{
  "budget": {
    "fixture_timeout_seconds": 1.0,
    "protocol_output_limit_bytes": 4096
  },
  "created_at": "2026-09-11T02:09:07.074081+00:00",
  "environment": {
    "machine": "arm64",
    "os": "Darwin",
    "python": "3.14.6"
  },
  "evaluator_sha256": "cacc6c777fb1dd71afa584234c944213118d9d6ceb54546fff84d7549cf11dca",
  "expected_answers_sha256": "e76fc357ff9474058edd929106462538b2791f827b169d1bafa592f1a902bf7b",
  "fixtures": [
    {
      "candidate_sha256": "dc254d8f78c860a415a99c598bec0e34d3f91546ef1de07b33c588ecf27f0126",
      "evidence": {
        "py": {
          "path": "correct.py",
          "sha256": "dc254d8f78c860a415a99c598bec0e34d3f91546ef1de07b33c588ecf27f0126"
        },
        "stderr": {
          "path": "correct.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "correct.stdout",
          "sha256": "bc7f3d403278867b0099019a75e86cc61d47859441887f49074f226c77d9d5ac"
        }
      },
      "expectation_met": true,
      "expected_reason": "accepted",
      "expected_score": 1.0,
      "fixture": "correct",
      "reason": "accepted",
      "runner": {
        "elapsed_seconds": 0.019206,
        "returncode": 0,
        "timed_out": false
      },
      "score": 1.0
    },
    {
      "candidate_sha256": "66b405e49553b4a12166830f5e3dcf4d7dd3687cb2627a29ebd26bffca9f3bac",
      "evidence": {
        "py": {
          "path": "wrong_answers.py",
          "sha256": "66b405e49553b4a12166830f5e3dcf4d7dd3687cb2627a29ebd26bffca9f3bac"
        },
        "stderr": {
          "path": "wrong_answers.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "wrong_answers.stdout",
          "sha256": "57d9f3c026d50cf3cd33a4427a4665f87988ffbcf3043bcb0b0dab63b1a30244"
        }
      },
      "expectation_met": true,
      "expected_reason": "incorrect",
      "expected_score": 0.16666666666666666,
      "fixture": "wrong_answers",
      "reason": "incorrect",
      "runner": {
        "elapsed_seconds": 0.012941,
        "returncode": 0,
        "timed_out": false
      },
      "score": 0.16666666666666666
    },
    {
      "candidate_sha256": "be625e7498ab418d06d6fc5bed0b4797951e2a0d32f89459ae152d8453bcdef6",
      "evidence": {
        "py": {
          "path": "fake_success_log.py",
          "sha256": "be625e7498ab418d06d6fc5bed0b4797951e2a0d32f89459ae152d8453bcdef6"
        },
        "stderr": {
          "path": "fake_success_log.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "fake_success_log.stdout",
          "sha256": "8135e7ede7bbe18ad15473036ad15cd278286f106f63251d5eebd31881cc309c"
        }
      },
      "expectation_met": true,
      "expected_reason": "invalid_json",
      "expected_score": null,
      "fixture": "fake_success_log",
      "reason": "invalid_json",
      "runner": {
        "elapsed_seconds": 0.013805,
        "returncode": 0,
        "timed_out": false
      },
      "score": null
    },
    {
      "candidate_sha256": "4ccc90b7f8624a0dadab22170f1d2106eefdc00563d728ffca7eb0900c8693d5",
      "evidence": {
        "py": {
          "path": "self_reported_score.py",
          "sha256": "4ccc90b7f8624a0dadab22170f1d2106eefdc00563d728ffca7eb0900c8693d5"
        },
        "stderr": {
          "path": "self_reported_score.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "self_reported_score.stdout",
          "sha256": "c9ea5aeb13abbd27c05e5453bfb18b00fd229f1312dd6edb841ec360b049e345"
        }
      },
      "expectation_met": true,
      "expected_reason": "invalid_schema",
      "expected_score": null,
      "fixture": "self_reported_score",
      "reason": "invalid_schema",
      "runner": {
        "elapsed_seconds": 0.012707,
        "returncode": 0,
        "timed_out": false
      },
      "score": null
    },
    {
      "candidate_sha256": "d74ff0ee8da3b9806b18c877dbf29bbde50b5bd8e4dad7a3a725000feb82e8f1",
