product-recognition-demo/recognization/data/evaluations/2026-09-29-session/server-smoke
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
..
gate-summary.json docs(decision): record the far-unknown calibration and the gate status 2026-09-29 04:11:00 +09:00
recognize-after-l12-rename.json docs(decision): refresh every number the corrected labels moved 2026-09-29 03:18:30 +09:00
recognize-after-size-gate.json test(server): record the real-endpoint smoke after the size gate 2026-09-29 03:06:28 +09:00
recognize-final.json test(server): final smoke with every catalog correction live 2026-09-29 03:41:05 +09:00
recognize-gate-calibrated.json docs(decision): record the far-unknown calibration and the gate status 2026-09-29 04:11:00 +09:00
summary.json test(server): final smoke with every catalog correction live 2026-09-29 03:41:05 +09:00