Make dataset audit mandatory for training loop

scripts/run_belgium_building_training_loop.py

@@ -78,6 +78,7 @@ def main() -> int:
     parser = argparse.ArgumentParser()
     parser.add_argument("--initial-model", type=Path, required=True)
     parser.add_argument("--train-yaml", type=Path, required=True)
+    parser.add_argument("--dataset-audit", type=Path, required=True)
     parser.add_argument("--calibration-summary", type=Path, required=True)
     parser.add_argument("--test-summary", type=Path, required=True)
     parser.add_argument("--background-summary", type=Path, required=True)
@@ -93,6 +94,11 @@ def main() -> int:
     args = parser.parse_args()
     if args.iterations < 1:
         raise SystemExit("--iterations must be positive")
+    dataset_audit = json.loads(args.dataset_audit.read_text(encoding="utf-8"))
+    if dataset_audit.get("status") != "ok":
+        raise SystemExit(f"Dataset audit is not ok: {args.dataset_audit}")
+    if int(dataset_audit.get("low_variance_positive_tile_count") or 0) != 0:
+        raise SystemExit("Dataset audit contains blank/low-variance positive tiles")
 
     state_path = args.output_dir / "training-loop-state.json"
     state: dict[str, Any] = {
@@ -101,6 +107,7 @@ def main() -> int:
         "started_at": datetime.now(UTC).isoformat(),
         "initial_model": str(args.initial_model),
         "train_yaml": str(args.train_yaml),
+        "dataset_audit": str(args.dataset_audit),
         "corpus_manifest": str(args.corpus_manifest),
         "iterations": [],
     }