feat: close measured model review evidence

2026-07-15 03:34:04 +02:00
parent 2a9b48d2b5
commit 919e102069
11 changed files with 512 additions and 9 deletions
@@ -964,6 +964,23 @@ geometry and green is a matched reference. Selection is deterministic and
 stratified by AOI and geodetic area bucket. Every CSV decision starts as
 `unreviewed`; no positive-training example is inferred.

+Validate the completed false-negative decisions symmetrically with the
+false-positive workflow:
+
+```bash
+docker exec geointel /opt/geointel/venv/bin/python \
+  /app/scripts/validate_detection_false_negative_review_decisions.py \
+  --review-summary /app/storage/operator-data/model-review/small-building-candidate/false-negative-visual-review/detection_false_negative_review_summary.json \
+  --decisions-csv /app/storage/operator-data/model-review/small-building-candidate/false-negative-visual-review/false_negative_review_decisions.csv \
+  --output-dir /app/storage/operator-data/model-review/small-building-candidate/false-negative-visual-review/validated \
+  --require-complete
+```
+
+The validator exits with code `2` while any row remains `unreviewed`. It emits
+only explicit `confirmed_model_false_negative` geometries; alignment,
+reference-gap and uncertain imagery decisions never become positive training
+labels.
+
 Reference features that do not intersect any persisted inference tile are not
 silently counted as reviewable model misses. They are reported separately in
 `false_negatives_outside_tile_coverage.geojson` with