{
  "container_limits": {
    "mem_limit": 8589934592,
    "memswap_limit": 8589934592,
    "nano_cpus": 4000000000,
    "network_mode": "none",
    "pids_limit": 512
  },
  "created_at": "2026-10-13T13:00:16.592901Z",
  "dataset": "princeton-nlp/SWE-bench_Verified",
  "dataset_snapshot": {
    "files": {
      "test-00000-of-00001.parquet": "a45b1fe4e2f0c8390b2b2938ac83e92ed5979000856808f3679c07812e9e6dcd"
    },
    "revision": "c104f840cc67f8b6eec6f759ebc8b2693d585d4a",
    "root": "<redacted-local-dataset-root>"
  },
  "endpoint": {
    "base_url": "<redacted-local-endpoint>",
    "model": "coder390-int4w4a16-tp1-c1-131k-nospec"
  },
  "failure": null,
  "harnesses": {
    "agent": {
      "name": "mini-swe-agent",
      "revision": "a83fcae82d2a08f0ee0c688f9d137b3566c097f8"
    },
    "grader": {
      "name": "swe-bench",
      "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
    },
    "grader_containment": {
      "adapter_sha256": "23c56b27d62b79c39aca6dcfdd4c504030e241e3a6941620cdc6e947b9035a7b",
      "receipt": "<redacted-local-containment-receipt>",
      "source_hashes": {
        "swebench/harness/docker_build.py": "5278842b60a7d38256f95f93c915dc84de2b8b4f286e9baae1b19280f768e484",
        "swebench/harness/run_evaluation.py": "6959f0b4e4eaf979771f529b88e3e9df1daa7fe86bc4291feec2e7d320bf7f2e"
      }
    },
    "python_environment": {
      "architecture": "x86_64",
      "platform": "linux",
      "python": {
        "implementation": "CPython",
        "version": "3.14.4"
      },
      "resolved_packages_sha256": "809336a2a74041fa07adad60eaca2208acd936f3728d2368d22f98657576a37a",
      "schema": "anvil-serving.swe-python-environment/v1"
    }
  },
  "image_observations": [],
  "instances": [
    {
      "duration_s": null,
      "exit_status": "Submitted",
      "failure_class": null,
      "grader": {
        "completed": true,
        "name": "swe-bench",
        "report_sha256": "1c9ba6c446640cf2087cba5c90463f0bc304cec594567c0990df4d1684cc3451",
        "resolved": true,
        "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
      },
      "instance_id": "sphinx-doc__sphinx-9658",
      "prediction_sha256": "d4abf13102719af9ca717e9cf62ab66f36adc557b42105629c58bec776f2fe9c",
      "prompt_identity": {
        "dataset": "princeton-nlp/SWE-bench_Verified",
        "split": "test"
      },
      "request_id_count": 31,
      "request_ids": "<redacted-request-ids>",
      "tokens": {
        "completion_tokens": null,
        "prompt_tokens": null,
        "total_tokens": null
      },
      "trajectory": {
        "path": "<redacted-local-trajectory>",
        "sha256": "8ae62fd60e20b2cf19eee0ffbaeccaeeca28c671375a6bd731c6fab7b5c2a978"
      }
    },
    {
      "duration_s": null,
      "exit_status": "Submitted",
      "failure_class": null,
      "grader": {
        "completed": true,
        "name": "swe-bench",
        "report_sha256": "1c9ba6c446640cf2087cba5c90463f0bc304cec594567c0990df4d1684cc3451",
        "resolved": true,
        "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
      },
      "instance_id": "sympy__sympy-12096",
      "prediction_sha256": "7ddb6564f132362278bb2d8a1ed3ec61f90da22765f9b7037428ac7fea908fc7",
      "prompt_identity": {
        "dataset": "princeton-nlp/SWE-bench_Verified",
        "split": "test"
      },
      "request_id_count": 26,
      "request_ids": "<redacted-request-ids>",
      "tokens": {
        "completion_tokens": null,
        "prompt_tokens": null,
        "total_tokens": null
      },
      "trajectory": {
        "path": "<redacted-local-trajectory>",
        "sha256": "bbbecb17b50d7b87649219dc2edefe3d5a8874fa8ca75aaf6e37c2a1877f674e"
      }
    },
    {
      "duration_s": null,
      "exit_status": "Submitted",
      "failure_class": null,
      "grader": {
        "completed": true,
        "name": "swe-bench",
        "report_sha256": "1c9ba6c446640cf2087cba5c90463f0bc304cec594567c0990df4d1684cc3451",
        "resolved": false,
        "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
