Record retained validation coverage

scripts/README.md

@@ -366,6 +366,9 @@ The tile exporter clips GRB building bounding boxes into each tile, writes
 YOLO labels beside each tile image, keeps a deterministic ratio of empty
 negative tiles, and records `yolo_tile_dataset_summary.json` with
 `positive_tile_count`, `negative_tile_count` and skipped negative tile counts.
+It separately records configured, retained and empty validation sample slugs;
+this keeps a holdout that lost every tile to quality filtering visible without
+pretending it contributed evaluation data.
 `--min-label-visible-ratio` drops labels where only a small clipped fragment of
 the original building bbox is visible inside the tile; this reduces noisy
 tile-edge labels in overlapping-tile datasets. Use `0` for legacy behavior.

scripts/export_operator_yolo_tile_dataset.py

@@ -181,6 +181,21 @@ def validate_validation_split(samples: list[dict[str, Any]], val_slugs: set[str]
     return val_slugs
 
 
+def validation_sample_coverage(
+    tiles: list[dict[str, Any]],
+    val_slugs: set[str],
+) -> dict[str, list[str]]:
+    retained = {
+        str(tile.get("sample_slug") or "").strip().lower()
+        for tile in tiles
+        if tile.get("kept", True) and str(tile.get("split") or "") == "val"
+    }
+    return {
+        "retained_validation_sample_slugs": sorted(retained),
+        "empty_validation_sample_slugs": sorted(val_slugs - retained),
+    }
+
+
 def edge_starts(length: int, tile_size: int, stride: int) -> list[int]:
     if tile_size <= 0:
         raise ValueError("tile_size must be positive")
@@ -555,6 +570,7 @@ def main() -> int:
         for tile in skipped_negative_tiles
         if tile.get("skip_reason") == LOW_VARIANCE_NEGATIVE_SKIP_REASON
     ]
+    validation_coverage = validation_sample_coverage(kept_tiles, val_slugs)
     summary = {
         "status": "ok",
         "dataset_yaml": str(dataset_yaml),
@@ -570,6 +586,7 @@ def main() -> int:
         "blank_range_threshold": args.blank_range_threshold,
         "source_sample_count": len(samples),
         "validation_sample_slugs": sorted(val_slugs),
+        **validation_coverage,
         "tile_count": len(kept_tiles),
         "positive_tile_count": len(positive_tiles),
         "negative_tile_count": len(negative_tiles),