feat: add coverage-aware Mol benchmark

scripts/README.md

@@ -261,9 +261,20 @@ confidence `0.15` and QA IoU `0.25`. Every positive run persists Project, Area,
 Dataset, Job, AnalysisRun, Detection, QualityCheck, Metric and Export records.
 The background run persists its project, AOI, raster, job, analysis and
 detections but intentionally does not invent QA metrics for an empty or sparse
-reference context. The combined JSON/Markdown summary reports
-`evidence_ready`; this records completed evidence and is not an automatic model
-promotion decision.
+reference context. Each matrix row now preserves the exact persisted inference
+coverage counts and the diagnostic-only reference-envelope comparison beside
+the canonical footprint-IoU metrics.
+
+The runner also writes `mol_operational_benchmark_report.json` and `.md`. The
+default operational gates require four positive holdouts, one background
+control, coverage provenance for every positive run, at least 95% reference
+coverage in every zone, mean F1 at least `0.25`, per-zone F1 at least `0.10`
+and zero detections in each pure-empty control. Override the numeric gates only
+through the documented `MOL_MIN_MEAN_F1`, `MOL_MIN_ZONE_F1`,
+`MOL_MIN_REFERENCE_COVERAGE` and `MOL_MAX_BACKGROUND_DETECTIONS` variables.
+An `accepted` report records bounded operational evidence; it does not mutate
+the active model. A `review_required` report is still a successful benchmark
+execution but explicitly blocks a promotion recommendation.
 
 For model-training candidates, prepare a larger operator-only sample manifest so
 tile overlap can create meaningful context instead of one tile per source
@@ -344,7 +355,10 @@ logs plus `quality_matrix_summary.json` under
 set. The summary ranks `best_by_score`, `best_by_recall` and
 `best_by_precision` so the next model decision is based on persisted
 `QualityCheck`/`Metric` evidence rather than visual guesses. It does not create
-provider data, use fixtures or download model weights.
+provider data, use fixtures or download model weights. Coverage-aware rows also
+record raw/evaluated/excluded/clipped candidate and reference counts, tile
+coverage provenance and the separately labelled box-to-footprint diagnostic
+gap.
 
 Run the same matrix across every prepared operator sample: