# Parent comparison: image 003

Parent: /root, local task 01a0e067-c27c-77f2-a3f9-ec52a44b62cf. Fresh describer: /root/blind_003, gpt-6-luna high, forked with no conversation context. Its only evidence input was this image. Parent has read its completed description and checked the image checksum.

[Actual screenshot](../inputs/003.png) · [Independent description](../descriptions/003.md)

Variant A. Captured action: Source workbook baseline in saved editor and PDF. URL: https://calendar-stage-20260923.cfd-staging.com/panel/proposals/?proposal=p_443dad7593c038b05e49b75dd468c49678d8df6676ec2b69cd96308c84bc1ca0. Screenshot SHA256: `e3a11352e398c9cf80e72bedf22e204303c4ab647cc6afa6113f0fc54ea1636d`.

- C07: When the original workbook fixture is loaded, then the sheet and PDF show the verified 374,500 Ft baseline, comprising 191,000 Ft labor, 25,000 Ft transport and 158,500 Ft materials, with source-excluded and unknown rows explicitly accounted for.

**Parent judgment: the described visible state supports its named evidence contribution.** The independent description identifies 374,500 Ft in both the editor summary and draft PDF preview. The source workbook hash was independently rechecked, with 16 row mappings and 18 formulas retained. The sanitized mapping and deployed scenario-1 PDFs independently reconcile 191,000 labor + 25,000 transport + 158,500 materials. Unknown/excluded row state and the unmapped M5 value are verified by those data/content checks. The image supports the required visible baseline, not arithmetic by itself.

[Completed GUI journeys and exact behavioral evidence](../../deployed-gui/scenario-matrix.md). [Source mapping without customer identity](../../source-mapping-sanitized.json). Full criterion acceptance also requires the other variant and its nonvisual checks. A screenshot is not treated as proof of persistence, timing, arithmetic or downloaded bytes.