{
  "completeness": "completed",
  "created_at": "2026-11-02T01:44:18.162516Z",
  "evidence_kind": "measured",
  "failure": null,
  "identities": {
    "concurrency": {
      "requests": 1,
      "workers": 1
    },
    "context": {
      "configured_tokens": 262144,
      "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": 634958655488,
      "harness_assets": [],
      "id": "[PRIMARY_NODE]",
      "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[REDACTED_PATH]sets/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": "[QUALIFICATION_FINAL_MODEL_ALIAS]"
    },
    "runtime": {
      "reason": "not exposed by router preflight",
      "status": "unavailable"
    },
    "served_model": {
      "configured_context": 262144,
      "id": "[QUALIFICATION_FINAL_MODEL_ALIAS]"
    },
    "topology": {
      "kind": "co-resident-benchmark-client",
      "worker_id": "[PRIMARY_NODE]"
    }
  },
  "promotion": {
    "authorized": false,
    "message": "Benchmark evidence does not authorize model promotion; promotion is a separate human decision."
  },
  "run": {
    "ownership_id": "[QUALIFICATION_FINAL_CAMPAIGN]",
    "profile": "scout",
    "run_id": "[QUALIFICATION_FINAL_SWE_RUN]",
    "spec_sha256": "76775258ce6e210fb657da389cbb83b28b582b0884a1ad1ff297b072b2e27560",
    "suite": "swe"
  },
  "schema": "anvil-serving.benchmark-evidence/v1",
  "stages": [
    {
      "evidence": [
        {
          "bytes": 10609,
          "path": "evidence/0-assets.json",
          "sha256": "705fc4c87244425518b079d4d8033489b02afc9f3748a3d0799fdb4c40516f2f"
        }
      ],
      "name": "asset_preparation",
      "sequence": 0,
      "status": "completed"
    },
    {
      "evidence": [
        {
          "bytes": 2114,
          "path": "evidence/0-preflight.json",
          "sha256": "30b7f7e3367e8d21cec5020c631f4432ad9b98643be8c540c667363c83614da1"
        }
      ],
      "name": "preflight",
      "sequence": 1,
      "status": "completed"
    },
    {
      "evidence": [
        {
          "bytes": 10044,
          "path": "evidence/0-swe-canonical-retention.json",
          "sha256": "0508e8e8fea9732d74d6a8de0948baf8c6d976e5ea2c72ea024399cc000b39d2"
        }
      ],
      "name": "swe_canonical_retention",
      "sequence": 2,
      "status": "completed"
    },
    {
      "evidence": [
        {
          "bytes": 182926,
          "path": "evidence/2-swe.json",
          "sha256": "f8809f0deac24d3f4e4d0b11260d7c9dc3d70ee42f8196ed9508f8ae2ec7d894"
        }
      ],
      "name": "swe",
      "sequence": 3,
      "status": "completed"
    }
  ],
  "summary": {
    "attempted": 5,
    "graded": 5,
    "resolve_rate": 0.8,
    "resolved": 4
  }
}