", "USA", "Veszprem", "Vietnam", "mixed" ], "imported_distinct_companies": 4532, "imported_distinct_domains": 3198, "imported_distinct_emails": 6219, "imported_occurrences": 15214, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "1rwAizuvg4maJ6Jrxi4PUcRL8geAVLwAm9zB2DHxgbGY", "stored_niches": [ "A B2B Business Process Outsourcing (BPO) company specializing in multilingual customer contact center services, enhanced with AI technology.", "A B2B technology company specializing in providing and supporting advanced engineering and R&D software solutions, acting as an official reseller and service partner for products like MATLAB, Simulink, and COMSOL.", "A full-service digital agency providing integrated services in creative communication, digital product development, performance marketing, and data solutions.", "A full-service, integrated marketing and communications agency.", "A multi-disciplinary business consulting and outsourcing group providing a wide range of professional services including finance, IT, HR, and management consulting.", "Accounting", "Advertising and Marketing. More specifically, a global marketing, communication, and digital transformation holding company.", "Airlines/aviation", "Alcoholic beverage manufacturer and distributor. They produce their own iconic Hungarian spirits and also distribute major international brands.", "Alcoholic beverage producer and distributor. They manufacture their own iconic Hungarian spirits and also distribute major international brands in Hungary.", "Animation", "Apparel & Fashion", "Applied Research and Development Institute, providing R&D, consulting, and analytical services.", "Architecture & Planning", "Automotive", "Automotive / Car Dealership. This is inferred from the company name ('Autó' means 'Car'), as the provided website content is a default NGINX server page and contains no information about the company's business.", "Automotive / Transportation, specifically in the car rental services niche.", "Automotive and Transportation Technology, specializing in V2X (Vehicle-to-Everything) communication solutions for smart infrastructure and connected vehicles.", "Automotive industry, specifically a large car dealership network that sells new and used cars, offers fleet management services, and provides vehicle maintenance.", "Automotive industry, specifically a large-scale car dealership and service center for new and used vehicles.", "Automotive industry, specifically a multi-brand car dealership and service center.", "Automotive industry, specifically a multi-brand dealership (Volvo, Ford, Hyundai, MG, Kawasaki etc.) and service center that also provides vehicle rental and fleet management.", "Aviation & Aerospace", "B2B Manufacturing of industrial components, specializing in enclosures, HMI systems, and mechanical systems.", "B2B SaaS (Software as a Service) company in the Tax Technology (TaxTech) niche, providing automated global tax compliance solutions.", "B2B SaaS (Software as a Service) company specializing in cloud contact center software.", "B2B Software company providing business management, accounting, and payroll software.", "B2B Software company specializing in business management software (accounting, payroll, invoicing) for small and medium-sized enterprises (SMEs).", "B2B professional services firm specializing in tax consulting, accounting, and business advisory.", "B2B supplier of promotional products and corporate gifts.", "B2B/B2G Management and IT Consulting firm.", "Banking", "Biotechnology", "Biotechnology / AI in Drug Discovery. They provide a specialized AI-powered cell simulation platform for the pharmaceutical industry, specifically focused on oncology drug discovery and development.", "Blockchain Technology / Fintech, specializing in institutional cryptocurrency staking services (Staking-as-a-Service).", "Building Materials", "Business Process Outsourcing (BPO) / Contact Center Services, specializing in multilingual customer support, sales outsourcing, and AI-enhanced solutions.", "Business Process Outsourcing (BPO), specializing in multilingual and AI-enhanced contact center services.", "Capital Markets", "Catering / Food Services. Specifically, public and corporate catering (canteens/cafeterias), likely as a brand or division of Hungast.", "Chemical/Pharmaceutical industry. Specifically, a Contract Development and Manufacturing Organization (CDMO) providing R&D, pilot, and large-scale manufacturing services for APIs and intermediates.", "Chemicals", "Civic & Social Organization", "Civil Engineering", "Civil Engineering and Construction, specializing as a civil contractor for large-scale infrastructure projects.", "Computer & Network Security", "Computer Games", "Computer Hardware", "Computer Networking", "Construction", "Construction and Real Estate Development, specializing in architecture, project management, and general contracting for large-scale projects.", "Consumer Electronics", "Consumer Goods", "Consumer Services", "Corporate training and consulting company, specializing in organizational development, leadership training, and grant application management.", "Cosmetics", "Dairy", "Design", "Digital solutions and custom software development agency, specializing in IT systems, e-commerce, and AI development.", "Digitális reklám és média", "E-commerce/Retail, specializing in beauty products, perfumes, fashion accessories, and jewelry.", "E-kereskedelem és informatika", "E-learning", "Education Management", "Education Technology (EdTech), specializing in interactive digital content and presentation software for the K-12 market.", "Education Technology (EdTech), specifically providing interactive digital educational software, content, and solutions for the K-12 market.", "Education. A private institute providing supplementary, English-language academic programs for high school students to prepare them for admission to elite international universities.", "Electrical/electronic Manufacturing", "Electronics manufacturing and engineering, specializing in Radio Frequency (RF) and Microwave solutions for the telecommunications, space, and defense sectors.", "Energy / Utilities, specializing in natural gas distribution.", "Energy / Utilities, specifically a natural gas transmission system operator (TSO).", "Energy/Utilities, specifically providing electricity and natural gas to non-residential customers.", "Enterprise IT services company specializing in custom software development, process automation, and business intelligence.", "Entertainment", "Environmental Services", "Events Services", "Events and Exhibitions industry, specifically providing venue rental, event organization, and related services.", "Executive Office", "FMCG / Food & Beverage Manufacturing, specializing in snack foods.", "Facilities Services", "Farming", "Felhőalapú kapcsolati központ (CCaaS) szoftver", "Financial Services", "Financial Services / Banking. Niche: State-owned Export-Import Bank providing financing and credit insurance.", "Financial Services / InsurTech, specializing as an online insurance comparison and brokerage platform.", "Financial Services / Insurance. The company is a major insurance provider in Hungary, operating as the local subsidiary of the German SIGNAL IDUNA group.", "Financial Services / Insurtech, specializing as an online insurance comparison and brokerage platform.", "Financial Services, specializing in asset financing and leasing for vehicles, agricultural machinery, and other equipment.", "Financial Services, specializing in providing credit guarantees and suretyship for businesses.", "Financial Services, specializing in vehicle and production equipment leasing and financing.", "Financial Services, specifically Asset and Fund Management.", "Financial Services, specifically a credit guarantee institution.", "Financial Services, specifically a state-owned export credit agency (ECA) providing banking and insurance services.", "Financial Services, specifically an independent financial advisory and brokerage firm serving both individual (B2C) and corporate (B2B) clients.", "Financial Services, specifically asset financing and leasing for vehicles, agricultural machinery, and equipment.", "Financial Services, specifically investment services, asset management, and corporate finance.", "Financial Services, specifically providing credit guarantees and suretyship.", "Financial Technology (FinTech / WealthTech) company providing investment and wealth management software solutions.", "Financial Technology (Fintech) company providing national payment and interbank clearing system infrastructure.", "Financial Technology (Fintech) specializing in Buy Now, Pay Later (BNPL) solutions.", "Financial consulting and brokerage, specializing in insurance, pensions, and investments.", "Financial services, specializing in providing credit guarantees.", "Financial services, specifically an independent financial advisory and brokerage firm.", "Fintech company providing B2B software solutions for the financial services industry, specializing in credit management.", "Fishery", "Food & Beverages", "Food Production", "Furniture", "Gambling & Casinos", "Glass, Ceramics & Concrete", "Global provider of professional information, software solutions, and services for the legal, tax & accounting, health, finance, and compliance sectors.", "Government Administration", "Government Agency - International Trade and Development, focused on export promotion for Hungarian businesses.", "Government-related non-profit organization specializing in national spatial data management, geoinformatics, and e-construction systems.", "Governmental/Non-profit organization specializing in national geospatial data management and e-government services for public administration.", "Graphic Design", "Gyógyszeripar", "Gyógyszeripar és biotechnológia", "Health, Wellness & Fitness", "Healthcare Technology (HealthTech), specifically providing enterprise-level virtual care platforms.", "Healthcare and Social Services, specializing in elderly care, housing, and social activities.", "High-end interior design and furnishing, providing both products (lighting, furniture) and services (procurement, design).", "Higher Education", "Higher Education, specifically a University of Art and Design.", "Hospital & Health Care", "Hospitality", "Hospitality / Food & Beverage. Specifically, a fast-casual Asian (Thai) restaurant chain.", "Hospitality, specifically a hotel chain focusing on wellness, spa, and conference hotels.", "Human Resources", "Human Resources (HR) Services, specializing in labor leasing, recruitment, and payroll outsourcing.", "Human Resources (HR) Services, specializing in staffing, recruitment, and payroll outsourcing.", "Human Resources / Staffing. Specifically, a school cooperative (Iskolaszövetkezet) that provides student workers for companies.", "Human Resources / Staffing. Specifically, a school cooperative that provides student workers for temporary and part-time positions to businesses.", "Human Resources Services, specializing in staffing, recruitment, and payroll outsourcing.", "Human Resources and Staffing, specializing in student work placement (Iskolaszövetkezet / School Cooperative).", "Human resources development and consulting, specializing in corporate training, organizational development, and grant writing services.", "IT / SaaS company specializing in automated cloud cost management for Google Cloud Platform (GCP), and providing related data analytics and infrastructure solutions.", "IT / Software, specifically a Low-Code Business Process Automation (BPA) platform.", "IT Consulting and Services, specializing in custom software development, business process automation (RPA, BI), and Industry 4.0 solutions.", "IT Consulting and Software company specializing in Enterprise Resource Planning (ERP) systems for manufacturing and logistics industries.", "IT Services & Consulting, specializing in custom software development, AI solutions, and digital transformation, with a strong focus on the Fintech/Banking sector.", "IT Services / Software Development, specializing in enterprise-level Digital Experience Platforms (DXP) and B2B commerce solutions.", "IT Services and Software Development. Specifically, they provide custom software solutions, team outsourcing, and DevOps services.", "IT Services and Technology Consulting, specializing in custom software development, Microsoft Dynamics 365 implementation, Business Intelligence (BI), and AI solutions.", "IT Services and Technology Consulting, with a niche in AI-driven digital transformation and solutions for the Telecom and BFSI sectors.", "IT Services, specializing in Software Quality Assurance (QA), AI solutions, and business process automation.", "IT and Business Consulting, specializing in SAP solutions, business process outsourcing, and consulting for financial institutions.", "IT and Project Management Consulting, specializing in government-funded digital transformation programs (B2G).", "IT and Software Development company specializing in Enterprise Resource Planning (ERP) systems, IT services, and e-commerce solutions.", "IT consulting and services company specializing in business process automation, custom software development, and cloud solutions.", "IT services and consulting, specializing in Google Cloud Platform solutions.", "IT services and consulting, specializing in cloud-native solutions and application modernization.", "IT services and solutions provider, specializing in IT infrastructure, custom development, and cybersecurity.", "IT solutions and consulting company specializing in AI development, digital transformation, and infrastructure, with a strong focus on the banking and financial sector.", "IT szolgáltatás", "IT szolgáltatások, pénzügyi és biztosítási szektor", "IT és telekommunikációs megfelelőség", "Ideiglenes épületinfrastruktúra és konténertechnológia", "Import & Export", "Independent financial advisory and insurance brokerage firm.", "Indeterminable. The provided website content is a technical prerequisite message ('You need to enable JavaScript to run this app') and offers no information about the company's industry or niche.", "Individual & Family Services", "Industrial Automation", "Industrial Manufacturing, specializing in the production and servicing of transformers and electric rotating machines.", "Informatika", "Informatika és szoftverfejlesztés", "Information Services", "Information Technology & Services", "Information Technology (IT) services and consulting, with a niche in solutions for the architecture, engineering, and construction (AEC) industry (BIM) and services for SMEs.", "Information Technology / Digital Media. Specifically, they develop and operate a large network of high-traffic web properties focused on live streaming technology and online payment systems.", "Information Technology and Cybersecurity, specializing in data protection, encrypted hardware, and data recovery services.", "Information Technology and Services, specializing in custom software development and IT consulting.", "Információtechnológia", "Insurance", "Insurance provider offering a range of life and non-life insurance products.", "Insurance. Specifically, an online provider of personal insurance products.", "Insurance. The company is an online insurance provider.", "International Affairs", "International Trade & Development", "Internet", "Investment Banking", "Investment Management", "Kontrakt bútor és belsőépítészet", "Legal Services", "Leisure, Travel & Tourism", "Logistics & Supply Chain", "Luxury Goods & Jewelry", "Luxus bútor és belsőépítészet", "Machinery", "Management Consulting", "Management and IT consulting firm serving a wide range of sectors.", "Manufacturing company specializing in flooring and coverings for various sectors.", "Manufacturing company specializing in flooring and interior coverings.", "Manufacturing industry, specializing in innovative and sustainable packaging solutions for B2B companies.", "Manufacturing, specifically building materials and healthcare industry products.", "Manufacturing, specifically power tools for forestry, agriculture, landscaping, construction, and garden care.", "Manufacturing, specifically producing specialized flooring and coverings.", "Maritime", "Market Research", "Marketing & Advertising", "Marketing & Advertising, specifically a full-service integrated communications agency.", "Marketing and Advertising. Specifically, a full-service, independent creative and communications agency.", "Marketing and Communications Agency specializing in PR, branding, and integrated campaigns for corporate clients.", "Marketing and Communications agency specializing in integrated PR, branding, and digital campaigns.", "Mechanical Or Industrial Engineering", "Media Distribution and Publishing Services, specializing in magazine distribution, sales, and marketing.", "Media Production", "Media and Publishing, with a specific focus on business and financial news.", "Medical / Healthcare. The specific niche is unclear from the name alone, but it is likely a B2B provider of medical products or services to other healthcare professionals or organizations.", "Medical Devices", "Medical Diagnostics / Biotechnology. Specifically, the company manufactures and distributes in-vitro diagnostic (IVD) products, including hematology and coagulation reagents, and laboratory equipment.", "Medical Diagnostics / Biotechnology. The company manufactures and distributes in-vitro diagnostic (IVD) reagents, control materials, and laboratory equipment.", "Medical Practice", "Megújuló energia", "Mental Health Care", "Mining & Metals", "Museums & Institutions", "Music", "Mérnöki és IT szolgáltatások", "Non-profit Copyright Collective / Performing Rights Organization in the music industry.", "Non-profit membership association for individuals with high IQs.", "Nonprofit IT service and software development provider for the Hungarian government.", "Nonprofit Organization Management", "Oil & Energy", "Okos mobilitás és forgalomirányítás", "Online Media", "Outsourcing/offshoring", "Package/freight Delivery", "Packaging & Containers", "Paper & Forest Products", "Pharmaceutical / Biotechnology, specializing in the research, development, manufacturing, and global supply of radiopharmaceutical products for nuclear medicine.", "Pharmaceuticals", "Pharmaceuticals / Life Sciences, specializing in the development, manufacturing, and global supply of radiopharmaceuticals and nuclear medicine.", "Photography", "Plastics", "Printing", "Printing industry, specializing in commercial printing, manufacturing and distribution of office/educational supplies, and stamp making.", "Professional Training & Coaching", "Public Relations & Communications", "Public Safety", "Public Utility company specializing in water and sewage services.", "Publishing", "Pályázatírók", "Pénzügyi szolgáltatások", "Railroad Manufacture", "Real Estate", "Real Estate Services, specializing in integrated facility and property management for commercial and industrial properties.", "Recreational Facilities & Services", "Renewable energy, specializing in the