{
  "created_at": "2026-10-05T08:59:33.623206Z",
  "failure": null,
  "partial": false,
  "provenance": {
    "endpoint": {
      "base_url": "REDACTED_LOOPBACK_ENDPOINT",
      "model": "candidate-local-tier-r1"
    },
    "finished_at": "2026-10-05T08:59:33.623120Z",
    "started_at": "2026-10-05T08:48:18.329754Z",
    "submitted_at": "2026-10-05T08:35:19.637922+00:00",
    "worker": {
      "id": "local-benchmark"
    }
  },
  "results": {
    "evidence": {
      "completeness": "completed",
      "created_at": "2026-10-05T08:59:33.610051Z",
      "evidence_kind": "measured",
      "failure": null,
      "identities": {
        "concurrency": {
          "requests": 1,
          "workers": 1
        },
        "context": {
          "configured_tokens": 262144
        },
        "dataset": {
          "name": "SWE-bench_Verified",
          "split": "test"
        },
        "hardware": {
          "gpu": "dual-96GiB-class-gpus",
          "vram_mib_per_gpu": 97887
        },
        "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": {
          "repository": "local-inference-lab/Qwen3.8-Flash-Next-NVFP4",
          "revision": "6909a5bed089a48fa07e956d3915af2537de9368",
          "served_name": "candidate-local-tier-r1"
        },
        "runtime": {
          "engine_revision": "00a33e23142097f99fef95b1ecab6da4ea271e2e",
          "image_id": "sha256:6008f020c23065bef71390194f968af9f5ebbedf57807b1659f876632e4a1067"
        },
        "served_model": {
          "configured_context": 262144,
          "id": "qwen38-step5500-tp2-nospec-262k-r1"
        },
        "topology": {
          "kind": "co-resident-benchmark-client",
          "worker_id": "REDACTED_RUN_OR_REQUEST_ID"
        }
      },
      "promotion": {
        "authorized": false,
        "message": "REDACTED_BENCHMARK_CONTENT"
      },
      "run": {
        "ownership_id": "REDACTED_RUN_OR_REQUEST_ID",
        "profile": "scout",
        "run_id": "REDACTED_RUN_OR_REQUEST_ID",
        "spec_sha256": "53f6aad2821eb114b4bdd4a429b77e5aa72f80d855830209b1316854643582cc",
        "suite": "swe"
      },
      "schema": "anvil-serving.benchmark-evidence/v1",
      "stages": [
        {
          "evidence": [
            {
              "bytes": 10882,
              "path": "REDACTED_PRIVATE_REFERENCE",
              "sha256": "e59dafea62fa651ac9880721adb2f9ee7d76b2c1f8a13280c06a1895513b0607"
            }
          ],
          "name": "asset_preparation",
          "sequence": 0,
          "status": "completed"
        },
        {
          "evidence": [
            {
              "bytes": 2006,
              "path": "REDACTED_PRIVATE_REFERENCE",
              "sha256": "e3ece539cd2a47352f1fbe7b07a373e069ea8095b73b75c96f2a0ae290f26dc6"
            }
          ],
          "name": "preflight",
          "sequence": 1,
          "status": "completed"
        },
        {
          "evidence": [
            {
              "bytes": 28139,
              "path": "REDACTED_PRIVATE_REFERENCE",
              "sha256": "b54f187c5172fb18fd50315edc7c036f21e1d1474db41884478903957ef9d5a6"
            }
          ],
          "name": "swe",
          "sequence": 2,
          "status": "completed"
        }
      ],
      "summary": {
        "attempted": 5,
        "graded": 5,
        "resolve_rate": 0.6,
        "resolved": 3
      }
    }
  },
  "run": {
    "ownership_id": "REDACTED_RUN_OR_REQUEST_ID",
    "profile": "scout",
    "run_id": "REDACTED_RUN_OR_REQUEST_ID",
    "spec_sha256": "53f6aad2821eb114b4bdd4a429b77e5aa72f80d855830209b1316854643582cc",
    "suite": "swe"
  },
  "schema": "anvil-serving.benchmark-result/v1",
  "status": "completed"
}