      "evidence": {
        "py": {
          "path": "missing_output.py",
          "sha256": "d74ff0ee8da3b9806b18c877dbf29bbde50b5bd8e4dad7a3a725000feb82e8f1"
        },
        "stderr": {
          "path": "missing_output.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "missing_output.stdout",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        }
      },
      "expectation_met": true,
      "expected_reason": "missing_output",
      "expected_score": null,
      "fixture": "missing_output",
      "reason": "missing_output",
      "runner": {
        "elapsed_seconds": 0.011995,
        "returncode": 0,
        "timed_out": false
      },
      "score": null
    },
    {
      "candidate_sha256": "dfb9848f58061d737798c1c98bf6a050ab9ed5b892e398569448149e1c7e188e",
      "evidence": {
        "py": {
          "path": "malformed_json.py",
          "sha256": "dfb9848f58061d737798c1c98bf6a050ab9ed5b892e398569448149e1c7e188e"
        },
        "stderr": {
          "path": "malformed_json.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "malformed_json.stdout",
          "sha256": "a6fb08fda1acb957b6116bd37811a1fe41a01611c0631edbf786d6889a27a55c"
        }
      },
      "expectation_met": true,
      "expected_reason": "invalid_json",
      "expected_score": null,
      "fixture": "malformed_json",
      "reason": "invalid_json",
      "runner": {
        "elapsed_seconds": 0.012332,
        "returncode": 0,
        "timed_out": false
      },
      "score": null
    },
    {
      "candidate_sha256": "f037acc45b2e92941d3050c6c7abc14d672b4eddce0af7c1525dd43aaab36cd3",
      "evidence": {
        "py": {
          "path": "non_finite_value.py",
          "sha256": "f037acc45b2e92941d3050c6c7abc14d672b4eddce0af7c1525dd43aaab36cd3"
        },
        "stderr": {
          "path": "non_finite_value.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "non_finite_value.stdout",
          "sha256": "986479c235662e0491b1b885bc2a216b135204ce81495a2f52749068481a5f30"
        }
      },
      "expectation_met": true,
      "expected_reason": "invalid_json",
      "expected_score": null,
      "fixture": "non_finite_value",
      "reason": "invalid_json",
      "runner": {
        "elapsed_seconds": 0.012225,
        "returncode": 0,
        "timed_out": false
      },
      "score": null
    },
    {
      "candidate_sha256": "ccdcb6622cdd153a49b57b6b952faf8f7ac25b41bc88a4bc696e8d0903f13251",
      "evidence": {
        "py": {
          "path": "boolean_answer.py",
          "sha256": "ccdcb6622cdd153a49b57b6b952faf8f7ac25b41bc88a4bc696e8d0903f13251"
        },
        "stderr": {
          "path": "boolean_answer.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "boolean_answer.stdout",
          "sha256": "3be80d11c39073eeaa3df169561685825030dc8a333a89e22b3f8ec58172bcce"
        }
      },
      "expectation_met": true,
      "expected_reason": "invalid_schema",
      "expected_score": null,
      "fixture": "boolean_answer",
      "reason": "invalid_schema",
      "runner": {
        "elapsed_seconds": 0.012555,
        "returncode": 0,
        "timed_out": false
      },
      "score": null
    },
    {
      "candidate_sha256": "4b695d16b33fdded5f9ba7969c542e19a5e40d9fa1b1a8511817794493b94d59",
      "evidence": {
        "py": {
          "path": "partial_results.py",
          "sha256": "4b695d16b33fdded5f9ba7969c542e19a5e40d9fa1b1a8511817794493b94d59"
        },
        "stderr": {
          "path": "partial_results.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "partial_results.stdout",
          "sha256": "fb62fdb4941adf361428525c8fa0293bc438fea375d1b05a7ea727267b74edd4"
        }
      },
      "expectation_met": true,
      "expected_reason": "invalid_schema",
      "expected_score": null,
      "fixture": "partial_results",