design, installation, wholesale, and servicing of solar panel and heat pump systems.", "Renewables & Environment", "Research", "Research and Consulting, specializing in political and economic analysis, public opinion polling, and strategic consulting for corporate and governmental clients.", "Restaurants", "Retail", "Retail and Automotive Services, specifically a chain of convenience stores, gas stations, and express car washes.", "Semiconductors", "Software development company specializing in administrative and management systems for the public sector.", "Sporting Goods", "Sports", "Staffing & Recruiting", "Tech & Software", "Technology and AI solutions provider, specializing in custom software development, cloud services, and legacy modernization for B2B clients.", "Technology/Software company specializing in translation and localization management solutions.", "Telecommunications", "Telecommunications infrastructure provider, focusing on B2B services.", "Telecommunications provider offering internet, cable TV, and phone services.", "Telecommunications, specifically a government-designated provider of critical communication services (EDR - Unified Digital Radio System) for emergency and public safety organizations.", "Textiles", "The company operates in the Information Technology (IT) services industry, with a focus on managed IT services, IT consulting, custom application development, and Building Information Modeling (BIM) solutions.", "Think Tanks", "Tobacco", "Translation & Localization", "Transportation/trucking/railroad", "Tömítés- és szigeteléstechnika", "Undeterminable. The website content is a default template for the 'Sitecore' digital experience platform and does not describe the company's actual business. The company name 'MVM CEEnergy' suggests the company is in the energy sector.", "Undeterminable. The website is a default Apache installation test page and contains no information about the company's business activities.", "Undetermined. The website is under construction and provides no information about the company's activities.", "Unidentifiable from website content. The website displays a default 'Welcome to nginx!' page, indicating it is not configured. Based on the name 'Schiller Autó Család' ('Autó' is Hungarian for 'car'), the industry is likely Automotive, specifically a car dealership.", "Unknown. The website displays a default nginx server page, which provides no information about the company's industry. Based on the name 'Schiller Autó Család' ('Autó' means 'Car'), the company is likely in the automotive industry, possibly a car dealership.", "Urban Development and Cultural Management, specializing in the management and promotion of a major public park and its cultural institutions.", "Utilities", "Venture Capital & Private Equity", "Veterinary", "Warehousing", "Wholesale", "Wholesale and retail trade of electrical supplies, lighting, automation components, and related technical products.", "Wireless", "Writing & Editing", "accounting", "airlines/aviation", "alkoholipar", "apparel & fashion", "architecture & planning", "automotive", "autóipari alkatrészek gyártása", "banking", "betongyártás", "building materials", "chemicals", "civic & social organization", "computer & network security", "computer games", "computer hardware", "construction", "consumer services", "design", "e-learning", "education management", "egészségügy", "electrical/electronic manufacturing", "elektronikai ipar", "energetikai", "entertainment", "environmental services", "events services", "facilities services", "financial services", "food & beverages", "food production", "furniture", "fémipari", "gyártás", "gyártó", "gyógyszergyártás", "gyógyszeripar", "gépipar", "health, wellness & fitness", "hospital & health care", "human resources", "import & export", "industrial automation", "informatika", "informatikai", "information services", "information technology & services", "ingatlanüzemeltetés", "insurance", "international trade & development", "internet", "intralogisztika", "izotópgyártás", "jogi", "juttatási", "játékipari", "kereskedelem", "kereskedelmi", "kiadás", "kutatás", "kémiai ipar", "legal services", "leisure, travel & tourism", "logistics & supply chain", "machinery", "management consulting", "market research", "marketing", "marketing & advertising", "mechanical or industrial engineering", "media production", "medical devices", "medical practice", "minőségellenőrzés", "média", "mérnöki", "nagykereskedelmi", "nonprofit organization management", "nukleáris medicina / radiogyógyszerek", "nyomdafesték-gyártás", "nyomdaipar", "oil & energy", "oktatási", "oktatástechnológia", "outsourcing/offshoring", "packaging & containers", "pharmaceuticals", "piacelemzés", "plastics", "professional training & coaching", "public relations & communications", "pénzügy", "pénzügyi", "radiogyógyszeripar", "real estate", "renewables & environment", "research", "restaurants", "retail", "semiconductors", "sporting goods", "staffing & recruiting", "szoftverfejlesztés", "szoftverfejlesztő", "tanácsadó", "technológia", "technológiai", "telecommunications", "think tanks", "translation & localization", "transportation/trucking/railroad", "turisztikai", "unclassified", "utilities", "vegyipar", "vegyipari eszközgyártás", "vegyipari technológiafejlesztés", "vendéglátás", "venture capital & private equity", "világítástechnika", "warehousing", "wholesale", "Éttermi vendéglátás", "édelmiszeripar", "élelmiszeripar", "építőipar", "étkeztetés", "étkezőipari szolgáltatás", "éttermi szolgáltatás" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Argentina", "Asia and Europe", "Ausztria", "Ausztria, Magyarország", "Ausztrália", "Belgium", "Belgium (központ)", "Belgium, Németország, Svédország, Franciaország, Egyesült Királyság, Lengyelország, Szlovákia, Spanyolország", "Brazília", "Budapest", "Bulgária", "Canada", "Chile", "China", "Csehország", "Czech Republic", "Dánia", "Dél-Korea", "Dél-Korea (központ)", "ESPAÑA", "Egyesült Királyság", "Egyesült Királyság és Európa", "Egyesült Királyság, Magyarország, India", "Európa", "Európa (központ)", "Európa (központ: Németország)", "Finnország", "Finnország (központ), Lengyelország, Észtország, Ausztria, Szlovákia, Franciaország, India", "Franciaország", "Franciaország (központ)", "Franciaország (székhely)", "Franciaország, Egyesült Királyság, Spanyolország, Szlovákia", "Franciaország, Magyarország, Szerbia, Kína, Mexikó", "Germany", "Globális (Európa, Ázsia, Dél-Amerika)", "Globális (központ: USA)", "Görögország (központ), globális jelenlét", "Görögország, Magyarország", "Hollandia", "Hollandia (központ)", "Hollandia, Németország", "Horvátország", "Hungary", "India", "Izrael", "Izrael, Magyarország", "Japán", "Jemen", "Kanada", "Kanada (központ), 19 ország világszerte", "Korea", "Kína", "Kína (Globális központ)", "Kína / Indonézia / Vietnam", "Kína, Magyarország", "Lengyelország", "Lettország", "Litvánia", "Luxemburg", "Magyarország", "Magyarország (többek között)", "Magyarország / Ausztria", "Magyarország, Kanada, Koreai Köztársaság", "Magyarország, Németország", "Magyarország, Románia", "Mauritius", "Mexico", "Mexikó", "Moldova", "México", "Nemzetközi (13 telephely 8 országban)", "Németország", "Németország (központ)", "Németország (központ), Magyarország, Csehország", "Németország / Ausztria", "Németország, Hollandia, Magyarország", "Németország, Magyarország", "Németország, Spanyolország, Csehország, Magyarország", "Olaszország", "Oroszország", "Pakistan", "Paraguay", "Portugália", "Rep. of Korea", "Románia", "Singapore", "Slovenia", "Spanyolország", "Spanyolország, Magyarország, Németország", "Svájc", "Svájc (és Magyarország)", "Svájc, Magyarország, India, USA", "Svájc, Olaszország, Németország, USA, Argentína", "Svédország", "Svédország (központ), Magyarország (gyártás)", "Svédország, Magyarország", "Switzerland", "Szaúd-Arábia", "Szentgotthard", "Szerbia", "Szerbia, Magyarország", "Szlovákia", "Szlovénia", "Tajvan", "Turkey", "Törökország", "Türkiye", "UAE", "UK", "USA", "USA (székhely), globális jelenlét", "USA / Kanada", "USA, Magyarország, Kína", "USA, Olaszország", "Ukrajna", "United Kingdom", "United States", "Uruguay", "Vietnam", "mixed", "Írország", "Österreich", "Österreich, Deutschland, Südkorea, Vereinigte Arabische Emirate", "Česká republika" ], "imported_distinct_companies": 2264, "imported_distinct_domains": 2142, "imported_distinct_emails": 1885, "imported_occurrences": 5264, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "1uqySxqJCLIEWkDGNmhactA1tkVJfEECWgiBdc6WAfaE", "stored_niches": [ "3D nyomtatás", "Architecture & Planning", "Automotive", "Building Materials", "Chemicals", "Construction", "Cosmetics", "Electrical/electronic Manufacturing", "Food & Beverages", "Food Production", "Fémipar", "Glass, Ceramics & Concrete", "Ipari beszállítás és gépészet", "Machinery", "Mechanical Or Industrial Engineering", "Mining & Metals", "Packaging & Containers", "Pharmaceuticals", "Plastics", "Railroad Manufacture", "Textiles", "acélipar", "additív gyártás", "alkatrészgyártás", "alumínium újrahasznosítás", "alumíniumújrahasznosítás", "audiovizuális ipar", "automatizálási ipar", "automotive", "autóalkatrész-gyártás", "autóipar", "autóipari alkatrészgyártás", "autóipari járműgyártás", "bicikligyártás", "biztonságtechnikai ipar", "building materials", "bútoripari", "chemicals", "construction", "csomagolás", "csomagolástechnika", "csomagolóanyag-gyártás", "electrical/electronic manufacturing", "elektromechanikai ipar", "elektromos ipar", "elektromos jármű töltőgyártás", "elektronikai ipar", "elektronikai tesztipar", "elektrotechnikai ipar", "energetikai ipar", "faipar", "faipari gyártás", "felületkezelő ipar", "festékgyártás", "filmipar", "fém- és műanyagipar", "fémipar", "fémmegmunkálás", "gumigyártás", "gumiipari", "gyártás", "gyógyszergyártás", "gyógyszeripar", "gázpatron-gyártás", "gépgyártás", "gépipar", "gépipari szolgáltatás", "gépliftgyártás", "gépmegmunkáló ipar", "gépmesterség", "gépszerelőipar", "hajtástechnika", "hidraulikai ipar", "hidraulikaipar", "hőcserélő-gyártás", "hűtőipari alkatrészek gyártása", "ipari automatizálás", "italipar", "izotópgyártás", "jármű-összeszerelésipar", "járműipar", "járműipari átalakítás", "kefegyártás", "klímatechnikai ipar", "kompozitgyártás", "kozmetikai ipar", "kábelgyártás", "kábelipar", "könnyűfém csomagolóanyag-gyártás", "légtechnikai ipar", "lézertechnológiai ipar", "machinery", "mechanical or industrial engineering", "mezőgazdasági világítástechnika", "mining & metals", "minőségbiztosítási szolgáltatások", "minőségellenőrzési szolgáltatások", "mérnöki ipar", "mérnöki szolgáltatások", "mérnöki tanácsadás és műszaki tervezés", "mérőeszköz-gyártás", "mérőműszer-gyártás", "műanyagfeldolgozás", "műanyaggyártás", "műanyagipar", "műanyagipari csomagolásgyártás", "műszeripar", "nyomdaipar", "papíripar", "speciális gépgyártás", "szappan- és tisztítószer-ipar", "szellőzőgép-gyártás", "szerszámgyártás", "szerszámgépgyártás", "szerszámkészítés és fémmegmunkálás", "szigetelőanyag-ipar", "szilikoncső-gyártás", "szivattyúgyártás", "szoftveripar", "színpadtechnika", "szűrőgyártás", "takarítószermesterítés", "textilipar", "textilipari konfekció", "tisztítószer-gyártás", "tömlőkereskedelem", "unclassified", "vegyi ipar", "vegyipar", "villamosipar", "villamosipari berendezésgyártás", "villanyszerelés", "világítástechnika", "világítástechnikai ipar", "árnyékolástechnika", "ásványvíz-ipar", "édelmiszeripar", "élelmiszeripar", "építőanyag-kereskedelem", "építőipar", "épületgépészet", "útépítési ipar", "üdítőital-gyártás", "üvegipar" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0", "legacy-jsonl/1.0" ], "dataset_versions": [ "01337c560a1f8ade8c6f2d49f80b2560a205e2f63b7d54418b930768b9ee1c26", "3a210215a9aa61cd3d788c7fcdfbe3fa66e7146dd2774a602fca34869de440ef" ], "earliest_collected_at": "2026-07-29T14:18:34Z", "exact_original_apify_input": null, "geography_values": [ "Alap", "Budakeszi", "Budaoers", "Budapest", "Debrecen", "Erd", "Goedoello", "Gyermely", "Gyor", "Hatvan", "Hungary", "Kecskemet", "Marbella", "Miskolc", "Nagytarcsa", "Pecs", "Roeszke", "Siofok", "Szeged", "Szekesfehervar", "Szentendre", "Szentes", "Szombathely", "Telki", "Veszprem", "mixed" ], "imported_distinct_companies": 5353, "imported_distinct_domains": 3934, "imported_distinct_emails": 7813, "imported_occurrences": 19998, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T14:18:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "legacy_sheets", "source_name": "1yLOaRe9pyAvyBgbJAOPKrOOnhDpFajDF38f_cTUWnek", "stored_niches": [ "Accounting", "Adatelemzés és üzleti intelligencia", "Adatintelligencia és üzleti elemzés", "Airlines/aviation", "Alkoholtermékek forgalmazása", "Animation", "Apparel & Fashion", "Architecture & Planning", "Arts & Crafts", "Automotive", "Automotive Supplier", "Autóipari és épületfólia-forgalmazás", "Aviation & Aerospace", "Banking", "Banking & Finance", "Befektetési és üzleti szolgáltatások", "Biotechnology", "Building Materials", "Capital Markets", "Chemicals", "Civic & Social Organization", "Civil Engineering", "Computer & Network Security", "Computer Games", "Computer Hardware", "Computer Networking", "Construction", "Consulting & Audit", "Consumer Electronics", "Consumer Goods", "Consumer Services", "Cosmetics", "Dairy", "Design", "Digitális marketing és stratégiai tanácsadás", "Digitális reklám és média", "E-kereskedelem és informatika", "E-learning", "Education Management", "Egészségügy", "Electrical/electronic Manufacturing", "Entertainment", "Environmental Services", "Events Services", "Executive Office", "Facilities Services", "Farming", "Felhőalapú kapcsolati központ (CCaaS) szoftver", "Financial Services", "Fishery", "Food & Beverages", "Food Production", "Fund-raising", "Furniture", "Fémipar", "Fémöntészet és fémfeldolgozás", "Gambling & Casinos", "Glass, Ceramics & Concrete", "Government Administration", "Graphic Design", "Gyógyszeripar", "HR", "Health, Wellness & Fitness", "Higher Education", "Hospital & Health Care", "Hospitality", "Human Resources", "Humánerőforrás szolgáltatások", "Háztartásigép-alkatrész kereskedelem és szerviz", "IT szolgáltatás", "IT szolgáltatások", "IT szolgáltatások, pénzügyi és biztosítási szektor", "IT tanácsadás", "IT és pénzügyi toborzás", "IT és telekommunikációs megfelelőség", "Ideiglenes épületinfrastruktúra és konténertechnológia", "Import & Export", "Industrial Automation", "Informatika", "Informatika / Szoftverfejlesztés", "Informatika és szoftverfejlesztés", "Informatikai szolgáltatások", "Information Services", "Information Technology", "Information Technology & Services", "Információtechnológia", "Ingatlan", "Insurance", "International Affairs", "International Trade & Development", "Internet", "Investment Banking", "Investment Management", "Ipari automatizálás és gépgyártás", "Ipari beszállítás és gépészet", "Ipari gyártás és anyagmozgatás", "Irodaellátás", "Kontrakt bútor és belsőépítészet", "Legal Services", "Leisure, Travel & Tourism", "Logistics & Supply Chain", "Luxury Goods & Jewelry", "Luxus bútor és belsőépítészet", "Machinery", "Management Consulting", "Market Research", "Marketing & Advertising", "Marketing és kommunikációs szolgáltatások", "Marketing és reklámügynökség", "Mechanical Or Industrial Engineering", "Media Production", "Medical Devices", "Medical Practice", "Megújuló energia", "Mental Health Care", "Mezőgazdaság és állattenyésztés", "Mining & Metals", "Museums & Institutions", "Music", "Mérnöki szolgáltatások", "Mérnöki és IT szolgáltatások", "Nonprofit Organization Management", "Oil & Energy", "Okosotthon és épületautomatizálás", "Online Media", "Online marketing", "Online reklámügynökség", "Outsourcing/offshoring", "Package/freight Delivery", "Packaging & Containers", "Paper & Forest Products", "Pharmaceuticals", "Plastics", "Printing", "Professional Training & Coaching", "Public Policy", "Public Relations & Communications", "Public Safety", "Publishing", "Pályázatírók", "Pénzügyi szolgáltatások", "Railroad Manufacture", "Real Estate", "Recreational Facilities & Services", "Rendezvényszervezés és humánerőforrás", "Rendezvényszervezés és utazás", "Renewables & Environment", "Research", "Restaurants", "Retail", "Semiconductors", "Sporting Goods", "Sports", "Staffing & Recruiting", "Szállítmányozás és logisztika", "Szórakoztatás", "Szórakoztatás és rendezvényszervezés", "Tech & Software", "Technológiai szolgáltatások", "Telecommunications", "Textiles", "Think Tanks", "Tobacco", "Translation & Localization", "Transportation/trucking/railroad", "Távközlés és energiaipar", "Tömítés- és szigeteléstechnika", "Utilities", "Vendéglátás és turizmus", "Venture Capital & Private Equity", "Veterinary", "Vezetési és IT tanácsadás", "Warehousing", "Wholesale", "Wireless", "accounting", "adatelemzés", "additív gyártóipar", "airlines/aviation", "alkatrészgyártás", "alkoholipar", "animation", "apparel & fashion", "architecture & planning", "automatizálási", "automotive", "autóipar", "autóipari", "autóipari alkatrészek gyártása", "autóipari kiegészítőgyártás", "autókereskedelem", "aviation & aerospace", "banking", "betongyártás", "bicikligyártás", "building materials", "chemicals", "civic & social organization", "computer games", "computer hardware", "computer networking", "construction", "consumer services", "csiszolóanyag-gyártás", "csomagolás", "csomagolóanyag-gyártás", "dairy", "darugépgyártás", "design", "disztribúció", "e-kereskedelem", "e-kereskedelmi", "e-learning", "education management", "egészségügy", "egészségügyi", "electrical/electronic manufacturing", "elektromos ipar", "elektronika", "elektronikai", "elektronikai ipar", "energetika", "energetikai", "entertainment", "environmental services", "events services", "facilities services", "farming", "financial services", "food & beverages", "food production", "fund-raising", "furniture", "fémipar", "fémipari", "fűtéstechnika", "gyártás", "gyártó", "gyógyszergyártás", "gyógyszeripar", "gyógyszeripari", "gépeséggyártás", "gépgyártás", "gépipar", "gépipari", "gépmegmunkáló ipar", "health, wellness & fitness", "hirdetési", "hospitality", "human resources", "hűtőipari alkatrészek gyártása", "industrial automation", "informatika", "informatikai", "informatikai szolgáltatások", "information services", "information technology & services", "ingatlanközvetítés", "ingatlanpiac", "ingatlanpiaci", "ingatlanüzemeltetés", "insurance", "international affairs", "international trade & development", "internet", "intralogisztika", "investment banking", "investment management", "ipari", "italgyártás", "izotópgyártás", "jogi", "jogvédelem", "juttatási", "játékfejlesztés és szoftverfejlesztés", "játékipari", "kereskedelem", "kereskedelmi", "kiadás", "kiadói", "kiberbiztonság", "kiszervezés", "kozmetika", "kutatás", "kutatás-fejlesztési", "kutatási", "kábelipar", "kémiai ipar", "képzés", "környezetvédelem", "környezetvédelmi", "közlekedés", "közlekedési", "közétkeztetés", "legal services", "leisure, travel & tourism", "logistics & supply chain", "logisztika", "logisztikai", "légiipari", "létesítménygazdálkodási", "machinery", "management consulting", "market research", "marketing", "marketing & advertising", "mechanical