History

kiyo9w 306ea9b3e8 test(external): score 8 independent-source images, 0 false accepts Eight images for sku_l04, sku_l07 and sku_l09 from six source domains, scored through the shipped LocalLaneAdapter and DecisionPolicy against stock-lopia-clean: 4 correct accepts, 4 abstains, no false accepts. Leak-tested first: the highest template match of any image against add/image6.jpg is 0.675, so none is a crop of the evaluation photo. The result that matters is sku_l07. It has no enrolled image, and both its images accept through the text lane alone - one reads ラッキーフヨネーズ, the other the rear label's 製造者：丸和油脂株式会社 with 内容量：200g, which together name the row 丸和油脂ラッキーマヨネーズ 200g. The text lane's coverage claim holds on data that was not used to build it. The four l04 abstentions are correct behaviour: l04 is also unenrolled and its reads are weak (one reads only コと旨タ味, another scores 0.379 against a 0.45 accept line). Also records the l12 reconciliation, the Kewpie 450 g research, and two reusable pan clips with 11 rejected candidates for a future Tier-3 replay. Nothing here is Tier 2 or Tier 3 and every manifest says so.		2026-09-29 03:13:16 +09:00
..
evaluations/2026-09-29-session	test(server): record the real-endpoint smoke after the size gate	2026-09-29 03:06:28 +09:00
external-eval	test(external): score 8 independent-source images, 0 false accepts	2026-09-29 03:13:16 +09:00
packshots	docs(packshots): record l04/l07/l10 identity provenance	2026-09-29 02:51:55 +09:00
README.md	Enroll from a repo data dir; read packshots in every orientation	2026-09-29 02:33:47 +09:00

README.md

Recognition data

Everything the identity work needs to be reproducible: sourced packshots, evaluation runs, and the audits that produced them. Nothing here is ephemeral; a run that matters is written here, not to a temp directory.

`packshots/source/`

Front packshots as downloaded, before enrollment. ATTRIBUTION.json records the source URL, the product as printed, and the manufacturer for each. ocr-reads.json holds the OCR text each image produced, so a name/OCR refusal can be re-checked without re-running Vision.

rebuild_catalog.py reads this directory and writes a catalog:

.venv/bin/python code/rebuild_catalog.py --source data/packshots/source \
    --output stock-lopia-clean --csv stock-lopia/stock.csv --min-views 1 --replace

`evaluations/`

One directory per session. Each holds the raw artifacts a claim was computed from, so a number in DECISION.md can be traced back to the run that produced it.

Directory	Contents
`stream/`	WebSocket track dumps from `stream_client.py`, scored by `score_stream.py`.
`still/`	`/v1/recognize` responses for the still-image path.
`catalog-audit/`	`rebuild_catalog.py --json` reports.
`scratch/`	Intermediate images (rotations, crops) kept because they document a finding.

Scoring a stream dump:

.venv/bin/python code/score_stream.py data/evaluations/<session>/stream/<file>.json \
    --labels eval/labels/image6.json --stock-dir stock-lopia-clean