kiyo9w 4bdad66bbe docs(decision): record the far-unknown calibration and the gate status ... The far-unknown claim in the verdict said 0.2-0.7% on 602 crops. That was the audit's variant matcher on the add/ photos; the shipped lane at the shipped lines was 3.61% on the Wikimedia sets. Both are now stated, with the sweep that chose 4.0/4 and the live-endpoint result: 44 named, 42 correct, 95.5% precision against 53/48/90.6% before. Gate status is recorded per gate rather than as a blanket claim: G2 and G3's far half pass offline, G8 passes, and G1/G4/G5/G6/G7 are not yet measured on held-out data because Tier 2 does not exist. The Wikimedia manifests and results are committed; the 59 MB of images are not, because collect_shelf_images.py fetches them from the source URLs the manifests record.		2026-09-29 04:11:00 +09:00
..
research/2026-09-28-recognition-architecture	docs(decision): record the far-unknown calibration and the gate status	2026-09-29 04:11:00 +09:00
API.md	docs: describe the mobile lane as shipped, and fix the capabilities example	2026-09-28 19:10:31 +09:00
DATA.md	docs: require explicit backend for legacy walks	2026-09-28 14:42:12 +09:00
design-price-tags-and-compliance.md	docs: design for price-tag OCR, reconciliation, compliance, and mobile scan	2026-09-24 13:45:54 +09:00
EXTERNAL-EVAL.md	feat: a store's fine-tuned head, and the two-stage gate it needs	2026-09-25 03:21:22 +09:00