or industrial engineering", "medical devices", "medical practice", "mezőgazdaság", "mezőgazdasági", "mezőgazdasági eszközgyártás", "mezőgazdasági gépgyártás", "mining & metals", "média", "médiaipar", "mérnöki", "mérnökség", "műanyaggyártás", "műanyagipar", "nagykereskedelem", "nagykereskedelmi", "nonprofit organization management", "nukleáris medicina / radiogyógyszerek", "nyomdafesték-gyártás", "nyomdaipar", "nyomdaipari", "oil & energy", "oktatás", "oktatási", "oktatástechnológia", "orvostechnológia", "outsourcing/offshoring", "packaging & containers", "paper & forest products", "pharmaceuticals", "piacelemzés", "piackutatás", "plastics", "poliolifin habszivacs gyártás", "printing", "professional training & coaching", "public policy", "pénzügy", "pénzügyi", "pénzügyi technológia (fintech)", "real estate", "recreational facilities & services", "rendezvényipari", "rendezvényszervezés", "rendezvényszervező", "renewables & environment", "research", "retail", "semiconductors", "sporting goods", "sportipar", "sportruházat", "sports", "staffing & recruiting", "szellőzőtechnika", "szerszámgyártás", "szoftver", "szoftverfejlesztés", "szoftverfejlesztő", "szolgáltatás", "szolgáltató", "szépségipar", "sörgyártás", "söripar", "tanácsadás", "tanácsadó", "technológia", "technológiai", "telecommunications", "tervezés", "textiles", "think tanks", "translation & localization", "transportation/trucking/railroad", "turisztikai", "turizmus", "távközlési", "unclassified", "utilities", "vegyipar", "vegyipari eszközgyártás", "vegyipari technológiafejlesztés", "vendéglátás", "venture capital & private equity", "villamosipar", "világítástechnika", "városgazdálkodás", "warehousing", "wholesale", "writing & editing", "Élelmiszeripar, fogyasztási cikkek", "Építőanyag kereskedelem és kivitelezés", "Építőipar", "Építőipar (válaszfalrendszerek és üveg megoldások)", "Éttermi vendéglátás", "állatgyógyászat", "élelmiszer-nagykereskedelem", "élelmiszer-technológia", "élelmiszeripar", "élelmiszeripari", "építészet", "építőipar", "építőipari", "építőipari technológia", "étkeztetés", "éttermi szolgáltatás", "üdítőipar", "ügyfélszolgálati", "üvegelemző ipar", "üveggyártás", "üzleti szolgáltatás" ], "stored_queries": [ "master.jsonl", "staging.csv" ] }, { "actor_or_importer_versions": [ "run_contact_crawl.py@sha256:66fa8b2e8471a2cd131c67ddac45d0227a5b2b875fcc5a2f30aa117eed87cc72" ], "dataset_versions": [ "689d19a8eed58a5ada29c0cbce3b90c068232b998e2a0f9a64fd84f00547ad78" ], "earliest_collected_at": "2026-07-29T15:20:46Z", "exact_original_apify_input": null, "geography_values": [ "Hungary" ], "imported_distinct_companies": 3985, "imported_distinct_domains": 4022, "imported_distinct_emails": 958, "imported_occurrences": 4022, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T15:47:42Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "union_contacts", "source_name": "canonical-source-union-contact-crawl-20260729", "stored_niches": [ "unclassified-existing-reservoir" ], "stored_queries": [ "source-union domains admitted by an objective defect, missing a published email or usable name" ] }, { "actor_or_importer_versions": [ "defect_scan.py@sha256:a791fb863b0565ceb4e10e77daa9dec34fe7b7efa94786d2294db452d51547a3" ], "dataset_versions": [ "1c314b7755672592bacac6090aab03e26fbf21fe3cdb5abc2b02fcf3885da119" ], "earliest_collected_at": "2026-07-29T14:06:32Z", "exact_original_apify_input": null, "geography_values": [ "Hungary" ], "imported_distinct_companies": 38499, "imported_distinct_domains": 39601, "imported_distinct_emails": 14905, "imported_occurrences": 39601, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T15:03:02Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "commoncrawl_union", "source_name": "commoncrawl-hosts2-osm-and-sibling-source-union", "stored_niches": [ "unclassified-existing-reservoir" ], "stored_queries": [ "defects_source_union_remaining_20260729.jsonl" ] }, { "actor_or_importer_versions": [ "fetch_kti_contractors.py@sha256:ad599dd2dbe45d38d3f0f3d8e6379218f133d253961111015a68aab8df0232fc" ], "dataset_versions": [ "fbe8b9696a902c05d3e1633b87647d05a3a922980d40a1d5fce163e88f8991a7" ], "earliest_collected_at": "2026-07-29T21:08:58Z", "exact_original_apify_input": null, "geography_values": [ "Hungary" ], "imported_distinct_companies": 1419, "imported_distinct_domains": 830, "imported_distinct_emails": 1423, "imported_occurrences": 1479, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T21:08:58Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "emi_registry", "source_name": "emi-kti-public-registry", "stored_niches": [ "construction-contractors" ], "stored_queries": [ "normalized.jsonl" ] }, { "actor_or_importer_versions": [ "defect_scan.py@sha256:a791fb863b0565ceb4e10e77daa9dec34fe7b7efa94786d2294db452d51547a3" ], "dataset_versions": [ "892b6a469a430658573685e1a5799d8540bdaf41de91ae6a9cc432743d79e2f2" ], "earliest_collected_at": "2026-07-29T13:58:52Z", "exact_original_apify_input": null, "geography_values": [ "Hungary" ], "imported_distinct_companies": 129256, "imported_distinct_domains": 136544, "imported_distinct_emails": 36716, "imported_occurrences": 136544, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T16:08:26Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "commoncrawl_hosts", "source_name": "existing-commoncrawl-and-hu-host-reservoir", "stored_niches": [ "unclassified-existing-reservoir" ], "stored_queries": [ "pool_reservoir minus the union of every defects_*.jsonl domain" ] }, { "actor_or_importer_versions": [ "migration-012-provenance-backfill+sanitize_contact_crawl_output.py@sha256:96c3ffac783b938a4d1c78b1c2d98c962b37dc544ee91576eb2c49c4db9507db", "run_contact_crawl.py@mixed-version-boundary-19852" ], "dataset_versions": [ "c7e9b67be58e3367e2befe6f81309b57c42c22a7c49ef4f293c0f9441e7522cb", "f981c3f204b76af4f18a75dc5d9c70c73668d75c02dc9a0dfe7c96a18f98c4c5" ], "earliest_collected_at": "2026-07-29T16:19:08Z", "exact_original_apify_input": null, "geography_values": [ "Hungary" ], "imported_distinct_companies": 20029, "imported_distinct_domains": 21756, "imported_distinct_emails": 3756, "imported_occurrences": 21907, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T22:14:25.298103+00:00", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "reservoir_contacts", "source_name": "existing-commoncrawl-and-hu-host-reservoir-contact-crawl", "stored_niches": [ "mixed-unclassified-existing-reservoir" ], "stored_queries": [ "21,756 previously discovered objective-qualified reservoir domains missing a published email or accepted decision-maker name", "evidence.jsonl" ] }, { "actor_or_importer_versions": [ "migration-012-provenance-backfill+sanitize_contact_crawl_output.py@sha256:96c3ffac783b938a4d1c78b1c2d98c962b37dc544ee91576eb2c49c4db9507db", "run_contact_crawl.py@sha256:62b7d13ee8bf5f3a9c0f3c5e8a7fddfcc97fb694c1c0c40472a3be6d4c8aaa1e + sanitize_contact_crawl_output.py@sha256:20d9a20fa6c9600e3d8a72834dc1e379603036706c6e07e293d57a4f8f6e4059" ], "dataset_versions": [ "17e1e5661199a9604e85e18e5f181dc4d084615a7baeb4d2e56af6771e7ab676", "f981c3f204b76af4f18a75dc5d9c70c73668d75c02dc9a0dfe7c96a18f98c4c5" ], "earliest_collected_at": "2026-07-29T20:38:17.750360+00:00", "exact_original_apify_input": null, "geography_values": [ "Hungary" ], "imported_distinct_companies": 2453, "imported_distinct_domains": 3688, "imported_distinct_emails": 474, "imported_occurrences": 4209, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T20:38:17.830558+00:00", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "freemail_recovery", "source_name": "existing-reservoir-published-freemail-recovery", "stored_niches": [ "mixed-unclassified-existing-reservoir" ], "stored_queries": [ "Re-crawl the 3,688 first-pass email_third_party_domain rows produced before published freemail retention was enabled", "evidence.jsonl" ] }, { "actor_or_importer_versions": [ "migration-012-provenance-backfill+sanitize_contact_crawl_output.py@sha256:96c3ffac783b938a4d1c78b1c2d98c962b37dc544ee91576eb2c49c4db9507db", "run_contact_crawl.py@sha256:432bd56334a7408a8a01ab9dffbce78ee7dc7e4de534d1c41c7f773e1b70691c + sanitize_contact_crawl_output.py@sha256:96c3ffac783b938a4d1c78b1c2d98c962b37dc544ee91576eb2c49c4db9507db" ], "dataset_versions": [ "5931997100d8dc33eedd49dc851b486ff04d49d8e59a10902089f28f0283773e", "f981c3f204b76af4f18a75dc5d9c70c73668d75c02dc9a0dfe7c96a18f98c4c5" ], "earliest_collected_at": "2026-07-29T21:35:46.736871+00:00", "exact_original_apify_input": null, "geography_values": [ "Hungary" ], "imported_distinct_companies": 11783, "imported_distinct_domains": 11783, "imported_distinct_emails": 1776, "imported_occurrences": 12457, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T21:35:47.020372+00:00", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "freemail_recovery", "source_name": "existing-reservoir-published-freemail-recovery-complement", "stored_niches": [ "mixed-unclassified-existing-reservoir" ], "stored_queries": [ "contacts-sanitized.jsonl", "evidence.jsonl" ] }, { "actor_or_importer_versions": [ "scrape_meevet.py@sha256:faf750f7ba84547a0674377411b11185949fd5f83c4b49e69ffe0d84cd9dc77b" ], "dataset_versions": [ "b8712c993f68d752dee85f966fa89709040c85ceac99f1a3be53524f35b68862" ], "earliest_collected_at": "2026-07-29T17:56:10.030978Z", "exact_original_apify_input": null, "geography_values": [ "Hungary" ], "imported_distinct_companies": 456, "imported_distinct_domains": 57, "imported_distinct_emails": 498, "imported_occurrences": 500, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T18:10:25.673602Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "meevet_registry", "source_name": "meevet-public-search", "stored_niches": [ "registered-electrician" ], "stored_queries": [ "nationwide public registry sample; offsets 0,12,24...; 500 immutable provider IDs" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0" ], "dataset_versions": [ "6cf2b30284e772182813731028113f0588444d947088a64d803e104eed084bf0" ], "earliest_collected_at": "2026-07-26T19:11:13Z", "exact_original_apify_input": null, "geography_values": [ "HU" ], "imported_distinct_companies": 616, "imported_distinct_domains": 616, "imported_distinct_emails": 616, "imported_occurrences": 616, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-26T21:27:09Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "owned", "source_name": "owned", "stored_niches": [ "unclassified" ], "stored_queries": [ "leads_v2.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0" ], "dataset_versions": [ "6cf2b30284e772182813731028113f0588444d947088a64d803e104eed084bf0" ], "earliest_collected_at": "2026-07-26T19:14:46Z", "exact_original_apify_input": null, "geography_values": [ "HU" ], "imported_distinct_companies": 11332, "imported_distinct_domains": 11332, "imported_distinct_emails": 11318, "imported_occurrences": 11332, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-26T23:35:06Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "host_reservoir", "source_name": "reservoir_hosts", "stored_niches": [ "unclassified" ], "stored_queries": [ "leads_v2.csv" ] }, { "actor_or_importer_versions": [ "legacy-csv/1.0" ], "dataset_versions": [ "6cf2b30284e772182813731028113f0588444d947088a64d803e104eed084bf0" ], "earliest_collected_at": "2026-07-26T19:15:33Z", "exact_original_apify_input": null, "geography_values": [ "HU" ], "imported_distinct_companies": 3602, "imported_distinct_domains": 3602, "imported_distinct_emails": 3590, "imported_occurrences": 3602, "input_provenance_status": "Original Apify actor input is not established by these legacy import records.", "latest_collected_at": "2026-07-29T09:05:10Z", "original_scraped_count": null, "original_scraped_status": "not_proven_by_import_receipts", "source_family": "osm_reservoir", "source_name": "reservoir_osm", "stored_niches": [ "unclassified" ], "stored_queries": [ "leads_v2.csv" ] } ] }, "limits": [ "The audit reads stored provider receipts rather than calling paid providers. Actor input evidence is the actual locally saved dispatch input and run receipt, not a new API fetch.", "Exact original scraper configuration and original scraped volume for legacy Google Sheets, host and CSV imports are not established. Null denotes unknown, not zero.", "Saved raw Maps evidence can show which sites have usable pages. The exact history-versus-identity prefilter rejection split before crawling is not separately persisted for every actor result. Do not label all absent scrapes as scraping failures.", "Current run remains live. Counts are a frozen 06:54:53 UTC snapshot and may change afterward. The older state checkpoint has a different timestamp.", "Exact original actor-input/run receipts were not recovered for 2 earlier reused Maps datasets: mS7tXRgpO3yRpFpHp, xqRqADT0wWoWv6nIc. They supplied zero admitted current-run candidates." ], "local_source_filters": { "email_policy": "MillionVerifier result ok with no provider error is required for current-ready. catch_all, invalid, unknown and uncertain provider results are held.", "fresh_maps_after_actor": "Reject missing websites, facebook.com, instagram.com, google.com and maps.google.com, permanentlyClosed rows, and non-HU countryCode. Check prior history and current source/company/email/domain/name identities. Require a usable own-company page with visible same-domain/subdomain email or a permitted free-mail address, then repeat final identity/history checks before admission.", "fresh_maps_implicit_size_filter": "No minimum revenue, employee count, review count or rating in the stored actor inputs. Construction and company-owned team/project/location text are priority signals, not an actor size filter.", "retained_candidates": "Require identity_receipt.clear, valid domain variable, no prior paid/prepared source, no current exclusion or overlapping current company/email/domain identity. Existing source fit remains subject to downstream company-page evidence." }, "reading_notes": [ "The default charts are monotone passing cohorts. Valid-email and later counts are intersections with preceding stages, never independent stage totals stitched together.", "163 emails are valid in total at snapshot, including 6 still-pending rows. The processed cohort contains 157 valid emails.", "107 rows have supported personalization and fit. Of those, 16 are held by email status, so 91 meet the current ready rule.", "Historical raw scraped counts are unknown unless a saved actor dataset proves them. Imported legacy occurrence counts are historical inventory, not newly scraped current supply.", "The 6,723 retained candidate records have no overlapping source, company, email or domain keys under the runtime normalization. The 2,127 admitted candidates and 91 ready leads also have zero overlapping identity keys. Historical imported-inventory totals are a different scope and must not be added to current supply.", "Fresh Maps raw query scopes overlap by 31 place occurrences. The family unique-place count is 481. All accepted Maps candidates are attributed exactly once to their saved run.", "Current ready means prepared for human review with source-backed fit, valid email and history clearance. This audit neither imports leads nor sends messages." ], "reconciliation": { "accepted_candidate_identity_duplicates": { "company": { "distinct_identity_keys": 2127, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 2280, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 2127, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 1692, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 2127, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "all_checks_passed": true, "checks": { "accepted_company_email_domain_name_source_duplicates_zero": true, "all_personalized_saved_quotes_exact": true, "all_ready_within_monotone_passing_cohort": true, "all_retained_admissions_match_historical_occurrence_checksum": true, "all_retained_admissions_present_in_input": true, "current_manifest_total_matches_source_sum": true, "family_processed_sum_reconciles": true, "family_ready_sum_reconciles": true, "fresh_actor_receipt_admissions_match": true, "fresh_actor_receipt_raw_totals_match": true, "fresh_actor_run_receipts_match_current_ledger": true, "manifest_candidates_sha256_matches": true, "negative_stage_counts_zero": true, "nonmonotone_funnels_zero": true, "planned_steps_distinguished": true, "primary_snapshot_stable": true, "processed_matches_terminal_outcome_count": true, "query_ready_sum_reconciles_fresh_maps": true, "ready_has_no_prior_or_current_history_conflicts": true, "ready_is_entirely_new_run": true, "ready_receipts_all_current_and_matching": true, "ready_saved_quotes_exact": true, "retained_input_equals_admitted_plus_rejected": true, "retained_source_ids_unique": true, "source_detail_admissions_reconcile_retained": true, "sqlite_row_count_matches_projection": true }, "initial_rejection_count": 4692, "initial_rejection_reason_counts_nonadditive": { "current_crm": 36, "current_membership": 1416, "current_sent_history": 993, "live_membership": 547, "live_sent_history": 283, "prior_paid_or_prepared_source": 4692, "prior_paid_or_reserved_company": 4244, "prior_prepared_alias": 4330, "prior_prepared_review_company": 4668 }, "input_candidate_identity_duplicates": { "company": { "distinct_identity_keys": 6723, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 7104, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 6723, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 5433, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 6723, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "monotonicity_failures": [], "negative_count_failures": [], "old_prepared_paid_contacted_or_assigned_ready_conflicts": 0, "ready_candidate_identity_duplicates": { "company": { "distinct_identity_keys": 91, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 96, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 91, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 90, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 91, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "row_snapshot_at": "2026-10-04T06:54:53.517369+00:00", "saved_sqlite_processing_count": 801, "saved_sqlite_ready_count": 91, "state_checkpoint_at": "2026-10-04T05:47:20.599647+00:00", "state_checkpoint_processing_count": 799, "state_checkpoint_ready_count": 91 }, "run_id": "clientsflow-new2000-20261004", "schema_version": 1, "snapshot": { "attempt": 1, "completed_at": "2026-10-04T06:54:53.517369+00:00", "drift_note": "SQLite rows and current ledger/manifest were frozen within this bounded window. State.json is a separate older checkpoint. Saved scrape evidence is read later and admitted only when its mtime is no later than snapshot completion.", "events_summary": { "count": 1127, "last_at": "2026-10-04T06:48:35.293438+00:00", "max_id": 23800 }, "manifest_candidate_sha256": "a902d177fb6bf98bcce786ec7a747d206ac55a9a6e5fed90811a0ced441b9c1f", "manifest_hash_verified": true, "sqlite_current_rows": 807, "sqlite_current_rows_sha256": "5e8a5b34037a22ce9c3a05df98d41ceaa07a2064e1f72d2268cfbb4453d468d0", "sqlite_prior_rows_count": 