feat: add coverage-aware Mol benchmark

scripts/run_multi_sample_detection_quality_matrix.sh

@@ -184,6 +184,12 @@ for summary_path in sorted(glob.glob(str(output_dir / "*" / "quality_matrix_summ
     for item in items:
         enriched = dict(item)
         enriched["sample_slug"] = sample_slug
+        enriched["sample_display_name"] = sample_metadata.get("display_name")
+        enriched["municipality"] = sample_metadata.get("municipality")
+        enriched["operational_zone"] = sample_metadata.get("operational_zone")
+        enriched["recommended_split"] = sample_metadata.get("recommended_split")
+        enriched["manifest_reference_feature_count"] = sample_metadata.get("reference_feature_count")
+        enriched["wgs84_bbox"] = sample_metadata.get("wgs84_bbox")
         flat_items.append(enriched)
     sample_summaries.append(
         {
@@ -232,10 +238,10 @@ summary_path.write_text(json.dumps(summary, indent=2, sort_keys=True), encoding=
 
 print("")
 print("Multi-sample detection quality summary")
-print("sample\tmodel\ttile\toverlap\tthreshold\tdetections\traw\tsuppressed\tscore\tprecision\trecall\tf1\tmatches\tfp\tfn")
+print("sample\tzone\tmodel\ttile\toverlap\tthreshold\tdetections\traw\tsuppressed\tscore\tprecision\trecall\tf1\tmatches\tfp\tfn\tcoverage\tdiagnostic_gap")
 for item in flat_items:
     print(
-        "{sample_slug}\t{model_asset_id}\t{tile_size}\t{tile_overlap}\t{threshold:.2f}\t{detection_count}\t{raw_detection_count}\t{suppressed_detection_count}\t{quality_score}\t{precision}\t{recall}\t{f1_score}\t{matches}\t{false_positives}\t{false_negatives}".format(
+        "{sample_slug}\t{operational_zone}\t{model_asset_id}\t{tile_size}\t{tile_overlap}\t{threshold:.2f}\t{detection_count}\t{raw_detection_count}\t{suppressed_detection_count}\t{quality_score}\t{precision}\t{recall}\t{f1_score}\t{matches}\t{false_positives}\t{false_negatives}\t{reference_coverage_ratio}\t{possible_box_to_footprint_mismatch_count}".format(
             **item
         )
     )