      },
      "instance_id": "django__django-13512",
      "prediction_sha256": "2aa21f716626d5ca4a7fec4f4f32373265dd7700cccaafe5a9197f5cc3da4724",
      "prompt_identity": {
        "dataset": "princeton-nlp/SWE-bench_Verified",
        "split": "test"
      },
      "request_id_count": 16,
      "request_ids": "<redacted-request-ids>",
      "tokens": {
        "completion_tokens": null,
        "prompt_tokens": null,
        "total_tokens": null
      },
      "trajectory": {
        "path": "<redacted-local-trajectory>",
        "sha256": "c3edb7ffefab6457fdc0f5d5833e575e0ed9492a56c8effe8807d5ee27b29be9"
      }
    },
    {
      "duration_s": null,
      "exit_status": "Submitted",
      "failure_class": null,
      "grader": {
        "completed": true,
        "name": "swe-bench",
        "report_sha256": "1c9ba6c446640cf2087cba5c90463f0bc304cec594567c0990df4d1684cc3451",
        "resolved": true,
        "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
      },
      "instance_id": "pydata__xarray-4356",
      "prediction_sha256": "08c69b410a4545b0800549b99097b945f6e6aff90c10dd65688df90c0242de92",
      "prompt_identity": {
        "dataset": "princeton-nlp/SWE-bench_Verified",
        "split": "test"
      },
      "request_id_count": 27,
      "request_ids": "<redacted-request-ids>",
      "tokens": {
        "completion_tokens": null,
        "prompt_tokens": null,
        "total_tokens": null
      },
      "trajectory": {
        "path": "<redacted-local-trajectory>",
        "sha256": "f16dbea59fc1b716e04ff17183d2ed9c0e67f75a9e273fdcd137545b07347362"
      }
    },
    {
      "duration_s": null,
      "exit_status": "Submitted",
      "failure_class": null,
      "grader": {
        "completed": true,
        "name": "swe-bench",
        "report_sha256": "1c9ba6c446640cf2087cba5c90463f0bc304cec594567c0990df4d1684cc3451",
        "resolved": false,
        "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
      },
      "instance_id": "pylint-dev__pylint-8898",
      "prediction_sha256": "48e1fc442cc60ae37e23993a1dc12c9125c45ae289ef23d97718884d14725260",
      "prompt_identity": {
        "dataset": "princeton-nlp/SWE-bench_Verified",
        "split": "test"
      },
      "request_id_count": 25,
      "request_ids": "<redacted-request-ids>",
      "tokens": {
        "completion_tokens": null,
        "prompt_tokens": null,
        "total_tokens": null
      },
      "trajectory": {
        "path": "<redacted-local-trajectory>",
        "sha256": "978e55482d936d16dac6396a6903d82abf0c9810ab87f9222967b7dec310c4bf"
      }
    }
  ],
  "official_grader_complete": true,
  "ownership_id": "qualification-20261013",
  "paired_image_ids": null,
  "plan_sha256": "0fec7a0290edeb4cb2a8fb6b0b616189a966750f55c2d2fa8257eab2715a7668",
  "profile": "scout",
  "profile_sha256": "fce0e6e1e7497585bdfc6f76507d3baaff99a6b4f174d841d268de20c68de7f6",
  "promotion": {
    "authorized": false,
    "message": "Benchmark evidence does not authorize model promotion."
  },
  "request_controls": {
    "reasoning_effort": "medium",
    "sampling": {
      "temperature": {
        "effective_request": 0.6,
        "requested": 0.6,
        "sent": true
      },
      "top_p": {
        "effective_request": 0.95,
        "requested": 0.95,
        "sent": true
      }
    },
    "thinking_mode": "default"
  },
  "run_id": "qualification-20261013-coder390-tp1-medium-swe5",
  "schema": "anvil-serving.swe-run/v1",
  "selection": {
    "instance_ids": [
      "sphinx-doc__sphinx-9658",
      "sympy__sympy-12096",
      "django__django-13512",
      "pydata__xarray-4356",
      "pylint-dev__pylint-8898"
    ],
    "kind": "explicit_instance_ids",
    "sha256": "622934396fb97d950f803dfbb0791f6a398a5a6fe0fd94cc27b329f1a953cac4"
  },
  "split": "test",
  "stage_count": 2,
  "stages": "<redacted-runtime-stage-transcripts>",
  "state": "completed",
  "summary": {
    "attempted": 5,
    "graded": 5,
    "resolve_rate": 0.6,
    "resolved": 3
  },
  "task_container_network": "none"
}