6016, "sqlite_prior_rows_sha256": "3619b7d54b6475e1f4d85383b12cf958793a203011d52419840844dd2b9b78b7", "sqlite_read_transaction": true, "stable_primary_files": true, "started_at": "2026-10-04T06:54:52.717945+00:00", "state_updated_at": "2026-10-04T05:47:20.599647+00:00" }, "source_details": [ { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 1, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 1, "observed_email_model_order": {}, "pending_total": 1, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": { "no_result_status": 1 }, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 1, "input_not_admitted": 6, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:1462n8bFK61jYMlA_OSo98Lm6zxiszEnIFVVorS4DtyE", "input_identity_duplicates": { "company": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 1462n8bFK61jYMlA_OSo98Lm6zxiszEnIFVVorS4DtyE", "raw_input_records": 7, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1462n8bFK61jYMlA_OSo98Lm6zxiszEnIFVVorS4DtyE" ], "stage_order": "readiness_cohort", "stages": [ { "count": 7, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 1, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 31, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 32, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 31, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 31, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "other_services": 1 }, "current_ready": 0, "eligible_candidates": 31, "email_attempt_state_counts": { "completed": 1 }, "email_attempted_all": 1, "email_result_counts_attempted_only": { "catch_all": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 1, "no_row_yet": 30, "observed_email_model_order": { "model_dispatched_before_email_completed": 1 }, "pending_total": 30, "pending_with_row": 0, "personalized_but_not_ready": 1, "processed": 1, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 1, "no_result_status": 30 }, "rows_in_sqlite": 1, "scrape_evidence_saved_all_candidates": 1, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 1, "terminal_outcome_count": 1, "usable_scrape_all_candidates": 1, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 30, "input_not_admitted": 25, "processed_not_valid_email": 1, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:17aN3vEQ2eVfs4zQ76dZSBGT48POxf5Zns2lODVv3SwU", "input_identity_duplicates": { "company": { "distinct_identity_keys": 56, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 57, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 56, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 37, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 56, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 17aN3vEQ2eVfs4zQ76dZSBGT48POxf5Zns2lODVv3SwU", "raw_input_records": 56, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "17aN3vEQ2eVfs4zQ76dZSBGT48POxf5Zns2lODVv3SwU" ], "stage_order": "readiness_cohort", "stages": [ { "count": 56, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 31, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 1, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "other_services": 1, "unresolved": 1 }, "current_ready": 1, "eligible_candidates": 3, "email_attempt_state_counts": { "completed": 1 }, "email_attempted_all": 1, "email_result_counts_attempted_only": { "ok": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 1, "no_row_yet": 1, "observed_email_model_order": { "email_completed_before_model_dispatch": 1 }, "pending_total": 1, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 2, "processed_without_email_attempt": 1, "processing_status_counts": { "complete": 1, "no_result_status": 1, "scrape_unavailable": 1 }, "rows_in_sqlite": 2, "scrape_evidence_saved_all_candidates": 2, "supported_fit_within_valid_scraped_processed": 1, "supported_personalization_fit_all": 1, "terminal_outcome_count": 2, "usable_scrape_all_candidates": 1, "usable_scrape_within_valid_processed": 1, "valid_email_all": 1, "valid_email_pending": 0, "valid_email_within_processed": 1 }, "drops": { "eligible_not_processed": 1, "input_not_admitted": 34, "processed_not_valid_email": 1, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:18l-qTgDfskAs5CgJX27wJXuCWk-SfyaPrYOwkBX3FAo", "input_identity_duplicates": { "company": { "distinct_identity_keys": 37, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 38, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 37, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 26, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 37, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 18l-qTgDfskAs5CgJX27wJXuCWk-SfyaPrYOwkBX3FAo", "raw_input_records": 37, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "18l-qTgDfskAs5CgJX27wJXuCWk-SfyaPrYOwkBX3FAo" ], "stage_order": "readiness_cohort", "stages": [ { "count": 37, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 3, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 2, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 1, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 1, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 1, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 1, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 76, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 85, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 76, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 55, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 76, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "other_services": 4, "unresolved": 2 }, "current_ready": 3, "eligible_candidates": 76, "email_attempt_state_counts": { "completed": 4 }, "email_attempted_all": 4, "email_result_counts_attempted_only": { "catch_all": 1, "ok": 3 }, "model_attempted_candidates": 4, "model_generation_in_row": 4, "no_row_yet": 70, "observed_email_model_order": { "model_dispatched_before_email_completed": 4 }, "pending_total": 70, "pending_with_row": 0, "personalized_but_not_ready": 1, "processed": 6, "processed_without_email_attempt": 2, "processing_status_counts": { "complete": 4, "no_result_status": 70, "scrape_unavailable": 2 }, "rows_in_sqlite": 6, "scrape_evidence_saved_all_candidates": 6, "supported_fit_within_valid_scraped_processed": 3, "supported_personalization_fit_all": 4, "terminal_outcome_count": 6, "usable_scrape_all_candidates": 4, "usable_scrape_within_valid_processed": 3, "valid_email_all": 3, "valid_email_pending": 0, "valid_email_within_processed": 3 }, "drops": { "eligible_not_processed": 70, "input_not_admitted": 88, "processed_not_valid_email": 3, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:1CkNd0uyZGudx-CJy-jg_wXLdQTXdpmVxxjCgmo5MmSE", "input_identity_duplicates": { "company": { "distinct_identity_keys": 164, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 174, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 164, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 126, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 164, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 1CkNd0uyZGudx-CJy-jg_wXLdQTXdpmVxxjCgmo5MmSE", "raw_input_records": 164, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1CkNd0uyZGudx-CJy-jg_wXLdQTXdpmVxxjCgmo5MmSE" ], "stage_order": "readiness_cohort", "stages": [ { "count": 164, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 76, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 6, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 3, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 3, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 3, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 3, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 1 }, "current_ready": 0, "eligible_candidates": 3, "email_attempt_state_counts": { "completed": 1 }, "email_attempted_all": 1, "email_result_counts_attempted_only": { "unknown": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 1, "no_row_yet": 2, "observed_email_model_order": { "model_dispatched_before_email_completed": 1 }, "pending_total": 2, "pending_with_row": 0, "personalized_but_not_ready": 1, "processed": 1, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 1, "no_result_status": 2 }, "rows_in_sqlite": 1, "scrape_evidence_saved_all_candidates": 1, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 1, "terminal_outcome_count": 1, "usable_scrape_all_candidates": 1, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 2, "input_not_admitted": 3, "processed_not_valid_email": 1, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:1GIA9Sxt9J9HfFj0ZfZmqBucSnqqZPTGJo0q7vHIH5to", "input_identity_duplicates": { "company": { "distinct_identity_keys": 6, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 6, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 6, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 6, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 1GIA9Sxt9J9HfFj0ZfZmqBucSnqqZPTGJo0q7vHIH5to", "raw_input_records": 6, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1GIA9Sxt9J9HfFj0ZfZmqBucSnqqZPTGJo0q7vHIH5to" ], "stage_order": "readiness_cohort", "stages": [ { "count": 6, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 3, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 1, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "other_services": 1 }, "current_ready": 0, "eligible_candidates": 2, "email_attempt_state_counts": { "completed": 1 }, "email_attempted_all": 1, "email_result_counts_attempted_only": { "invalid": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 1, "no_row_yet": 1, "observed_email_model_order": { "model_dispatched_before_email_completed": 1 }, "pending_total": 1, "pending_with_row": 0, "personalized_but_not_ready": 1, "processed": 1, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 1, "no_result_status": 1 }, "rows_in_sqlite": 1, "scrape_evidence_saved_all_candidates": 1, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 1, "terminal_outcome_count": 1, "usable_scrape_all_candidates": 1, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 1, "input_not_admitted": 1, "processed_not_valid_email": 1, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:1GKPpi3PJBIfDL2YAF0VFVOutT7BFz8WmpNDrofarFlU", "input_identity_duplicates": { "company": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 1GKPpi3PJBIfDL2YAF0VFVOutT7BFz8WmpNDrofarFlU", "raw_input_records": 3, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1GKPpi3PJBIfDL2YAF0VFVOutT7BFz8WmpNDrofarFlU" ], "stage_order": "readiness_cohort", "stages": [ { "count": 3, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 2, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 1, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 94, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 100, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 94, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 58, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 94, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 3, "excluded": 1, "other_services": 2, "unresolved": 3 }, "current_ready": 1, "eligible_candidates": 94, "email_attempt_state_counts": { "completed": 5 }, "email_attempted_all": 5, "email_result_counts_attempted_only": { "catch_all": 4, "ok": 1 }, "model_attempted_candidates": 8, "model_generation_in_row": 6, "no_row_yet": 85, "observed_email_model_order": { "model_dispatched_before_email_completed": 5, "model_dispatched_without_a_completed_email_timestamp": 3 }, "pending_total": 85, "pending_with_row": 0, "personalized_but_not_ready": 4, "processed": 9, "processed_without_email_attempt": 4, "processing_status_counts": { "complete": 6, "model_held": 2, "no_result_status": 85, "scrape_unavailable": 1 }, "rows_in_sqlite": 9, "scrape_evidence_saved_all_candidates": 9, "supported_fit_within_valid_scraped_processed": 1, "supported_personalization_fit_all": 5, "terminal_outcome_count": 9, "usable_scrape_all_candidates": 8, "usable_scrape_within_valid_processed": 1, "valid_email_all": 1, "valid_email_pending": 0, "valid_email_within_processed": 1 }, "drops": { "eligible_not_processed": 85, "input_not_admitted": 564, "processed_not_valid_email": 8, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:1IbQ0bg_X7JkHi0KWZ5Bu5-EHlSZmBjr4bpWhCnniN80", "input_identity_duplicates": { "company": { "distinct_identity_keys": 658, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 711, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 658, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 484, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 658, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 1IbQ0bg_X7JkHi0KWZ5Bu5-EHlSZmBjr4bpWhCnniN80", "raw_input_records": 658, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1IbQ0bg_X7JkHi0KWZ5Bu5-EHlSZmBjr4bpWhCnniN80" ], "stage_order": "readiness_cohort", "stages": [ { "count": 658, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 94, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 9, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 1, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 1, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 1, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 1, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 8, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 11, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 11, "observed_email_model_order": {}, "pending_total": 11, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": { "no_result_status": 11 }, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 11, "input_not_admitted": 13, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:1huAYSNvOu_9NAwnEKksbgtv3z-Y7jpEH9coulgZMT_M", "input_identity_duplicates": { "company": { "distinct_identity_keys": 24, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 25, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 24, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 17, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 24, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 1huAYSNvOu_9NAwnEKksbgtv3z-Y7jpEH9coulgZMT_M", "raw_input_records": 24, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1huAYSNvOu_9NAwnEKksbgtv3z-Y7jpEH9coulgZMT_M" ], "stage_order": "readiness_cohort", "stages": [ { "count": 24, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 11, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 1, "other_services": 1 }, "current_ready": 0, "eligible_candidates": 7, "email_attempt_state_counts": { "completed": 2 }, "email_attempted_all": 2, "email_result_counts_attempted_only": { "catch_all": 1, "unknown": 1 }, "model_attempted_candidates": 2, "model_generation_in_row": 2, "no_row_yet": 5, "observed_email_model_order": { "model_dispatched_before_email_completed": 2 }, "pending_total": 5, "pending_with_row": 0, "personalized_but_not_ready": 2, "processed": 2, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 2, "no_result_status": 5 }, "rows_in_sqlite": 2, "scrape_evidence_saved_all_candidates": 2, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 2, "terminal_outcome_count": 2, "usable_scrape_all_candidates": 2, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 5, "input_not_admitted": 10, "processed_not_valid_email": 2, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:1k_iZ-fCNSUmqt0AyyyclI_OGAGc6fqb9QTxzNHvBGCY", "input_identity_duplicates": { "company": { "distinct_identity_keys": 17, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 17, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 17, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 17, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 17, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 1k_iZ-fCNSUmqt0AyyyclI_OGAGc6fqb9QTxzNHvBGCY", "raw_input_records": 17, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1k_iZ-fCNSUmqt0AyyyclI_OGAGc6fqb9QTxzNHvBGCY" ], "stage_order": "readiness_cohort", "stages": [ { "count": 17, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 7, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 2, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 39, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 42, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 39, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 32, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 39, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 2, "other_services": 3, "unresolved": 2 }, "current_ready": 1, "eligible_candidates": 39, "email_attempt_state_counts": { "completed": 5 }, "email_attempted_all": 5, "email_result_counts_attempted_only": { "catch_all": 1, "invalid": 2, "ok": 1, "unknown": 1 }, "model_attempted_candidates": 5, "model_generation_in_row": 5, "no_row_yet": 32, "observed_email_model_order": { "model_dispatched_before_email_completed": 5 }, "pending_total": 32, "pending_with_row": 0, "personalized_but_not_ready": 4, "processed": 7, "processed_without_email_attempt": 2, "processing_status_counts": { "complete": 5, "no_result_status": 32, "scrape_unavailable": 2 }, "rows_in_sqlite": 7, "scrape_evidence_saved_all_candidates": 7, "supported_fit_within_valid_scraped_processed": 1, "supported_personalization_fit_all": 5, "terminal_outcome_count": 7, "usable_scrape_all_candidates": 5, "usable_scrape_within_valid_processed": 1, "valid_email_all": 1, "valid_email_pending": 0, "valid_email_within_processed": 1 }, "drops": { "eligible_not_processed": 32, "input_not_admitted": 174, "processed_not_valid_email": 6, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:1kxRhcfPs41nEj2zazsD2olfrzmanIKtkp--NazmZHCY", "input_identity_duplicates": { "company": { "distinct_identity_keys": 213, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 228, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 213, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 157, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 213, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 1kxRhcfPs41nEj2zazsD2olfrzmanIKtkp--NazmZHCY", "raw_input_records": 213, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1kxRhcfPs41nEj2zazsD2olfrzmanIKtkp--NazmZHCY" ], "stage_order": "readiness_cohort", "stages": [ { "count": 213, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 39, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 7, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 1, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 1, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 1, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 1, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 3, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:1r1aczQGjxRP9KmJN5iu0xTRQgbkFTUrVXoVjZsdqOH0", "input_identity_duplicates": { "company": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 3, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 1r1aczQGjxRP9KmJN5iu0xTRQgbkFTUrVXoVjZsdqOH0", "raw_input_records": 3, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1r1aczQGjxRP9KmJN5iu0xTRQgbkFTUrVXoVjZsdqOH0" ], "stage_order": "readiness_cohort", "stages": [ { "count": 3, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "other_services": 1 }, "current_ready": 0, "eligible_candidates": 11, "email_attempt_state_counts": { "completed": 1 }, "email_attempted_all": 1, "email_result_counts_attempted_only": { "catch_all": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 1, "no_row_yet": 