Classify operator background corpus

scripts/README.md

@@ -187,8 +187,11 @@ Kasterlee-bos, Dessel-heide, Ravels-bos, Meerhout-bos, Geel-Bel,
 Arendonk-heide and Herenthout-bos. Normal reference AOIs still fail when GRB
 returns no buildings; background candidates are explicitly marked with
 `sample_role` and may write an empty reference FeatureCollection for
-negative-tile training. The helper fetches only the explicit documented AOIs,
-records Digitaal Vlaanderen attribution and reuses existing files by default.
+negative-tile training. Generated manifests also classify background samples as
+`pure_empty_negative` when GRB returns zero reference buildings or
+`sparse_building_context` when GRB returns one or more contextual buildings.
+The helper fetches only the explicit documented AOIs, records Digitaal
+Vlaanderen attribution and reuses existing files by default.
 Use `--force` only when the local runtime artifacts should be regenerated.
 GRB building references are fetched through the provider's OGC API
 `rel=next` pagination links, so dense AOIs are not silently limited to the
@@ -472,6 +475,7 @@ before changing model defaults:
 
 ```bash
 OPERATOR_SAMPLE_MANIFEST_PATH=storage/operator-data/operator_samples_manifest.json \
+OPERATOR_BACKGROUND_CATEGORIES="pure_empty_negative" \
 OPERATOR_BACKGROUND_SAMPLE_SLUGS="postel_bos lommel_heide kasterlee_bos dessel_heide ravels_bos meerhout_bos geel_bel arendonk_heide herenthout_bos" \
 QUALITY_MODEL_ASSET_IDS="geointel-building-yolov8n-expanded160e50-pt geointel-building-yolov8n-tile30-pt yolov8s-building-segmentation-pt" \
 QUALITY_TILE_SIZES="640" \
@@ -485,7 +489,12 @@ The hard-negative matrix uploads only the background raster, generates tiles,
 runs configured-YOLO detection and counts persisted detections as
 `false_positive_pressure`. It does not upload a reference vector and does not
 run QA/QC, because empty or sparse background AOIs do not have a meaningful
-precision/recall target. In the first live run, `geointel-building-yolov8n-expanded160e50-pt`
+precision/recall target. Use `OPERATOR_BACKGROUND_CATEGORIES="pure_empty_negative"`
+for the strict default-promotion false-positive gate. Run
+`OPERATOR_BACKGROUND_CATEGORIES="sparse_building_context"` separately for
+contextual review; sparse-context detections should be inspected, not counted
+as fake precision/recall metrics. In the first live run,
+`geointel-building-yolov8n-expanded160e50-pt`
 was clean on Postel-bos and Lommel-heide at thresholds `0.25` and `0.15`, but
 produced 38 detections on Kasterlee-bos even at `0.25`. That blocks it from
 becoming a V1 default until a hard-negative-balanced candidate improves.