docs(decision): record the far-unknown calibration and the gate status

Browse source

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.

...

This commit is contained in:

kiyo9w 2026-09-29 04:11:00 +09:00

parent 07de2bd37d

commit 4bdad66bbe

7 changed files with 1264 additions and 2 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

1

recognization/data/evaluations/2026-09-29-session/server-smoke/recognize-gate-calibrated.json Normal file

View file

File diff suppressed because one or more lines are too long