10, "observed_email_model_order": { "model_dispatched_before_email_completed": 1 }, "pending_total": 10, "pending_with_row": 0, "personalized_but_not_ready": 1, "processed": 1, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 1, "no_result_status": 10 }, "rows_in_sqlite": 1, "scrape_evidence_saved_all_candidates": 1, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 1, "terminal_outcome_count": 1, "usable_scrape_all_candidates": 1, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 10, "input_not_admitted": 73, "processed_not_valid_email": 1, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:1rwAizuvg4maJ6Jrxi4PUcRL8geAVLwAm9zB2DHxgbGY", "input_identity_duplicates": { "company": { "distinct_identity_keys": 84, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 86, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 84, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 63, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 84, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 1rwAizuvg4maJ6Jrxi4PUcRL8geAVLwAm9zB2DHxgbGY", "raw_input_records": 84, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1rwAizuvg4maJ6Jrxi4PUcRL8geAVLwAm9zB2DHxgbGY" ], "stage_order": "readiness_cohort", "stages": [ { "count": 84, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 11, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 1, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 12, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 12, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 12, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 8, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 12, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "other_services": 1, "unresolved": 2 }, "current_ready": 0, "eligible_candidates": 12, "email_attempt_state_counts": { "completed": 1 }, "email_attempted_all": 1, "email_result_counts_attempted_only": { "catch_all": 1 }, "model_attempted_candidates": 2, "model_generation_in_row": 1, "no_row_yet": 9, "observed_email_model_order": { "model_dispatched_before_email_completed": 1, "model_dispatched_without_a_completed_email_timestamp": 1 }, "pending_total": 9, "pending_with_row": 0, "personalized_but_not_ready": 1, "processed": 3, "processed_without_email_attempt": 2, "processing_status_counts": { "complete": 1, "model_held": 1, "no_result_status": 9, "scrape_unavailable": 1 }, "rows_in_sqlite": 3, "scrape_evidence_saved_all_candidates": 3, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 1, "terminal_outcome_count": 3, "usable_scrape_all_candidates": 2, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 9, "input_not_admitted": 52, "processed_not_valid_email": 3, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:1uqySxqJCLIEWkDGNmhactA1tkVJfEECWgiBdc6WAfaE", "input_identity_duplicates": { "company": { "distinct_identity_keys": 64, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 67, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 64, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 48, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 64, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 1uqySxqJCLIEWkDGNmhactA1tkVJfEECWgiBdc6WAfaE", "raw_input_records": 64, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1uqySxqJCLIEWkDGNmhactA1tkVJfEECWgiBdc6WAfaE" ], "stage_order": "readiness_cohort", "stages": [ { "count": 64, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 12, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 3, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 7, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 7, "observed_email_model_order": {}, "pending_total": 7, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": { "no_result_status": 7 }, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 7, "input_not_admitted": 3, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_sheets", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:1yLOaRe9pyAvyBgbJAOPKrOOnhDpFajDF38f_cTUWnek", "input_identity_duplicates": { "company": { "distinct_identity_keys": 10, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 10, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 10, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 6, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 10, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "Legacy Google Sheet 1yLOaRe9pyAvyBgbJAOPKrOOnhDpFajDF38f_cTUWnek", "raw_input_records": 10, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1yLOaRe9pyAvyBgbJAOPKrOOnhDpFajDF38f_cTUWnek" ], "stage_order": "readiness_cohort", "stages": [ { "count": 10, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 7, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 10, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 1, "unresolved": 5 }, "current_ready": 1, "eligible_candidates": 7, "email_attempt_state_counts": { "completed": 6 }, "email_attempted_all": 6, "email_result_counts_attempted_only": { "catch_all": 4, "invalid": 1, "ok": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 1, "no_row_yet": 1, "observed_email_model_order": { "email_completed_before_model_dispatch": 1 }, "pending_total": 1, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 6, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 1, "email_held": 5, "no_result_status": 1 }, "rows_in_sqlite": 6, "scrape_evidence_saved_all_candidates": 6, "supported_fit_within_valid_scraped_processed": 1, "supported_personalization_fit_all": 1, "terminal_outcome_count": 6, "usable_scrape_all_candidates": 6, "usable_scrape_within_valid_processed": 1, "valid_email_all": 1, "valid_email_pending": 0, "valid_email_within_processed": 1 }, "drops": { "eligible_not_processed": 1, "input_not_admitted": 11, "processed_not_valid_email": 5, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "union_contacts", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:canonical-source-union-contact-crawl-20260729", "input_identity_duplicates": { "company": { "distinct_identity_keys": 18, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 21, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 18, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 18, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 18, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "canonical-source-union-contact-crawl-20260729", "raw_input_records": 18, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "canonical-source-union-contact-crawl-20260729" ], "stage_order": "readiness_cohort", "stages": [ { "count": 18, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 7, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 6, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 1, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 1, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 1, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 1, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 195, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 204, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 195, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 193, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 195, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 4, "excluded": 1, "unresolved": 141 }, "current_ready": 4, "eligible_candidates": 195, "email_attempt_state_counts": { "completed": 144, "uncertain": 2 }, "email_attempted_all": 146, "email_result_counts_attempted_only": { "catch_all": 58, "invalid": 26, "ok": 17, "provider_result_missing": 2, "unknown": 43 }, "model_attempted_candidates": 6, "model_generation_in_row": 5, "no_row_yet": 49, "observed_email_model_order": { "email_completed_before_model_dispatch": 6 }, "pending_total": 49, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 146, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 5, "email_held": 129, "model_held": 1, "no_result_status": 49, "scrape_unavailable": 11 }, "rows_in_sqlite": 146, "scrape_evidence_saved_all_candidates": 146, "supported_fit_within_valid_scraped_processed": 4, "supported_personalization_fit_all": 4, "terminal_outcome_count": 146, "usable_scrape_all_candidates": 124, "usable_scrape_within_valid_processed": 6, "valid_email_all": 17, "valid_email_pending": 0, "valid_email_within_processed": 17 }, "drops": { "eligible_not_processed": 49, "input_not_admitted": 348, "processed_not_valid_email": 129, "scraped_without_supported_fit": 2, "supported_not_current_ready": 0, "valid_without_usable_scrape": 11 }, "family_id": "commoncrawl_union", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:commoncrawl-hosts2-osm-and-sibling-source-union", "input_identity_duplicates": { "company": { "distinct_identity_keys": 543, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 560, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 543, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 538, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 543, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "commoncrawl-hosts2-osm-and-sibling-source-union", "raw_input_records": 543, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "commoncrawl-hosts2-osm-and-sibling-source-union" ], "stage_order": "readiness_cohort", "stages": [ { "count": 543, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 195, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 146, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 17, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 6, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 4, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 4, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 127, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 136, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 127, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 126, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 127, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 127, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 127, "observed_email_model_order": {}, "pending_total": 127, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": { "no_result_status": 127 }, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 127, "input_not_admitted": 376, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "emi_registry", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:emi-kti-public-registry", "input_identity_duplicates": { "company": { "distinct_identity_keys": 503, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 522, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 503, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 500, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 503, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "emi-kti-public-registry", "raw_input_records": 503, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "emi-kti-public-registry" ], "stage_order": "readiness_cohort", "stages": [ { "count": 503, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 127, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 877, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 966, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 877, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 875, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 877, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 20, "excluded": 2, "other_services": 12, "unresolved": 272 }, "current_ready": 32, "eligible_candidates": 877, "email_attempt_state_counts": { "completed": 305, "uncertain": 1 }, "email_attempted_all": 306, "email_result_counts_attempted_only": { "catch_all": 142, "invalid": 37, "ok": 53, "provider_result_missing": 1, "unknown": 73 }, "model_attempted_candidates": 36, "model_generation_in_row": 35, "no_row_yet": 571, "observed_email_model_order": { "email_completed_before_model_dispatch": 36 }, "pending_total": 571, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 306, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 35, "email_held": 252, "model_held": 1, "no_result_status": 571, "scrape_unavailable": 17, "uncertain_paid_held": 1 }, "rows_in_sqlite": 306, "scrape_evidence_saved_all_candidates": 305, "supported_fit_within_valid_scraped_processed": 32, "supported_personalization_fit_all": 32, "terminal_outcome_count": 306, "usable_scrape_all_candidates": 264, "usable_scrape_within_valid_processed": 36, "valid_email_all": 53, "valid_email_pending": 0, "valid_email_within_processed": 53 }, "drops": { "eligible_not_processed": 571, "input_not_admitted": 1464, "processed_not_valid_email": 253, "scraped_without_supported_fit": 4, "supported_not_current_ready": 0, "valid_without_usable_scrape": 17 }, "family_id": "commoncrawl_hosts", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:existing-commoncrawl-and-hu-host-reservoir", "input_identity_duplicates": { "company": { "distinct_identity_keys": 2341, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 2530, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 2341, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 2325, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 2341, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "existing-commoncrawl-and-hu-host-reservoir", "raw_input_records": 2341, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "existing-commoncrawl-and-hu-host-reservoir" ], "stage_order": "readiness_cohort", "stages": [ { "count": 2341, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 877, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 306, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 53, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 36, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 32, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 32, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 52, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 54, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 52, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 49, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 52, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 52, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 52, "observed_email_model_order": {}, "pending_total": 52, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": { "no_result_status": 52 }, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 52, "input_not_admitted": 66, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "reservoir_contacts", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:existing-commoncrawl-and-hu-host-reservoir-contact-crawl", "input_identity_duplicates": { "company": { "distinct_identity_keys": 118, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 125, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 118, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 113, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 118, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "existing-commoncrawl-and-hu-host-reservoir-contact-crawl", "raw_input_records": 118, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "existing-commoncrawl-and-hu-host-reservoir-contact-crawl" ], "stage_order": "readiness_cohort", "stages": [ { "count": 118, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 52, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 1, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 1, "observed_email_model_order": {}, "pending_total": 1, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": { "no_result_status": 1 }, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 1, "input_not_admitted": 1, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "freemail_recovery", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:existing-reservoir-published-freemail-recovery", "input_identity_duplicates": { "company": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "existing-reservoir-published-freemail-recovery", "raw_input_records": 2, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "existing-reservoir-published-freemail-recovery" ], "stage_order": "readiness_cohort", "stages": [ { "count": 2, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 1, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 1, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 1, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 1, "observed_email_model_order": {}, "pending_total": 1, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": { "no_result_status": 1 }, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 1, "input_not_admitted": 1, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "freemail_recovery", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:existing-reservoir-published-freemail-recovery-complement", "input_identity_duplicates": { "company": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "existing-reservoir-published-freemail-recovery-complement", "raw_input_records": 2, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "existing-reservoir-published-freemail-recovery-complement" ], "stage_order": "readiness_cohort", "stages": [ { "count": 2, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 1, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 25, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 25, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 25, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 25, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 25, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 25, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 25, "observed_email_model_order": {}, "pending_total": 25, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": { "no_result_status": 25 }, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 25, "input_not_admitted": 22, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "meevet_registry", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:meevet-public-search", "input_identity_duplicates": { "company": { "distinct_identity_keys": 47, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 47, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 47, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 46, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 47, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "meevet-public-search", "raw_input_records": 47, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "meevet-public-search" ], "stage_order": "readiness_cohort", "stages": [ { "count": 47, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 25, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "other_services": 1, "unresolved": 3 }, "current_ready": 1, "eligible_candidates": 4, "email_attempt_state_counts": { "completed": 4 }, "email_attempted_all": 4, "email_result_counts_attempted_only": { "catch_all": 1, "invalid": 1, "ok": 1, "unknown": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 1, "no_row_yet": 0, "observed_email_model_order": { "email_completed_before_model_dispatch": 1 }, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 4, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 1, "email_held": 3 }, "rows_in_sqlite": 4, "scrape_evidence_saved_all_candidates": 4, "supported_fit_within_valid_scraped_processed": 1, "supported_personalization_fit_all": 1, "terminal_outcome_count": 4, "usable_scrape_all_candidates": 3, "usable_scrape_within_valid_processed": 1, "valid_email_all": 