5 Commits

Include renames

Author	SHA1	Message	Date
JensandClaude Opus 5	5278fcd361	bound the QA evidence overlay and fetch only what it draws ... evidence_geojson emitted one feature per false positive, one per false negative and two per match, with no limit. A regional check of 40k detections against 45k reference footprints produced well over a hundred thousand features in a single response, plus one warning string per unresolvable identifier. The endpoint the entire review workflow depends on therefore failed exactly where review matters most. What to draw is now decided before any geometry is fetched, so the query work is proportional to the result rather than to the size of the check — previously 130k geometries were resolved through an IN clause holding every identifier in the check, to then discard most of them. The budget is split between misses and false positives in proportion to their populations with at least one of each, rather than by strict priority, which would mean a check with 50.000 misses and three false positives never showed one. Confirmations fill what remains, and a match is kept or dropped as a pair because half a match is not reviewable evidence. limit_evidence and evidence_role_counts are removed: plan_evidence supersedes them, and helpers kept alive only by their own tests read like a contract. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-22 15:14:26 +02:00
JensandClaude Opus 5	2b968b74cf	make QA scoring reproducible and threshold-independent ... The greedy IoU matcher gave a reference to whichever candidate was offered first. Row order decided that, and every detection in a run shares one transaction timestamp, so ordering by created_at left the assignment undefined: the same QA run over the same data produced different mean IoU, and the geometry shown to a reviewer as a false positive could be the better of two detections. Candidates are now ranked by confidence with feature identity as tiebreaker, which is also the COCO/PASCAL rule. A single precision/recall/F1 triple describes one operating point, so two models cannot be compared from it: a conservatively calibrated model looks worse at a low confidence cut and better at a high one without detecting anything differently. DetectionMetricsService adds the full curve, average precision and the threshold where F1 actually peaks. Also: - report the population the metrics were computed over, so matches + false_positives equals candidate_feature_count even under an area filter; raw dataset totals move to the _raw fields; - state whether candidates are axis-aligned boxes or footprint polygons. A box can never reach IoU 1 against a rotated building, so the strict score has a ceiling that has nothing to do with detection quality. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-08-22 14:31:21 +02:00
Codex	0fae53a7de	Harden RC7 API response contracts	2026-07-18 05:07:35 +02:00
Codex	368c1ad738	Persist QA feature evidence	2026-06-25 02:57:50 +02:00
Codex	6ea3586a3e	Initial GeoIntel V1 foundation	2026-06-16 23:36:32 +02:00