product-recognition-demo/recognization/data/evaluations/2026-09-29-session
kiyo9w 01d9a5e614 docs(decision): re-measure the stream and live rows after the calibration
The stream row was recorded before the accept lines moved. Three fresh 20 s pan
replays through the shipped lane: 70-74% coverage at 77-85% precision, 0 wrong
labels in all three (0-1 before), 8-14 unknown false accepts - the near-unknown
case, which the size gate and catalog completeness own rather than the accept
line.

Live resolution on the shipped evaluator: 56% end-to-end at 97% precision with
1 false accept, so the calibration is not a full-resolution artifact.

The recordings are committed under stream-gated/ so the row is reproducible.
2026-09-29 04:22:46 +09:00
..
catalog-audit chore(eval): reconcile the distractor sets and refresh the sweep numbers 2026-09-29 04:17:54 +09:00
scratch chore(eval): reconcile the distractor sets and refresh the sweep numbers 2026-09-29 04:17:54 +09:00
server-smoke docs(decision): record the far-unknown calibration and the gate status 2026-09-29 04:11:00 +09:00
still Enroll from a repo data dir; read packshots in every orientation 2026-09-29 02:33:47 +09:00
stream Enroll from a repo data dir; read packshots in every orientation 2026-09-29 02:33:47 +09:00
stream-gated docs(decision): re-measure the stream and live rows after the calibration 2026-09-29 04:22:46 +09:00