docs(accuracy): publish phase 4 benchmark evidence

docs/accuracy-program/status.json

@@ -2,7 +2,7 @@
   "schema_version": 1,
   "program": "GeoIntel Accuracy Improvement Program",
   "phase": "P4",
-  "generated_at": "2026-08-02T01:04:48+02:00",
+  "generated_at": "2026-08-02T04:40:51+02:00",
   "scope": {
     "product": "Belgium and the Belgian North Sea",
     "active_building_model_claim": "Mol/Kempen only, operator review required",
@@ -104,9 +104,56 @@
     ]
   },
   "phase4": {
-    "status": "ready",
-    "meaning": "Ready to remediate and review the P3 anomaly and quarantine manifests; release gates remain governed by P2 and the execution contract.",
-    "evidence_root": "artifacts/evidence/accuracy/P3"
+    "status": "in_progress",
+    "meaning": "The content-addressed local evaluation harness passes, but the governed product benchmark fails on confirmed Phase-3 leakage and remains not evaluable for missing product evidence.",
+    "workflow": "scripts/run_accuracy_phase4_benchmark.py",
+    "workflow_version": "2.0.1",
+    "evaluator_version": "2.1.0",
+    "split_generator_version": "1.3.0",
+    "local_harness_status": "pass",
+    "product_benchmark_status": "fail",
+    "phase4_done": false,
+    "evidence_run_id": "p4-2.0.1-9677d0ef37db82bcf39b",
+    "evidence_root": "artifacts/evidence/accuracy/P4/runs/p4-2.0.1-9677d0ef37db82bcf39b",
+    "repository_commit": "70fb4b94e5cb7c248beec5a936ce186f38cc183c",
+    "benchmark_manifest_sha256": "0ea5ab07f46c509a7a24943b31d5e9bfd6368920609227bc47613e18e52c4642",
+    "benchmark_file_sha256": "868dd7eb2dfa8344e417879ed3f5dd7c7d9e5673add7e3e2294c5cbde4b75d57",
+    "evidence_manifest_file_sha256": "fdc15a95ee2a0754dfa169f4b41036e084b8d8909afc37fd8ea68ee6b9210f98",
+    "release_gate_report_file_sha256": "e5f1c9c43c8da22acfa5486e641c010a278431f90634f91335b039ab7bdb50a4",
+    "product_gate_evidence_sha256": "c9f5e3de3ab6d64911f8807b26caa661ccf911a5fd6b995107edda2004836e0c",
+    "case_count": 9,
+    "task_family_count": 7,
+    "implemented_capability_count": 15,
+    "failure_example_count": 14,
+    "split_counts": {
+      "background-test": 2,
+      "calibration": 2,
+      "challenge": 4,
+      "test": 7,
+      "train": 3,
+      "val": 3
+    },
+    "blockers": [
+      "configured active model bytes are not locally accessible",
+      "no governed seven-task product baseline manifest with current CUDA receipt exists",
+      "Phase-3 leakage status is attention and therefore a failing product gate",
+      "no checksum-bound representative human review ledger exists",
+      "no governed zero-under-2-km product split audit exists",
+      "no protected vault evidence with hash-chained access log exists",
+      "no complete task-zone authority portfolio exists",
+      "no representative support over all thirteen subgroup dimensions exists"
+    ],
+    "does_not_mean": [
+      "Phase 4 is complete",
+      "production accuracy is measured",
+      "Phase 5 is ready",
+      "training or promotion is allowed"
+    ]
+  },
+  "phase5": {
+    "status": "not_ready",
+    "meaning": "Phase 5 remains blocked until every governed Phase-4 product gate passes in the same checksum-bound workflow.",
+    "blocked_by": "phase4"
   },
   "runtime": {
     "cuda_available": true,
@@ -276,6 +323,35 @@
       "static_inventory": "artifacts/evidence/accuracy/P2/source-contract-inventory.json",
       "claim_boundary": "This is not a production migration deployment, corpus-release, accuracy or promotion result."
     },
+    "phase4_evaluation": {
+      "status": "local_pass_product_fail",
+      "targeted_tests": {
+        "passed": 60,
+        "duration_seconds": 22.28
+      },
+      "relevant_regression_tests": {
+        "passed": 103,
+        "duration_seconds": 27.61,
+        "shell_provider": "C:/Program Files/Git/bin/bash.exe",
+        "note": "The Windows Store WSL bash stub was unavailable; the same shell syntax test passed with the installed Git Bash provider."
+      },
+      "ruff": "pass",
+      "format_check": "pass",
+      "compileall": "pass",
+      "python_typecheck": "not_configured",
+      "alembic_head": "202608010001",
+      "migration_and_provenance_tests": {
+        "passed": 29,
+        "duration_seconds": 5.73
+      },
+      "workflow_reproduction": {
+        "allow_product_blocked_exit": 0,
+        "default_exit": 2,
+        "byte_identical": true,
+        "status_bookkeeping_stable": true
+      },
+      "claim_boundary": "Local harness and contract gates pass. Product accuracy is not measured; Phase-3 leakage fails and missing governed product evidence remains not evaluable."
+    },
     "golden_qa": {
       "semantic_results_stable": true,
       "byte_identical": false,
@@ -311,12 +387,21 @@
     "docs/accuracy-program/06-implementation-roadmap.md",
     "docs/accuracy-program/07-source-authority-matrix.md",
     "docs/accuracy-program/08-data-contracts.md",
-    "docs/accuracy-program/09-full-data-scan.md"
+    "docs/accuracy-program/09-full-data-scan.md",
+    "docs/accuracy-program/10-evaluation-protocol.md",
+    "docs/accuracy-program/11-baseline-benchmark.md",
+    "docs/accuracy-program/12-release-gates.md"
   ],
   "evidence_root": "artifacts/evidence/accuracy/P1",
   "evidence_manifest": "artifacts/evidence/accuracy/P1/evidence-manifest.json",
   "phase2_evidence_root": "artifacts/evidence/accuracy/P2",
   "phase2_evidence_manifest": "artifacts/evidence/accuracy/P2/evidence-manifest.json",
   "phase3_evidence_root": "artifacts/evidence/accuracy/P3",
-  "phase3_manifest": "artifacts/evidence/accuracy/P3/full-scan-manifest.json"
+  "phase3_manifest": "artifacts/evidence/accuracy/P3/full-scan-manifest.json",
+  "phase4_evidence_root": "artifacts/evidence/accuracy/P4/runs/p4-2.0.1-9677d0ef37db82bcf39b",
+  "phase4_evidence_manifest": "artifacts/evidence/accuracy/P4/runs/p4-2.0.1-9677d0ef37db82bcf39b/evidence-manifest.json",
+  "phase4_benchmark_manifest": "artifacts/evidence/accuracy/P4/runs/p4-2.0.1-9677d0ef37db82bcf39b/benchmark-manifest.json",
+  "phase4_release_gate_report": "artifacts/evidence/accuracy/P4/runs/p4-2.0.1-9677d0ef37db82bcf39b/release-gate-report.json",
+  "phase4_metric_report": "artifacts/evidence/accuracy/P4/runs/p4-2.0.1-9677d0ef37db82bcf39b/metric-report.json",
+  "phase4_failure_gallery": "artifacts/evidence/accuracy/P4/runs/p4-2.0.1-9677d0ef37db82bcf39b/failure-gallery.json"
 }