Gate YOLO tile labels by visible ratio

docs/CODEX_EXECUTION_LOG.md

@@ -1,3 +1,27 @@
+## Sprint 150 YOLO label visible-ratio gate (2026-07-09)
+
+Changed:
+- Added `--min-label-visible-ratio` / `OPERATOR_YOLO_MIN_LABEL_VISIBLE_RATIO` to `scripts/export_operator_yolo_tile_dataset.py`.
+- The tile exporter now computes the visible share of each original building bbox inside a tile and can drop labels below the configured ratio.
+- Default remains `0` for legacy behavior; use `0.25` for the next overlap-heavy operator dataset experiment.
+- Tile dataset summaries include `min_label_visible_ratio`.
+- `scripts/audit_operator_yolo_dataset_quality.py` now reports `min_label_visible_ratio` in JSON and Markdown.
+- Updated operator script documentation.
+
+Why:
+- The current rejected AOI512 candidate still shows low precision/recall after max-det and duplicate suppression hardening.
+- A likely label-quality issue is that overlapping tile export can create many small clipped edge labels for buildings mostly outside a tile.
+- This pass improves the next training dataset gate without activating a model, faking detections, fetching providers or changing persistence.
+
+Tested:
+- Red step: `python -m pytest backend\tests\test_sprint130_operator_yolo_tile_dataset.py -q` failed because the exporter lacked `min_label_visible_ratio`, CLI help and visible-fragment filtering.
+- `python -m pytest backend\tests\test_sprint130_operator_yolo_tile_dataset.py -q` (`6 passed`)
+- Red step: `python -m pytest backend\tests\test_sprint146_operator_yolo_dataset_quality_audit.py -q` failed because the audit report did not expose `min_label_visible_ratio`.
+- `python -m pytest backend\tests\test_sprint130_operator_yolo_tile_dataset.py backend\tests\test_sprint146_operator_yolo_dataset_quality_audit.py -q` (`7 passed`)
+
+Next:
+- Run full readiness, deploy Tower, export a new visible-ratio-gated operator tile dataset, audit it, then decide whether it is good enough for another CPU training candidate.
+
 ## Sprint 149 YOLO duplicate suppression evidence (2026-07-09)
 
 Changed:

docs/TODO.md

@@ -114,9 +114,10 @@ This file now starts with the current implementation status. Older preparation/b
 - [x] Rerun live dense-AOI calibration after redeploy with `YOLO_MAX_DETECTIONS=1000`; Westerlo reached 523/1000 detections at lower thresholds and Turnhout reached 822/1000, confirming the old 300 cap is removed.
 - [x] Add configured-YOLO cross-tile duplicate suppression and raw/suppressed calibration evidence fields.
 - [x] Rerun live dense-AOI calibration after redeploy with `YOLO_DUPLICATE_IOU_THRESHOLD=0.5`; Westerlo 0.25 improved to F1 `0.2537313432835821` and Turnhout 0.25 improved to F1 `0.14114114114114112`, but the candidate remains rejected.
+- [x] Add `OPERATOR_YOLO_MIN_LABEL_VISIBLE_RATIO` so the next overlapping-tile dataset can drop tiny clipped edge-fragment labels.
 - [ ] Find or train a materially stronger aerial/Kempen building model candidate; `geointel-building-yolov8n-expanded160e50-pt` is the best current dense-AOI candidate but still too weak and too noisy for a V1 default.
 - [ ] Train a higher-capacity local aerial-building detector with stronger positive recall while preserving the hard-negative false-positive gate.
-- [ ] Add more diverse positive AOIs and revisit geometry-to-box label strategy before the next default-model training attempt.
+- [ ] Export and audit a visible-ratio-gated tile dataset on Tower before the next default-model training attempt.
 - [ ] Build the next candidate gate around better positive AOI coverage, label strategy and hard-negative retention.
 
 ## Sprint 8 status