      "reason": "invalid_schema",
      "runner": {
        "elapsed_seconds": 0.012855,
        "returncode": 0,
        "timed_out": false
      },
      "score": null
    },
    {
      "candidate_sha256": "1fc8379dbe8918a479fad1e9442973b29caea87de88e9ea54a1045f7f18eb31c",
      "evidence": {
        "py": {
          "path": "duplicate_key.py",
          "sha256": "1fc8379dbe8918a479fad1e9442973b29caea87de88e9ea54a1045f7f18eb31c"
        },
        "stderr": {
          "path": "duplicate_key.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "duplicate_key.stdout",
          "sha256": "26cf77e984bcd03039dc3c77796194829c127bc0e97f96a8f13fbe4ff8f07aea"
        }
      },
      "expectation_met": true,
      "expected_reason": "invalid_json",
      "expected_score": null,
      "fixture": "duplicate_key",
      "reason": "invalid_json",
      "runner": {
        "elapsed_seconds": 0.013053,
        "returncode": 0,
        "timed_out": false
      },
      "score": null
    },
    {
      "candidate_sha256": "834161bcb66c032bf80b9b1b885314b8745a463bc7db6f1102cd9c39c8a57c20",
      "evidence": {
        "py": {
          "path": "oversized_output.py",
          "sha256": "834161bcb66c032bf80b9b1b885314b8745a463bc7db6f1102cd9c39c8a57c20"
        },
        "stderr": {
          "path": "oversized_output.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "oversized_output.stdout",
          "sha256": "e86951fc857c11311efb0aac676f59a661cc2f89c5da367797d1aef9312d72a3"
        }
      },
      "expectation_met": true,
      "expected_reason": "output_too_large",
      "expected_score": null,
      "fixture": "oversized_output",
      "reason": "output_too_large",
      "runner": {
        "elapsed_seconds": 0.012345,
        "returncode": 0,
        "timed_out": false
      },
      "score": null
    },
    {
      "candidate_sha256": "68c12dffa9f331384750c8d4dfd3283e4e18fd386efcec787dd073dabaf5a083",
      "evidence": {
        "py": {
          "path": "nonzero_exit.py",
          "sha256": "68c12dffa9f331384750c8d4dfd3283e4e18fd386efcec787dd073dabaf5a083"
        },
        "stderr": {
          "path": "nonzero_exit.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "nonzero_exit.stdout",
          "sha256": "bc7f3d403278867b0099019a75e86cc61d47859441887f49074f226c77d9d5ac"
        }
      },
      "expectation_met": true,
      "expected_reason": "nonzero_exit",
      "expected_score": null,
      "fixture": "nonzero_exit",
      "reason": "nonzero_exit",
      "runner": {
        "elapsed_seconds": 0.01693,
        "returncode": 1,
        "timed_out": false
      },
      "score": null
    },
    {
      "candidate_sha256": "2e19ecdd6381aa3b76d4f9ba687f84337a6709fd0020dfe484c9db9639d56611",
      "evidence": {
        "py": {
          "path": "timeout.py",
          "sha256": "2e19ecdd6381aa3b76d4f9ba687f84337a6709fd0020dfe484c9db9639d56611"
        },
        "stderr": {
          "path": "timeout.stderr",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        },
        "stdout": {
          "path": "timeout.stdout",
          "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        }
      },
      "expectation_met": true,
      "expected_reason": "timeout",
      "expected_score": null,
      "fixture": "timeout",
      "reason": "timeout",
      "runner": {
        "elapsed_seconds": 1.002896,
        "returncode": null,
        "timed_out": true
      },
      "score": null
    }
  ],
  "model_id": null,
  "schema": "meshia.evaluator-smoke-test.v1",
  "scope": "Synthetic protocol fixtures only; no model, search, sandbox, or held-out claim",
  "seed": null,
  "summary": {
    "accepted_candidates": 1,
    "expectations_met": 13,
    "fixtures": 13
  },
  "task_manifest_sha256": "ebf689bca8b884b68330d521374a880379a052283e9972a79a967c7ca12ed259"
}
