{
  "completeness": "failed",
  "created_at": "2026-10-17T03:10:40.529496Z",
  "evidence_kind": "measured",
  "failure": {
    "class": "model_behavior",
    "code": "model_failure",
    "message": "benchmark suite did not complete"
  },
  "identities": {
    "concurrency": {
      "requests": 1,
      "workers": 1
    },
    "context": {
      "configured_tokens": null,
      "output_headroom_tokens": "not-applicable",
      "profile_buckets": "not-applicable",
      "selected_buckets": "not-applicable"
    },
    "dataset": {
      "name": "SWE-bench_Verified",
      "split": "test"
    },
    "hardware": {
      "architecture": "x86_64",
      "container_capable": true,
      "free_disk_bytes": 109701644288,
      "harness_assets": [],
      "owned_output_writable": true,
      "platform": "linux"
    },
    "harnesses": {
      "mini-swe-agent": {
        "revision": "a83fcae82d2a08f0ee0c688f9d137b3566c097f8",
        "source": "https://github.com/SWE-agent/mini-swe-agent"
      },
      "swe-bench": {
        "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9",
        "source": "https://github.com/SWE-bench/SWE-bench"
      },
      "swe-bench-verified": {
        "revision": "c104f840cc67f8b6eec6f759ebc8b2693d585d4a",
        "source": "https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified"
      },
      "worker-base": {
        "image": "python:3.12-slim@sha256:57cd7c3a7a273101a6485ba99423ee568157882804b1124b4dd04266317710de"
      }
    },
    "image": {
      "image": "python:3.12-slim@sha256:57cd7c3a7a273101a6485ba99423ee568157882804b1124b4dd04266317710de",
      "kind": "image",
      "reused": true
    },
    "model": {
      "alias": "llm.primary"
    },
    "runtime": {
      "reason": "not exposed by router preflight",
      "status": "unavailable"
    },
    "served_model": {
      "configured_context": null,
      "id": "llm.primary"
    },
    "topology": {
      "kind": "co-resident-benchmark-client"
    }
  },
  "promotion": {
    "authorized": false,
    "message": "Benchmark evidence does not authorize model promotion; promotion is a separate human decision."
  },
  "run": {
    "ownership_id": "glm-natural-baseline-20261016",
    "profile": "scout",
    "run_id": "glm-natural-baseline-20261016-cached-swe-r2",
    "spec_sha256": "119054039eb08071fefe15721abb5a8e0c52ff82d1efbffe06afb5b2a3405ed1",
    "suite": "swe"
  },
  "schema": "anvil-serving.benchmark-evidence/v1",
  "stages": [
    {
      "evidence": [
        {
          "bytes": 10908,
          "path": "redacted://campaign-stage/asset_preparation",
          "sha256": "be5da794984c6deea46dfc00218a484e96abec46a260a05be0ff25ab459f182d"
        }
      ],
      "name": "asset_preparation",
      "sequence": 0,
      "status": "completed"
    },
    {
      "evidence": [
        {
          "bytes": 2114,
          "path": "redacted://campaign-stage/preflight",
          "sha256": "c89cbcc5196db1cfa1ae2ecacf28a8717b98dbfae79c85e7465f212463c3edba"
        }
      ],
      "name": "preflight",
      "sequence": 1,
      "status": "completed"
    },
    {
      "evidence": [
        {
          "bytes": 42202,
          "path": "redacted://campaign-stage/swe",
          "sha256": "f629daff8a454f754d07c2c726eb5553ba0735c457e631f0429ca1d3ce7404f4"
        }
      ],
      "name": "swe",
      "sequence": 2,
      "status": "failed"
    }
  ],
  "summary": {
    "attempted": true,
    "completed": false
  }
}