{
  "scope": "PARTIAL263 actual final selected-context metrics and native outcomes; not a complete500 or leaderboard result.",
  "cases": 263,
  "official_valid_cases": 263,
  "macro": {
    "file": {
      "recall": 0.9019920540958164,
      "precision": 0.21167070760819762,
      "f1": 0.31096742476310446
    },
    "block": {
      "recall": 0.8676457530388805,
      "precision": 0.1507786338612076,
      "f1": 0.23776140744723157
    },
    "line": {
      "recall": 0.8030867099462999,
      "precision": 0.22836569260100936,
      "f1": 0.3264669344187032
    }
  },
  "resolved": 216,
  "unresolved": 47,
  "partial_native_pass_at_1": 0.8212927756653993,
  "modeled_search_plus_repair_usage_usd": 161.66804502,
  "modeled_usage_per_case_usd": 0.614707395513308,
  "metered_sessions": 2868,
  "failed_and_unresolved_cases_retained": true,
  "per_case_F1_then_macro_mean": true,
  "retrospective_selection_cases": 3,
  "arbitrary_shell_source_attribution": "partial",
  "reference_material_supplied_to_model": false,
  "evaluator_commit": "1436c28a8eb95496da4ea69ad458b9f8a8eb7d61",
  "input_sha256": "9b7475f29f0aae4f0c2ff8864cf2fa523e10df646a32831423a816f12d8a11d6",
  "raw_index_verification_sha256": "76c0d15cc9a6e581809e4c4c1919d17eba806ab83f17426738775fd0bbe334a8",
  "full500_official_results_or_submission_ready": false,
  "model_calls": 0,
  "native_tests_rerun": 0,
  "financial_mutations": 0,
  "official_metrics_sha256": "a1e723a6eabfb0e76bf681aecf581e2a555f4464726e302cacc4c6d08c7e5032",
  "same263_search_reference_macro": {
    "file": {
      "recall": 0.9019920540958164,
      "precision": 0.21186624179325647,
      "f1": 0.31119468397798605
    },
    "block": {
      "recall": 0.8654161603198216,
      "precision": 0.15140132443502255,
      "f1": 0.2384536972198083
    },
    "line": {
      "recall": 0.7983491871601313,
      "precision": 0.23033743161310508,
      "f1": 0.32772387741251663
    }
  },
  "same263_reference_is_not_a_strict_causal_ablation": true,
  "same_ID_descriptive_delta_audit": {
    "file": {
      "recall_higher": 0,
      "recall_equal": 263,
      "recall_lower": 0,
      "F1_higher": 0,
      "F1_equal": 256,
      "F1_lower": 7
    },
    "block": {
      "recall_higher": 6,
      "recall_equal": 257,
      "recall_lower": 0,
      "F1_higher": 4,
      "F1_equal": 226,
      "F1_lower": 33
    },
    "line": {
      "recall_higher": 16,
      "recall_equal": 247,
      "recall_lower": 0,
      "F1_higher": 7,
      "F1_equal": 200,
      "F1_lower": 56
    }
  },
  "source_counts": {
    "SWE-Bench-Verified": 174,
    "SWE-Bench-Pro": 54,
    "SWE-PolyBench": 32,
    "Multi-SWE-Bench": 3
  },
  "same263_search_reference_metrics_sha256": "f423199b8357f2f7f01c72dc66d7b4693c600c934b927079a06eccc62a5dd7dc"
}
