{
  "schema_version": "evalarc.evaluation.v2",
  "created_at": "2026-09-14T03:44:31.804346+00:00",
  "evalarc_version": "0.5.0",
  "task": {
    "id": "durable-kv",
    "version": "0.1.0",
    "domain": "coding",
    "split": "public-development"
  },
  "candidate_sha256": "378209f3f88e8e610eb07203e42dea1890d14e96408ed2e0593468e8f88ec0fe",
  "grader_sha256": "2283f5c82c24ac536c4467f5833333fc7098adb46839238fdc56eca017ef2039",
  "cases_sha256": "842a16a1e65700cde92ee5f5aaaa10d494a9fc9d71bd2d99fb68147b19aad63a",
  "runtime": {
    "backend": "docker",
    "image": "python:3.12-slim",
    "image_id": "sha256:78387bc3881b8273120a12ebe6c1ab22b018ccc2c9adf565ae1ac9b536e184ea",
    "command": [
      "{python}",
      "-I",
      "-B",
      "main.py",
      "{state}/store.db"
    ],
    "response_timeout_seconds": 10.0,
    "case_timeout_seconds": 60.0,
    "session_output_limit_bytes": 1048576,
    "python": "3.12.3",
    "platform": "Linux-6.17.0-1020-aws-x86_64-with-glibc2.39"
  },
  "seeds": [
    17
  ],
  "valid": true,
  "status": "passed",
  "score": 1.0,
  "resolved": true,
  "dimensions": {
    "basic": {
      "passed": 3,
      "total": 3,
      "assessed": 3,
      "weight": 0.25,
      "score": 1.0
    },
    "validation": {
      "passed": 2,
      "total": 2,
      "assessed": 2,
      "weight": 0.15,
      "score": 1.0
    },
    "transactions": {
      "passed": 2,
      "total": 2,
      "assessed": 2,
      "weight": 0.2,
      "score": 1.0
    },
    "compare_swap": {
      "passed": 2,
      "total": 2,
      "assessed": 2,
      "weight": 0.15,
      "score": 1.0
    },
    "persistence": {
      "passed": 3,
      "total": 3,
      "assessed": 3,
      "weight": 0.15,
      "score": 1.0
    },
    "crash_recovery": {
      "passed": 3,
      "total": 3,
      "assessed": 3,
      "weight": 0.1,
      "score": 1.0
    }
  },
  "cases": [
    {
      "seed": 17,
      "case_id": "read-write-delete",
      "dimension": "basic",
      "checks": {
        "basic": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 6,
      "duration_seconds": 0.486523,
      "transcript_sha256": "c809eed26dc56583f9385d7d4adca2d981d06a672dc1ccbc0ffc52aa228b86f7",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 200,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "json-types-and-overwrite",
      "dimension": "basic",
      "checks": {
        "basic": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 16,
      "duration_seconds": 0.553741,
      "transcript_sha256": "83f6377f4b57ac659e8162136107ca644158ee089c944892aa9817085e74bd60",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 4594,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "reject-and-continue",
      "dimension": "validation",
      "checks": {
        "validation": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 10,
      "duration_seconds": 0.490818,
      "transcript_sha256": "d4e0c26837f54e0af94d4909e3cab21d86dedca8c8842d0daae9e7471198c2a0",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 452,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "empty-and-unicode-keys",
      "dimension": "validation",
      "checks": {
        "validation": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 4,
      "duration_seconds": 0.51482,
      "transcript_sha256": "e8abe374fc308ce0744e96d2920495b96bda3b026cec9b86fa055023e1e4e620",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 232,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "commit-batch",
      "dimension": "transactions",
      "checks": {
        "transactions": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 4,
      "duration_seconds": 0.517392,
      "transcript_sha256": "ac21f2f6bcc47e3c807fa4ed72300af0f5ef39809ba17f93423e37a0e177e718",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 96,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "rollback-batch",
      "dimension": "transactions",
      "checks": {
        "transactions": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 7,
      "duration_seconds": 0.500656,
      "transcript_sha256": "1786c093ba29dcad562531a44cdbe5fddbed9d3f4632c1c6ddfe736baa240f35",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 374,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "cas-match-and-mismatch",
      "dimension": "compare_swap",
      "checks": {
        "compare_swap": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 7,
      "duration_seconds": 0.488908,
      "transcript_sha256": "ecd6148f6f387b4ef5351b877afd4cf27ea2a04c4253a34220fd78de5442d89f",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 278,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "cas-type-sensitivity",
