{
  "benchmark": "synthetic_repo_native",
  "case_count": 36,
  "categories": {
    "allowlist": {
      "cases": 3,
      "passed": 3
    },
    "complete": {
      "cases": 3,
      "passed": 3
    },
    "conflict": {
      "cases": 3,
      "passed": 3
    },
    "credentials": {
      "cases": 3,
      "passed": 3
    },
    "customer_data": {
      "cases": 3,
      "passed": 3
    },
    "data_boundary": {
      "cases": 3,
      "passed": 3
    },
    "missing_critical": {
      "cases": 6,
      "passed": 6
    },
    "multilingual": {
      "cases": 3,
      "passed": 3
    },
    "optional_abstention": {
      "cases": 3,
      "passed": 3
    },
    "prompt_injection": {
      "cases": 3,
      "passed": 3
    },
    "unsafe_action": {
      "cases": 3,
      "passed": 3
    }
  },
  "claim_boundary": "Deterministic baseline proof only; this is not a model-quality claim.",
  "contract_version": "brief_mapping_eval.v1",
  "dataset_sha256": "7b7a0fd60e0b0c23b40ac872d2e0df10277f6ad171c84fecee72f088870d1e86",
  "failures": [],
  "metrics": {
    "contract_valid_rate": 1.0,
    "deterministic_replay_rate": 1.0,
    "evidence_grounded_rate": 1.0,
    "field_exact_match_rate": 1.0,
    "mutation_guard_rate": 1.0,
    "risk_flag_recall": 1.0,
    "status_match_rate": 1.0
  },
  "model": "label_parser_v1",
  "passed": true,
  "prompt_version": "brief_mapping_prompt.v1",
  "provider": "deterministic_baseline",
  "schema_sha256": "60b429b6020ae59082c73ef07e98bef1c0eaa1ce034915a2f433b9ef9ee4398e",
  "split_counts": {
    "development": 24,
    "holdout": 12
  },
  "thresholds": {
    "contract_valid_rate": 1.0,
    "deterministic_replay_rate": 1.0,
    "evidence_grounded_rate": 1.0,
    "field_exact_match_rate": 1.0,
    "mutation_guard_rate": 1.0,
    "risk_flag_recall": 1.0,
    "status_match_rate": 1.0
  }
}