1, "valid_email_pending": 0, "valid_email_within_processed": 1 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 10, "processed_not_valid_email": 3, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "owned", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:owned", "input_identity_duplicates": { "company": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "owned", "raw_input_records": 14, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "owned" ], "stage_order": "readiness_cohort", "stages": [ { "count": 14, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 4, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 4, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 1, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 1, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 1, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 1, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 394, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 415, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 394, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 67, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 394, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "excluded": 1, "other_services": 3, "unresolved": 205 }, "current_ready": 3, "eligible_candidates": 394, "email_attempt_state_counts": { "completed": 209 }, "email_attempted_all": 209, "email_result_counts_attempted_only": { "catch_all": 49, "invalid": 96, "ok": 21, "unknown": 43 }, "model_attempted_candidates": 5, "model_generation_in_row": 4, "no_row_yet": 185, "observed_email_model_order": { "email_completed_before_model_dispatch": 5 }, "pending_total": 185, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 209, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 4, "email_held": 188, "model_held": 1, "no_result_status": 185, "scrape_unavailable": 16 }, "rows_in_sqlite": 209, "scrape_evidence_saved_all_candidates": 209, "supported_fit_within_valid_scraped_processed": 3, "supported_personalization_fit_all": 3, "terminal_outcome_count": 209, "usable_scrape_all_candidates": 116, "usable_scrape_within_valid_processed": 5, "valid_email_all": 21, "valid_email_pending": 0, "valid_email_within_processed": 21 }, "drops": { "eligible_not_processed": 185, "input_not_admitted": 877, "processed_not_valid_email": 188, "scraped_without_supported_fit": 2, "supported_not_current_ready": 0, "valid_without_usable_scrape": 16 }, "family_id": "host_reservoir", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:reservoir_hosts", "input_identity_duplicates": { "company": { "distinct_identity_keys": 1271, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 1316, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 1271, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 378, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 1271, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "reservoir_hosts", "raw_input_records": 1271, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "reservoir_hosts" ], "stage_order": "readiness_cohort", "stages": [ { "count": 1271, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 394, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 209, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 21, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 5, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 3, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 3, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 51, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 52, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 51, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 51, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 51, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 5, "other_services": 1, "unresolved": 30 }, "current_ready": 6, "eligible_candidates": 51, "email_attempt_state_counts": { "completed": 36 }, "email_attempted_all": 36, "email_result_counts_attempted_only": { "catch_all": 4, "invalid": 9, "ok": 13, "unknown": 10 }, "model_attempted_candidates": 6, "model_generation_in_row": 6, "no_row_yet": 15, "observed_email_model_order": { "email_completed_before_model_dispatch": 6 }, "pending_total": 15, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 36, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 6, "email_held": 23, "no_result_status": 15, "scrape_unavailable": 7 }, "rows_in_sqlite": 36, "scrape_evidence_saved_all_candidates": 36, "supported_fit_within_valid_scraped_processed": 6, "supported_personalization_fit_all": 6, "terminal_outcome_count": 36, "usable_scrape_all_candidates": 23, "usable_scrape_within_valid_processed": 6, "valid_email_all": 13, "valid_email_pending": 0, "valid_email_within_processed": 13 }, "drops": { "eligible_not_processed": 15, "input_not_admitted": 129, "processed_not_valid_email": 23, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 7 }, "family_id": "osm_reservoir", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "source:reservoir_osm", "input_identity_duplicates": { "company": { "distinct_identity_keys": 180, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 186, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 180, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 169, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 180, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_detail", "label": "reservoir_osm", "raw_input_records": 180, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "reservoir_osm" ], "stage_order": "readiness_cohort", "stages": [ { "count": 180, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 51, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 36, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 13, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 6, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 6, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 6, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 15, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Magyarország", "maxCrawledPlacesPerSearch": 200, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "tetőfedő", "villanyszerelő" ], "skipClosedPlaces": false, "website": "allPlaces" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "0xfgKoCAJP2fNLLxG", "finished_at": "2026-09-23T09:19:37.981Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 1.5, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 400, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/actor-run.json" }, "run_id": "noV86emu3XLEDnOF2", "started_at": "2026-09-23T09:19:04.390Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:0xfgKoCAJP2fNLLxG", "input_identity_duplicates": { "company": { "distinct_identity_keys": 15, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 15, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 15, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 15, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 15, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset 0xfgKoCAJP2fNLLxG", "raw_input_records": 15, "raw_original_scraped_records": 400, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 15, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 60, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Budapest, Magyarország", "maxCrawledPlacesPerSearch": 100, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos", "vízvezeték szerelő", "szobafestő" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "1FEQB1T7kZYIeOmak", "finished_at": "2026-09-23T10:35:27.835Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 2.41, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 586, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-00-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-00-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-00-actor-run.json" }, "run_id": "pWzaexJUN8vX87tiU", "started_at": "2026-09-23T10:33:51.641Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:1FEQB1T7kZYIeOmak", "input_identity_duplicates": { "company": { "distinct_identity_keys": 60, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 61, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 60, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 59, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 60, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset 1FEQB1T7kZYIeOmak", "raw_input_records": 60, "raw_original_scraped_records": 586, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 60, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 11, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Székesfehérvár, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "7PigdDsQ0izTaNDZD", "finished_at": "2026-09-23T12:43:33.703Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 61, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-06-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-06-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-06-actor-run.json" }, "run_id": "PZ5HNJdakZbCgmkrD", "started_at": "2026-09-23T12:41:56.366Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:7PigdDsQ0izTaNDZD", "input_identity_duplicates": { "company": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset 7PigdDsQ0izTaNDZD", "raw_input_records": 11, "raw_original_scraped_records": 61, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 11, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 2, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Szombathely, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "8PGirekhXtNiramYo", "finished_at": "2026-09-23T13:35:50.373Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 35, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-09-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-09-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-09-actor-run.json" }, "run_id": "anpZyFqQmLQoGTiUA", "started_at": "2026-09-23T13:33:17.479Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:8PGirekhXtNiramYo", "input_identity_duplicates": { "company": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset 8PGirekhXtNiramYo", "raw_input_records": 2, "raw_original_scraped_records": 35, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 2, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 9, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Miskolc, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "TWoiDPMkcUUdlYBvF", "finished_at": "2026-09-23T12:35:25.909Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 44, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-05-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-05-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-05-actor-run.json" }, "run_id": "tVgl53jpQWG8gHlKR", "started_at": "2026-09-23T12:33:53.256Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:TWoiDPMkcUUdlYBvF", "input_identity_duplicates": { "company": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset TWoiDPMkcUUdlYBvF", "raw_input_records": 9, "raw_original_scraped_records": 44, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 9, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 14, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Győr, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "VhzKbuze8xyvQ1VjN", "finished_at": "2026-09-23T12:00:09.016Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 70, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-02-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-02-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-02-actor-run.json" }, "run_id": "q51Pa5GBR4YfzWlfa", "started_at": "2026-09-23T11:58:34.901Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:VhzKbuze8xyvQ1VjN", "input_identity_duplicates": { "company": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 15, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset VhzKbuze8xyvQ1VjN", "raw_input_records": 14, "raw_original_scraped_records": 70, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 14, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 124, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Magyarország", "maxCrawledPlacesPerSearch": 60, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "vízvezeték szerelő Debrecen", "szobafestő Debrecen", "vízvezeték szerelő Győr", "szobafestő Győr", "vízvezeték szerelő Pécs", "szobafestő Pécs", "vízvezeték szerelő Szeged", "szobafestő Szeged", "vízvezeték szerelő Miskolc", "szobafestő Miskolc", "vízvezeték szerelő Székesfehérvár", "szobafestő Székesfehérvár", "vízvezeték szerelő Kecskemét", "szobafestő Kecskemét", "vízvezeték szerelő Nyíregyháza", "szobafestő Nyíregyháza", "vízvezeték szerelő Szombathely", "szobafestő Szombathely" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "WupQAmJqDGZUFpgj4", "finished_at": "2026-09-23T13:54:16.053Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 4.33, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 892, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-10-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-10-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-10-actor-run.json" }, "run_id": "0mMImGh8mGlXU2OER", "started_at": "2026-09-23T13:39:33.805Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:WupQAmJqDGZUFpgj4", "input_identity_duplicates": { "company": { "distinct_identity_keys": 124, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 125, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 124, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 123, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 124, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset WupQAmJqDGZUFpgj4", "raw_input_records": 124, "raw_original_scraped_records": 892, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 124, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 7, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Debrecen, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "bcrNW3dKr83SOpIoi", "finished_at": "2026-09-23T11:49:20.642Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 87, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-01-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-01-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-01-actor-run.json" }, "run_id": "GnC1xrHs4H7o1Uw3s", "started_at": "2026-09-23T11:47:34.424Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:bcrNW3dKr83SOpIoi", "input_identity_duplicates": { "company": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset bcrNW3dKr83SOpIoi", "raw_input_records": 7, "raw_original_scraped_records": 87, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 7, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 49, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "burkoló Debrecen", "klímaszerelő Debrecen", "burkoló Győr", "klímaszerelő Győr", "burkoló Pécs", "klímaszerelő Pécs", "burkoló Szeged", "klímaszerelő Szeged", "burkoló Miskolc", "klímaszerelő Miskolc" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "egAiz3RhNVv2HKH3Z", "finished_at": "2026-09-23T14:44:34.494Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 2.01, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 372, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-11-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-11-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-11-actor-run.json" }, "run_id": "3vvOgHTx35wiDc65b", "started_at": "2026-09-23T14:32:29.631Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:egAiz3RhNVv2HKH3Z", "input_identity_duplicates": { "company": { "distinct_identity_keys": 49, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 50, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 49, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 49, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 49, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset egAiz3RhNVv2HKH3Z", "raw_input_records": 49, "raw_original_scraped_records": 372, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 49, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 7, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Pécs, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "hRhbu7S1XJh2NJulW", "finished_at": "2026-09-23T12:14:04.539Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 52, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-03-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-03-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-03-actor-run.json" }, "run_id": "YDqhUQutgruxVadWK", "started_at": "2026-09-23T12:12:30.603Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:hRhbu7S1XJh2NJulW", "input_identity_duplicates": { "company": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset hRhbu7S1XJh2NJulW", "raw_input_records": 7, "raw_original_scraped_records": 52, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 7, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 5, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": null, "historical_actor_receipt_status": "not_recovered_in_inspected_prior_pool_receipts", "historical_purchased_dataset": { "below_retrieval_limit": true, "bytes": 282213, "dataset_id": "mS7tXRgpO3yRpFpHp", "observed_country_codes": [ "HU", "None" ], "observed_search_strings": [ "bútorgyártás" ], "original_actor_input": null, "original_actor_run_receipt": null, "path": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/purchased-mS7tXRgpO3yRpFpHp.json", "raw_stage_semantics": "Retained purchased dataset file. Original actor input/run not recovered by this audit.", "record_count": 100, "records_type": "list", "retrieval_code_path": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/pilot.py", "retrieval_code_sha256": "d71be00b3cd96ce85fd36edbf226ee6147f8e85140a23b10c1cb3bb78628085f", "sha256": "737d85e1575e3f55d720a56a48249dfe2dd26654851dffec17b84765fa4d6bd1", "stored_retrieval_limit": 1100 }, "id": "historical_dataset:mS7tXRgpO3yRpFpHp", "input_identity_duplicates": { "company": { "distinct_identity_keys": 5, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 5, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 5, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 5, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 5, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset mS7tXRgpO3yRpFpHp", "raw_input_records": 5, "raw_original_scraped_records": 100, "raw_original_scraped_status": "verified_retained_dataset_below_1100_retrieval_limit_original_actor_input_unknown", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 5, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 10, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Nyíregyháza, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "tMcWZXzyTrebv6ovP", "finished_at": "2026-09-23T13:24:36.970Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 55, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-08-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-08-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-08-actor-run.json" }, "run_id": "aAxS9VtIYZ19KWr8b", "started_at": "2026-09-23T13:21:46.051Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:tMcWZXzyTrebv6ovP", "input_identity_duplicates": { "company": { "distinct_identity_keys": 10, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 11, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 10, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 10, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 10, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset tMcWZXzyTrebv6ovP", "raw_input_records": 10, "raw_original_scraped_records": 55, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 10, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 9, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Szeged, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "ujGSMGPg15Zygp5Jv", "finished_at": "2026-09-23T12:25:27.570Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 67, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-04-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-04-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-04-actor-run.json" }, "run_id": "wmiCcX8Sy5hLcVIot", "started_at": "2026-09-23T12:23:42.680Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:ujGSMGPg15Zygp5Jv", "input_identity_duplicates": { "company": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 8, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset ujGSMGPg15Zygp5Jv", "raw_input_records": 9, "raw_original_scraped_records": 67, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 9, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 9, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": null, "historical_actor_receipt_status": "not_recovered_in_inspected_prior_pool_receipts", "historical_purchased_dataset": { "below_retrieval_limit": true, "bytes": 1255061, "dataset_id": "xqRqADT0wWoWv6nIc", "observed_country_codes": [ "HU", "None" ], "observed_search_strings": [ "csomagolóanyag gyártás", "elektronikai gyártás", "vegyipari gyártás", "építőanyag gyártás" ], "original_actor_input": null, "original_actor_run_receipt": null, "path": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/purchased-xqRqADT0wWoWv6nIc.json", "raw_stage_semantics": "Retained purchased dataset file. Original actor input/run not recovered by this audit.", "record_count": 400, "records_type": "list", "retrieval_code_path": "/home/matt/.local/state/get-leads-review/maps-extension-20260923/pilot.py", "retrieval_code_sha256": "d71be00b3cd96ce85fd36edbf226ee6147f8e85140a23b10c1cb3bb78628085f", "sha256": "fc265bdf972537ed39cc71edebc3d6ee6e2349e0849b73cf33427bc76a7878cd", "stored_retrieval_limit": 1100 }, "id": "historical_dataset:xqRqADT0wWoWv6nIc", "input_identity_duplicates": { "company": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 12, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 9, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset xqRqADT0wWoWv6nIc", "raw_input_records": 9, "raw_original_scraped_records": 400, "raw_original_scraped_status": "verified_retained_dataset_below_1100_retrieval_limit_original_actor_input_unknown", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 9, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "drops": { "eligible_not_processed": 0, "input_not_admitted": 7, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "family_id": "legacy_maps", "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "historical_actor_receipt": { "actor_id": "nwua9Gu5YrADL7ZDj", "actor_input": { "countryCode": "hu", "language": "hu", "locationQuery": "Kecskemét, Magyarország", "maxCrawledPlacesPerSearch": 50, "maxImages": 0, "maxReviews": 0, "maximumLeadsEnrichmentRecords": 0, "scrapeContacts": false, "scrapePlaceDetailPage": false, "searchStringsArray": [ "generálkivitelezés", "nyílászáró beépítés", "kertépítés", "bútorasztalos" ], "skipClosedPlaces": false, "website": "withWebsite" }, "actor_name": "compass/crawler-google-places", "build_id": "25eYtYhYgMLbooPDN", "build_number": "0.14.759", "context_only": true, "dataset_id": "yf4wNhmhrRfV9GpQD", "finished_at": "2026-09-23T12:56:28.185Z", "options": { "build": "0.14.759", "diskMbytes": 8192, "isMaxTotalChargeUsdSetByUser": true, "maxItems": null, "maxTotalChargeUsd": 0.81, "memoryMbytes": 4096, "restartOnError": false, "timeoutSecs": 1800 }, "raw_record_count": 42, "receipt_paths": { "input": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-07-actor-input.json", "records": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-07-actor-records.json", "run": "/home/matt/.local/state/get-leads-review/maps-wave2-20260923/wave2-07-actor-run.json" }, "run_id": "QMwiOEGDkM3ctCao2", "started_at": "2026-09-23T12:54:17.314Z", "status": "SUCCEEDED" }, "historical_actor_receipt_status": "stored_exact_input_and_run", "id": "historical_dataset:yf4wNhmhrRfV9GpQD", "input_identity_duplicates": { "company": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "historical_dataset", "label": "Earlier Maps dataset yf4wNhmhrRfV9GpQD", "raw_input_records": 7, "raw_original_scraped_records": 42, "raw_original_scraped_status": "verified_prior_actor_dataset", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 7, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] } ], "source_families": [ { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 96, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 96, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 96, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 94, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 96, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "Actor results → raw identity/history prefilter → own-site scrape → visible email extraction → final candidate admission → MillionVerifier → model personalization/fit → current eligibility receipt. The later usable-scrape chart stage intersects the processed valid-email cohort with its already acquired site evidence.", "counts": { "category_counts_rows_only": { "construction_services": 37, "other_services": 1, "unresolved": 29 }, "current_ready": 38, "eligible_candidates": 96, "email_attempt_state_counts": { "completed": 67 }, "email_attempted_all": 67, "email_result_counts_attempted_only": { "catch_all": 8, "invalid": 5, "ok": 51, "unknown": 3 }, "model_attempted_candidates": 40, "model_generation_in_row": 38, "no_row_yet": 29, "observed_email_model_order": { "email_completed_before_model_dispatch": 39 }, "pending_total": 35, "pending_with_row": 6, "personalized_but_not_ready": 0, "processed": 61, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 38, "email_held": 16, "no_result_status": 29, "pending": 6, "uncertain_paid_held": 1, "worker_held": 6 }, "rows_in_sqlite": 67, "scrape_evidence_saved_all_candidates": 96, "supported_fit_within_valid_scraped_processed": 38, "supported_personalization_fit_all": 38, "terminal_outcome_count": 61, "usable_scrape_all_candidates": 96, "usable_scrape_within_valid_processed": 45, "valid_email_all": 51, "valid_email_pending": 6, "valid_email_within_processed": 45 }, "description": "Newly purchased current-run Google Maps results. Own-site email extraction precedes eligibility admission and email verification.", "drops": { "eligible_not_processed": 35, "email_candidates_rejected_by_final_history_check": 3, "processed_not_valid_email": 16, "raw_repeat_place_occurrences": 31, "unique_places_without_saved_usable_scrape": 331, "usable_without_email_candidate": 51, "valid_without_supported_fit": 7 }, "first_attribution": "Overlapping raw datasets use the first current actor query in index order for placeId attribution. Accepted candidates use their saved source_reservoir actor run, so each admitted company is counted once. All 96 accepted place IDs are attributed to their earliest raw query.", "id": "fresh_maps", "kind": "source_family", "label": "Fresh Google Maps via Apify", "own_site_email_candidates": 99, "post_email_extraction_rejected": 3, "raw_input_records": 512, "raw_original_scraped_records": 512, "raw_original_scraped_status": "verified_current_run_actor_datasets", "raw_repeat_place_occurrences": 31, "raw_unique_place_ids": 481, "raw_unique_website_domains": 459, "stage_order": "acquisition_then_readiness_cohort", "stages": [ { "count": 512, "key": "raw_actor_records", "label": "Raw Maps results", "status": "verified" }, { "count": 481, "key": "unique_places", "label": "Unique places", "status": "verified" }, { "count": 150, "key": "saved_usable_site", "label": "Usable own-site evidence", "note": "Distinct place IDs with a matching saved usable scrape, first attributed to earliest current dataset. No fresh scrape was run for this audit.", "status": "verified" }, { "count": 99, "key": "own_site_email_extracted", "label": "Own-site email extracted", "status": "verified" }, { "count": 96, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 61, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 45, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 45, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 38, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 38, "key": "current_ready", "label": "Current ready", "status": "verified" } ], "unique_places_with_saved_scrape": 210, "unique_places_with_saved_usable_scrape": 150 }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 297, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 316, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 297, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 199, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 297, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 7, "excluded": 1, "other_services": 15, "unresolved": 10 }, "current_ready": 6, "eligible_candidates": 297, "email_attempt_state_counts": { "completed": 22 }, "email_attempted_all": 22, "email_result_counts_attempted_only": { "catch_all": 10, "invalid": 3, "ok": 6, "unknown": 3 }, "model_attempted_candidates": 26, "model_generation_in_row": 23, "no_row_yet": 264, "observed_email_model_order": { "email_completed_before_model_dispatch": 1, "model_dispatched_before_email_completed": 21, "model_dispatched_without_a_completed_email_timestamp": 4 }, "pending_total": 264, "pending_with_row": 0, "personalized_but_not_ready": 16, "processed": 33, "processed_without_email_attempt": 11, "processing_status_counts": { "complete": 23, "model_held": 3, "no_result_status": 264, "scrape_unavailable": 7 }, "rows_in_sqlite": 33, "scrape_evidence_saved_all_candidates": 33, "supported_fit_within_valid_scraped_processed": 6, "supported_personalization_fit_all": 22, "terminal_outcome_count": 33, "usable_scrape_all_candidates": 26, "usable_scrape_within_valid_processed": 6, "valid_email_all": 6, "valid_email_pending": 0, "valid_email_within_processed": 6 }, "description": "Retained records imported from Google Sheets through staging.csv and master.jsonl. Original scraper inputs are not retained in the inspected receipts.", "drops": { "eligible_not_processed": 264, "input_not_admitted": 1049, "processed_not_valid_email": 27, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "legacy_sheets", "input_identity_duplicates": { "company": { "distinct_identity_keys": 1346, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 1433, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 1346, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 993, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 1346, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_family", "label": "Legacy Google Sheets imports", "raw_input_records": 1346, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "1462n8bFK61jYMlA_OSo98Lm6zxiszEnIFVVorS4DtyE", "17aN3vEQ2eVfs4zQ76dZSBGT48POxf5Zns2lODVv3SwU", "18l-qTgDfskAs5CgJX27wJXuCWk-SfyaPrYOwkBX3FAo", "1CkNd0uyZGudx-CJy-jg_wXLdQTXdpmVxxjCgmo5MmSE", "1GIA9Sxt9J9HfFj0ZfZmqBucSnqqZPTGJo0q7vHIH5to", "1GKPpi3PJBIfDL2YAF0VFVOutT7BFz8WmpNDrofarFlU", "1IbQ0bg_X7JkHi0KWZ5Bu5-EHlSZmBjr4bpWhCnniN80", "1huAYSNvOu_9NAwnEKksbgtv3z-Y7jpEH9coulgZMT_M", "1k_iZ-fCNSUmqt0AyyyclI_OGAGc6fqb9QTxzNHvBGCY", "1kxRhcfPs41nEj2zazsD2olfrzmanIKtkp--NazmZHCY", "1r1aczQGjxRP9KmJN5iu0xTRQgbkFTUrVXoVjZsdqOH0", "1rwAizuvg4maJ6Jrxi4PUcRL8geAVLwAm9zB2DHxgbGY", "1uqySxqJCLIEWkDGNmhactA1tkVJfEECWgiBdc6WAfaE", "1yLOaRe9pyAvyBgbJAOPKrOOnhDpFajDF38f_cTUWnek" ], "stage_order": "readiness_cohort", "stages": [ { "count": 1346, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 297, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 33, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 6, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 6, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 6, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 6, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 394, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 415, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 394, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 67, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 394, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "excluded": 1, "other_services": 3, "unresolved": 205 }, "current_ready": 3, "eligible_candidates": 394, "email_attempt_state_counts": { "completed": 209 }, "email_attempted_all": 209, "email_result_counts_attempted_only": { "catch_all": 49, "invalid": 96, "ok": 21, "unknown": 43 }, "model_attempted_candidates": 5, "model_generation_in_row": 4, "no_row_yet": 185, "observed_email_model_order": { "email_completed_before_model_dispatch": 5 }, "pending_total": 185, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 209, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 4, "email_held": 188, "model_held": 1, "no_result_status": 185, "scrape_unavailable": 16 }, "rows_in_sqlite": 209, "scrape_evidence_saved_all_candidates": 209, "supported_fit_within_valid_scraped_processed": 3, "supported_personalization_fit_all": 3, "terminal_outcome_count": 209, "usable_scrape_all_candidates": 116, "usable_scrape_within_valid_processed": 5, "valid_email_all": 21, "valid_email_pending": 0, "valid_email_within_processed": 21 }, "description": "Source label reservoir_hosts in the retained leads_v2.csv import.", "drops": { "eligible_not_processed": 185, "input_not_admitted": 877, "processed_not_valid_email": 188, "scraped_without_supported_fit": 2, "supported_not_current_ready": 0, "valid_without_usable_scrape": 16 }, "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "host_reservoir", "input_identity_duplicates": { "company": { "distinct_identity_keys": 1271, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 1316, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 1271, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 378, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 1271, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_family", "label": "Retained Hungarian host reservoir", "raw_input_records": 1271, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "reservoir_hosts" ], "stage_order": "readiness_cohort", "stages": [ { "count": 1271, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 394, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 209, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 21, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 5, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 3, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 3, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 51, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 52, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 51, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 51, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 51, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 5, "other_services": 1, "unresolved": 30 }, "current_ready": 6, "eligible_candidates": 51, "email_attempt_state_counts": { "completed": 36 }, "email_attempted_all": 36, "email_result_counts_attempted_only": { "catch_all": 4, "invalid": 9, "ok": 13, "unknown": 10 }, "model_attempted_candidates": 6, "model_generation_in_row": 6, "no_row_yet": 15, "observed_email_model_order": { "email_completed_before_model_dispatch": 6 }, "pending_total": 15, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 36, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 6, "email_held": 23, "no_result_status": 15, "scrape_unavailable": 7 }, "rows_in_sqlite": 36, "scrape_evidence_saved_all_candidates": 36, "supported_fit_within_valid_scraped_processed": 6, "supported_personalization_fit_all": 6, "terminal_outcome_count": 36, "usable_scrape_all_candidates": 23, "usable_scrape_within_valid_processed": 6, "valid_email_all": 13, "valid_email_pending": 0, "valid_email_within_processed": 13 }, "description": "Source label reservoir_osm in the retained leads_v2.csv import.", "drops": { "eligible_not_processed": 15, "input_not_admitted": 129, "processed_not_valid_email": 23, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 7 }, "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "osm_reservoir", "input_identity_duplicates": { "company": { "distinct_identity_keys": 180, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 186, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 180, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 169, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 180, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_family", "label": "Retained OpenStreetMap reservoir", "raw_input_records": 180, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "reservoir_osm" ], "stage_order": "readiness_cohort", "stages": [ { "count": 180, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 51, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 36, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 13, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 6, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 6, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 6, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "other_services": 1, "unresolved": 3 }, "current_ready": 1, "eligible_candidates": 4, "email_attempt_state_counts": { "completed": 4 }, "email_attempted_all": 4, "email_result_counts_attempted_only": { "catch_all": 1, "invalid": 1, "ok": 1, "unknown": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 1, "no_row_yet": 0, "observed_email_model_order": { "email_completed_before_model_dispatch": 1 }, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 4, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 1, "email_held": 3 }, "rows_in_sqlite": 4, "scrape_evidence_saved_all_candidates": 4, "supported_fit_within_valid_scraped_processed": 1, "supported_personalization_fit_all": 1, "terminal_outcome_count": 4, "usable_scrape_all_candidates": 3, "usable_scrape_within_valid_processed": 1, "valid_email_all": 1, "valid_email_pending": 0, "valid_email_within_processed": 1 }, "description": "Source label owned in the retained leads_v2.csv import. The label alone does not establish the original acquisition method.", "drops": { "eligible_not_processed": 0, "input_not_admitted": 10, "processed_not_valid_email": 3, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "owned", "input_identity_duplicates": { "company": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 14, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_family", "label": "Retained owned-source import", "raw_input_records": 14, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "owned" ], "stage_order": "readiness_cohort", "stages": [ { "count": 14, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 4, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 4, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 1, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 1, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 1, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 1, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 195, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 204, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 195, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 193, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 195, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 4, "excluded": 1, "unresolved": 141 }, "current_ready": 4, "eligible_candidates": 195, "email_attempt_state_counts": { "completed": 144, "uncertain": 2 }, "email_attempted_all": 146, "email_result_counts_attempted_only": { "catch_all": 58, "invalid": 26, "ok": 17, "provider_result_missing": 2, "unknown": 43 }, "model_attempted_candidates": 6, "model_generation_in_row": 5, "no_row_yet": 49, "observed_email_model_order": { "email_completed_before_model_dispatch": 6 }, "pending_total": 49, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 146, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 5, "email_held": 129, "model_held": 1, "no_result_status": 49, "scrape_unavailable": 11 }, "rows_in_sqlite": 146, "scrape_evidence_saved_all_candidates": 146, "supported_fit_within_valid_scraped_processed": 4, "supported_personalization_fit_all": 4, "terminal_outcome_count": 146, "usable_scrape_all_candidates": 124, "usable_scrape_within_valid_processed": 6, "valid_email_all": 17, "valid_email_pending": 0, "valid_email_within_processed": 17 }, "description": "Stored defect-scan output for the union of Common Crawl, host and OSM sources.", "drops": { "eligible_not_processed": 49, "input_not_admitted": 348, "processed_not_valid_email": 129, "scraped_without_supported_fit": 2, "supported_not_current_ready": 0, "valid_without_usable_scrape": 11 }, "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "commoncrawl_union", "input_identity_duplicates": { "company": { "distinct_identity_keys": 543, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 560, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 543, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 538, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 543, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_family", "label": "Common Crawl, hosts and OSM source union", "raw_input_records": 543, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "commoncrawl-hosts2-osm-and-sibling-source-union" ], "stage_order": "readiness_cohort", "stages": [ { "count": 543, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 195, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 146, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 17, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 6, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 4, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 4, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 877, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 966, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 877, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 875, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 877, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 20, "excluded": 2, "other_services": 12, "unresolved": 272 }, "current_ready": 32, "eligible_candidates": 877, "email_attempt_state_counts": { "completed": 305, "uncertain": 1 }, "email_attempted_all": 306, "email_result_counts_attempted_only": { "catch_all": 142, "invalid": 37, "ok": 53, "provider_result_missing": 1, "unknown": 73 }, "model_attempted_candidates": 36, "model_generation_in_row": 35, "no_row_yet": 571, "observed_email_model_order": { "email_completed_before_model_dispatch": 36 }, "pending_total": 571, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 306, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 35, "email_held": 252, "model_held": 1, "no_result_status": 571, "scrape_unavailable": 17, "uncertain_paid_held": 1 }, "rows_in_sqlite": 306, "scrape_evidence_saved_all_candidates": 305, "supported_fit_within_valid_scraped_processed": 32, "supported_personalization_fit_all": 32, "terminal_outcome_count": 306, "usable_scrape_all_candidates": 264, "usable_scrape_within_valid_processed": 36, "valid_email_all": 53, "valid_email_pending": 0, "valid_email_within_processed": 53 }, "description": "Stored defect-scan output for the existing Common Crawl and Hungarian-host reservoir.", "drops": { "eligible_not_processed": 571, "input_not_admitted": 1464, "processed_not_valid_email": 253, "scraped_without_supported_fit": 4, "supported_not_current_ready": 0, "valid_without_usable_scrape": 17 }, "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "commoncrawl_hosts", "input_identity_duplicates": { "company": { "distinct_identity_keys": 2341, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 2530, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 2341, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 2325, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 2341, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_family", "label": "Common Crawl and Hungarian hosts", "raw_input_records": 2341, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "existing-commoncrawl-and-hu-host-reservoir" ], "stage_order": "readiness_cohort", "stages": [ { "count": 2341, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 877, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 306, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 53, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 36, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 32, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 32, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 10, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 7, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": { "construction_services": 1, "unresolved": 5 }, "current_ready": 1, "eligible_candidates": 7, "email_attempt_state_counts": { "completed": 6 }, "email_attempted_all": 6, "email_result_counts_attempted_only": { "catch_all": 4, "invalid": 1, "ok": 1 }, "model_attempted_candidates": 1, "model_generation_in_row": 1, "no_row_yet": 1, "observed_email_model_order": { "email_completed_before_model_dispatch": 1 }, "pending_total": 1, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 6, "processed_without_email_attempt": 0, "processing_status_counts": { "complete": 1, "email_held": 5, "no_result_status": 1 }, "rows_in_sqlite": 6, "scrape_evidence_saved_all_candidates": 6, "supported_fit_within_valid_scraped_processed": 1, "supported_personalization_fit_all": 1, "terminal_outcome_count": 6, "usable_scrape_all_candidates": 6, "usable_scrape_within_valid_processed": 1, "valid_email_all": 1, "valid_email_pending": 0, "valid_email_within_processed": 1 }, "description": "Retained company-site contact crawl derived from the source union.", "drops": { "eligible_not_processed": 1, "input_not_admitted": 11, "processed_not_valid_email": 5, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "union_contacts", "input_identity_duplicates": { "company": { "distinct_identity_keys": 18, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 21, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 18, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 18, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 18, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_family", "label": "Source-union contact recrawl", "raw_input_records": 18, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "canonical-source-union-contact-crawl-20260729" ], "stage_order": "readiness_cohort", "stages": [ { "count": 18, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 7, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 6, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 1, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 1, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 1, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 1, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 52, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 54, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 52, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 49, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 52, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 52, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 52, "observed_email_model_order": {}, "pending_total": 52, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": { "no_result_status": 52 }, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "description": "Retained company-site contact crawl derived from the host reservoir.", "drops": { "eligible_not_processed": 52, "input_not_admitted": 66, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "reservoir_contacts", "input_identity_duplicates": { "company": { "distinct_identity_keys": 118, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 125, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 118, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 113, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 118, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_family", "label": "Common Crawl and host contact recrawl", "raw_input_records": 118, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "existing-commoncrawl-and-hu-host-reservoir-contact-crawl" ], "stage_order": "readiness_cohort", "stages": [ { "count": 118, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 52, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 2, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 2, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 2, "observed_email_model_order": {}, "pending_total": 2, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": { "no_result_status": 2 }, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "description": "Retained public company-site recrawls recovering published free-mail contacts.", "drops": { "eligible_not_processed": 2, "input_not_admitted": 2, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "freemail_recovery", "input_identity_duplicates": { "company": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 4, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_family", "label": "Published freemail recovery", "raw_input_records": 4, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "existing-reservoir-published-freemail-recovery", "existing-reservoir-published-freemail-recovery-complement" ], "stage_order": "readiness_cohort", "stages": [ { "count": 4, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 2, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 127, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 136, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 127, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 126, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 127, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 127, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 127, "observed_email_model_order": {}, "pending_total": 127, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": { "no_result_status": 127 }, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "description": "Retained public ÉMI / KTI registry records.", "drops": { "eligible_not_processed": 127, "input_not_admitted": 376, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "emi_registry", "input_identity_duplicates": { "company": { "distinct_identity_keys": 503, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 522, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 503, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 500, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 503, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_family", "label": "ÉMI contractor registry", "raw_input_records": 503, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "emi-kti-public-registry" ], "stage_order": "readiness_cohort", "stages": [ { "count": 503, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 127, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 25, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 25, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 25, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 25, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 25, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 25, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 25, "observed_email_model_order": {}, "pending_total": 25, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": { "no_result_status": 25 }, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "description": "Retained public MEE VET electrician search sample.", "drops": { "eligible_not_processed": 25, "input_not_admitted": 22, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "meevet_registry", "input_identity_duplicates": { "company": { "distinct_identity_keys": 47, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 47, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 47, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 46, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 47, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_family", "label": "MEE VET public search", "raw_input_records": 47, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "meevet-public-search" ], "stage_order": "readiness_cohort", "stages": [ { "count": 47, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 25, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] }, { "accepted_identity_duplicates": { "company": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 0, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "actual_execution_order": "The active processor verifies email first, then scrapes the site and personalizes valid-email candidates. Some earlier legacy results were generated before the email-first change. Stored events and side metrics retain those held results.", "counts": { "category_counts_rows_only": {}, "current_ready": 0, "eligible_candidates": 0, "email_attempt_state_counts": {}, "email_attempted_all": 0, "email_result_counts_attempted_only": {}, "model_attempted_candidates": 0, "model_generation_in_row": 0, "no_row_yet": 0, "observed_email_model_order": {}, "pending_total": 0, "pending_with_row": 0, "personalized_but_not_ready": 0, "processed": 0, "processed_without_email_attempt": 0, "processing_status_counts": {}, "rows_in_sqlite": 0, "scrape_evidence_saved_all_candidates": 0, "supported_fit_within_valid_scraped_processed": 0, "supported_personalization_fit_all": 0, "terminal_outcome_count": 0, "usable_scrape_all_candidates": 0, "usable_scrape_within_valid_processed": 0, "valid_email_all": 0, "valid_email_pending": 0, "valid_email_within_processed": 0 }, "description": "Previously prepared Maps pools were scanned as reservoir input. None were admitted to the additional-leads run.", "drops": { "eligible_not_processed": 0, "input_not_admitted": 338, "processed_not_valid_email": 0, "scraped_without_supported_fit": 0, "supported_not_current_ready": 0, "valid_without_usable_scrape": 0 }, "first_attribution": "A candidate is attributed to its immutable accepted source_id and source_name. Source-pool ownership uses the first path in the recorded input order. Duplicate raw identities are reported separately, never multiplied into ready counts.", "id": "legacy_maps", "input_identity_duplicates": { "company": { "distinct_identity_keys": 338, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "domain": { "distinct_identity_keys": 346, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "email": { "distinct_identity_keys": 338, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" }, "name": { "distinct_identity_keys": 335, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "Domains include aliases. Names shorter than five normalized characters are not deduplication keys." }, "source": { "distinct_identity_keys": 338, "duplicate_key_groups": 0, "extra_identity_occurrences": 0, "note": "" } }, "kind": "source_family", "label": "Earlier Maps pools, excluded from new supply", "raw_input_records": 338, "raw_original_scraped_records": null, "raw_original_scraped_status": "unknown", "source_names": [ "apify:compass/crawler-google-places" ], "stage_order": "readiness_cohort", "stages": [ { "count": 338, "key": "raw_pool_records", "label": "Raw retained candidate records", "note": "Candidate records scanned by the current run. Not an original historical scrape count.", "status": "verified" }, { "count": 0, "key": "eligible_candidates", "label": "Eligible candidate", "status": "verified" }, { "count": 0, "key": "processed", "label": "Processed", "status": "verified" }, { "count": 0, "key": "valid_email", "label": "Valid email", "note": "Completed processed candidates only. Valid emails in still-pending rows are shown separately.", "status": "verified" }, { "count": 0, "key": "usable_company_scrape", "label": "Usable company scrape", "note": "Intersection with all preceding stages. This is a readiness cohort, not chronological order for Maps.", "status": "verified" }, { "count": 0, "key": "supported_personalization_fit", "label": "Supported personalization and fit", "status": "verified" }, { "count": 0, "key": "current_ready", "label": "Current ready", "status": "verified" } ] } ], "target_additional_ready": 2000, "totals": { "additional_ready_shortfall": 1909, "all_input_record_occurrences": 7235, "category_counts_rows_only": { "construction_services": 74, "excluded": 5, "other_services": 33, "unresolved": 695 }, "current_ready": 91, "eligible_candidates": 2127, "email_attempt_state_counts": { "completed": 793, "uncertain": 3 }, "email_attempted_all": 796, "email_result_counts_attempted_only": { "catch_all": 276, "invalid": 178, "ok": 163, "provider_result_missing": 3, "unknown": 176 }, "historical_1200_ready_count_added": 0, "model_attempted_candidates": 121, "model_generation_in_row": 113, "new_maps_admitted": 96, "new_maps_raw_records": 512, "new_maps_unique_places": 481, "no_row_yet": 1320, "observed_email_model_order": { "email_completed_before_model_dispatch": 95, "model_dispatched_before_email_completed": 21, "model_dispatched_without_a_completed_email_timestamp": 4 }, "pending_total": 1326, "pending_with_row": 6, "personalized_but_not_ready": 16, "processed": 801, "processed_without_email_attempt": 11, "processing_status_counts": { "complete": 113, "email_held": 616, "model_held": 6, "no_result_status": 1320, "pending": 6, "scrape_unavailable": 58, "uncertain_paid_held": 2, "worker_held": 6 }, "ready_from_fresh_maps": 38, "ready_from_retained_sources": 53, "retained_admitted": 2031, "retained_input_candidate_records": 6723, "retained_rejected": 4692, "rows_in_sqlite": 807, "scrape_evidence_saved_all_candidates": 835, "supported_fit_within_valid_scraped_processed": 91, "supported_personalization_fit_all": 107, "terminal_outcome_count": 801, "usable_scrape_all_candidates": 658, "usable_scrape_within_valid_processed": 106, "valid_email_all": 163, "valid_email_pending": 6, "valid_email_within_processed": 157 } }