{
  "schema_version": 1,
  "controlled_benchmark": {
    "kind": "controlled_mutations",
    "scenarios": 15,
    "fixture_tests": 24,
    "failure_revealing_test_instances_selected": 29,
    "failure_revealing_test_instances_total": 29,
    "failure_recall": 1.0,
    "test_reduction": 0.6917,
    "source": "evaluation/results.json"
  },
  "real_prs": [
    {
      "repository": "psf/requests",
      "pr_url": "https://github.com/psf/requests/pull/6644",
      "pr_number": 6644,
      "base_commit": "382fc2c0c6c0ef0874bc65bc1175f97c073e5086",
      "base_ref": "main",
      "analyzed_commit": "60389df6d69ce833164696dcf36cbb43336d3426",
      "functions_indexed": null,
      "call_edges_indexed": null,
      "index_counts_note": "The committed Requests report records the selected graph paths but not total index counts.",
      "collected_full_suite_cases": null,
      "selected_targets": 1,
      "expanded_selected_cases": 1,
      "selected_pass": 1,
      "selected_fail": 0,
      "selected_skip": 0,
      "selection_reduction": null,
      "selection_reduction_note": "No reliable full-suite collection count was recorded.",
      "full_suite_status": "not_run",
      "full_suite_reason": "A full-suite comparison was not completed.",
      "failure_recall": null,
      "failure_recall_reason": "No valid complete full suite with a genuine failing test is available.",
      "selected_test": "tests/test_adapters.py::test_request_url_trims_leading_path_separators"
    },
    {
      "repository": "httpie/cli",
      "pr_url": "https://github.com/httpie/cli/pull/1327",
      "pr_number": 1327,
      "base_commit": "85ba9ad8eaa718d7f9dbcb7129168d6a877f3d30",
      "base_ref": "master",
      "analyzed_commit": "17ec3be6512919fafae4300083e03580d4a00ff2",
      "functions_indexed": 956,
      "call_edges_indexed": 876,
      "collected_full_suite_cases": 1012,
      "selected_targets": 18,
      "expanded_selected_cases": 43,
      "selected_pass": 34,
      "selected_fail": 0,
      "selected_skip": 9,
      "selection_reduction": 0.9575,
      "selection_reduction_note": "1 - 43 / 1012; selected cases are not a full-suite failure-recall measurement.",
      "full_suite_status": "environment_blocked",
      "full_suite_reason": "The unsandboxed run showed failures requiring dependency/environment review; no valid complete baseline was established.",
      "failure_recall": null,
      "failure_recall_reason": "Without a valid complete full suite, failure recall is not computable.",
      "remote_skip_reason": "Nine cases requiring the remote pie.dev service were skipped.",
      "selected_test_outcomes": "34 passed, 9 skipped, 0 failed"
    }
  ]
}