      "dimension": "compare_swap",
      "checks": {
        "compare_swap": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 5,
      "duration_seconds": 0.493342,
      "transcript_sha256": "459a5b74588217d8abcf8e138eb559364a1d01d1f23e8c43ca0127ba28240258",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 160,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "restart-preserves-acknowledged-write",
      "dimension": "persistence",
      "checks": {
        "persistence": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 4,
      "duration_seconds": 1.418594,
      "transcript_sha256": "c97b82c67f26a1aa2fdc8ac57f50690dbbe13554d094059ffe6690a592df3a55",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 13,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        },
        {
          "exit_code": 0,
          "output_bytes": 116,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        },
        {
          "exit_code": 0,
          "output_bytes": 29,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "restart-preserves-transaction",
      "dimension": "persistence",
      "checks": {
        "persistence": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 3,
      "duration_seconds": 0.899825,
      "transcript_sha256": "2d1f704df309d49f8e6e89e674581af2cf81aa22fdde633058e2f2d7b8c8a430",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 13,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        },
        {
          "exit_code": 0,
          "output_bytes": 206,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "sigkill-after-acknowledgement",
      "dimension": "crash_recovery",
      "checks": {
        "crash_recovery": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 2,
      "duration_seconds": 0.999686,
      "transcript_sha256": "544c6be916371ed5a0e901394c5e293733ca84e0ad20079a952f9c4b2821a728",
      "error": null,
      "processes": [
        {
          "exit_code": 137,
          "output_bytes": 13,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        },
        {
          "exit_code": 0,
          "output_bytes": 103,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "sigkill-after-atomic-batch",
      "dimension": "crash_recovery",
      "checks": {
        "crash_recovery": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 3,
      "duration_seconds": 0.949866,
      "transcript_sha256": "2d1f704df309d49f8e6e89e674581af2cf81aa22fdde633058e2f2d7b8c8a430",
      "error": null,
      "processes": [
        {
          "exit_code": 137,
          "output_bytes": 13,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        },
        {
          "exit_code": 0,
          "output_bytes": 206,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "restart-preserves-cas",
      "dimension": "persistence",
      "checks": {
        "persistence": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 3,
      "duration_seconds": 0.977125,
      "transcript_sha256": "149c04fd1366e77603e631349740ae38bdff40aa69f6eb4c738979eb13bf3f49",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 43,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        },
        {
          "exit_code": 0,
          "output_bytes": 42,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "sigkill-after-delete",
      "dimension": "crash_recovery",
      "checks": {
        "crash_recovery": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 3,
      "duration_seconds": 1.400092,
      "transcript_sha256": "b3dba7f28e6629bb22f49b0439e0f74580ca3263dd98e16061ac9a8f680b5df7",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 13,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        },
        {
          "exit_code": 137,
          "output_bytes": 13,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        },
        {
          "exit_code": 0,
          "output_bytes": 29,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    },
    {
      "seed": 17,
      "case_id": "seeded-state-machine",
      "dimension": "basic",
      "checks": {
        "basic": true
      },
      "passed": true,
      "status": "passed",
      "checks_completed": 52,
      "duration_seconds": 0.706039,
      "transcript_sha256": "2a7e5ad4bedce67faf4d53f289c3a1a7304345a0167b287418fdf7dd411030f8",
      "error": null,
      "processes": [
        {
          "exit_code": 0,
          "output_bytes": 1250,
          "stderr_tail": "",
          "stderr_tail_limit_bytes": 2048
        }
      ]
    }
  ],
  "evaluation_seconds": 11.418674,
  "agent_cost_usd": null,
  "agent_tokens": null
}
