{
  "schema": "layer0-evidence-manifest/0.1",
  "sealed_at": "2026-11-20T05:39:36+00:00",
  "sealer_inspect_ai": "0.3.291",
  "attestation": "CONTENT_ADDRESSED_UNSIGNED",
  "attestation_note": "Hashes and Merkle root only; no signature. An owner Ed25519 signature over merkle_root (e.g. under did:web:csoai.org) is the next step and is NOT performed here.",
  "merkle_rule": "leaves sorted by filename; leaf=SHA256(0x00||sha256(file)); node=SHA256(0x01||L||R); odd node promoted",
  "merkle_root": "dc977e1c9b5c6fa0c1e6a6d1fb05e59dffe5c90fd63fb7e47a19c2c0836bd9e7",
  "leaf_count": 5,
  "caveat": "mockllm rows are pipeline tests: the mock model returns a fixed default string, so metrics are not measurements.",
  "logs": [
    {
      "file": "2026-11-20T04-51-52-00-00_gspc-govbench_Cb78yXhpQe7ZBGBibCGR4p.eval",
      "sha256": "4cdfde2aa7ec18bd13fb175e625175237c62edeb9adfd91348a795fbbee78946",
      "bytes": 34088,
      "task": "gspc_govbench",
      "task_version": "0.1.0",
      "task_args": "{}",
      "model": "hf/Qwen/Qwen2.5-0.5B-Instruct",
      "run_kind": "SMOKE_RUN_REAL_MODEL (n too small for any claim)",
      "status": "success",
      "samples_run": 10,
      "dataset_size": 237,
      "dataset": "csoai/gspc-gov",
      "dataset_revision": "c6ddc5a92c2354248e6b1328ebd341872ee80019",
      "revision_pin_source": "gspc_govbench/govbench.py DATASET_REVISION",
      "inspect_ai": "0.3.291",
      "inspect_evals": "",
      "eval_id": "dnxkvq5hRkthuA67btE5rK",
      "run_id": "oAreaoRJGp2GJBiiEsECBd",
      "created": "2026-11-20T04:51:52+00:00",
      "gspc_axes": "governance",
      "metrics": "{\"gspc_label_scorer.accuracy\": 0.1, \"gspc_label_scorer.accuracy_parsed\": 0.1, \"gspc_label_scorer.parse_rate\": 1.0, \"gspc_label_scorer.stderr\": 0.09999999999999999}"
    },
    {
      "file": "2026-11-20T05-31-04-00-00_gspc-govbench_XLvuPum2URdxWY4J8XJGPM.eval",
      "sha256": "d9d4c0c4f8bb17c058ff13bc33cde44801664021ffc5a4662ddb73eb399ca3f8",
      "bytes": 32497,
      "task": "gspc_govbench",
      "task_version": "0.1.0",
      "task_args": "{}",
      "model": "mockllm/model",
      "run_kind": "PIPELINE_TEST_MOCKLLM (not a measurement)",
      "status": "success",
      "samples_run": 10,
      "dataset_size": 237,
      "dataset": "csoai/gspc-gov",
      "dataset_revision": "c6ddc5a92c2354248e6b1328ebd341872ee80019",
      "revision_pin_source": "gspc_govbench/govbench.py DATASET_REVISION",
      "inspect_ai": "0.3.291",
      "inspect_evals": "",
      "eval_id": "K5snyGZXNR9MoM2vQF2Qns",
      "run_id": "Y3MZrzd6iPtNxJu4N2j9CP",
      "created": "2026-11-20T05:31:04+00:00",
      "gspc_axes": "governance",
      "metrics": "{\"gspc_label_scorer.accuracy\": 0.0, \"gspc_label_scorer.accuracy_parsed\": NaN, \"gspc_label_scorer.parse_rate\": 0.0, \"gspc_label_scorer.stderr\": 0.0}"
    },
    {
      "file": "2026-11-20T05-36-00-00-00_air-bench_Qo89ffGcv2wQcfL6hk7dNR.eval",
      "sha256": "3910d7d6a30652df3709fee4f8cebfdf1b7118acf935fdb7c91c3754aa424ae8",
      "bytes": 24588,
      "task": "inspect_evals/air_bench",
      "task_version": "4",
      "task_args": "{}",
      "model": "mockllm/model",
      "run_kind": "PIPELINE_TEST_MOCKLLM (not a measurement)",
      "status": "success",
      "samples_run": 5,
      "dataset_size": 5694,
      "dataset": "stanford-crfm/air-bench-2024",
      "dataset_revision": "976d9fbb0f52bce704dcbef5bd7a2652e65f2a21",
      "revision_pin_source": "inspect_evals/air_bench/air_bench.py AIR_BENCH_DATASET_REVISION",
      "inspect_ai": "0.3.291",
      "inspect_evals": "0.29.0",
      "eval_id": "PGh2fyY46Uuo6MeKk7G7dt",
      "run_id": "9EiHhow2uZJuFwYbXW2YpG",
      "created": "2026-11-20T05:36:00+00:00",
      "gspc_axes": "art5-safeguard (partial), governance (adjacent)",
      "metrics": "{\"air_bench_scorer.all\": NaN}"
    },
    {
      "file": "2026-11-20T05-36-25-00-00_coconot_kSzJiCWx9K5ZN6SBkMLJAW.eval",
      "sha256": "efe31d42bafb4ed3d0b10dd3166611157024642716dc11103ee3b07f33976118",
      "bytes": 24463,
      "task": "inspect_evals/coconot",
      "task_version": "4",
      "task_args": "{\"grader\": \"mockllm/model\"}",
      "model": "mockllm/model",
      "run_kind": "PIPELINE_TEST_MOCKLLM (not a measurement)",
      "status": "success",
      "samples_run": 5,
      "dataset_size": 1001,
      "dataset": "allenai/coconot",
      "dataset_revision": "2cbe16aabf9069f17e48c8daad8aeabc29469eb7",
      "revision_pin_source": "inspect_evals/coconot/coconot.py COCONOT_DATASET_REVISION",
      "inspect_ai": "0.3.291",
      "inspect_evals": "0.29.0",
      "eval_id": "gKNbHJEWiACRT8ETM4YNwX",
      "run_id": "fHuYHS86n6MFC5FwJT39Js",
      "created": "2026-11-20T05:36:25+00:00",
      "gspc_axes": "safety, care (partial; substitute for gated XSTest)",
      "metrics": "{\"model_graded_qa.compliance_rate\": NaN}"
    },
    {
      "file": "2026-11-20T05-36-30-00-00_coconot_PhXfomJCaAfwHsQEjmaz6A.eval",
      "sha256": "6a0530d9bdce9736a7b2c8cebc6e59af24fa35713053c6cfd15586376a1020ad",
      "bytes": 24082,
      "task": "inspect_evals/coconot",
      "task_version": "4",
      "task_args": "{\"grader\": \"mockllm/model\", \"subset\": \"contrast\"}",
      "model": "mockllm/model",
      "run_kind": "PIPELINE_TEST_MOCKLLM (not a measurement)",
      "status": "success",
      "samples_run": 5,
      "dataset_size": 379,
      "dataset": "allenai/coconot",
      "dataset_revision": "2cbe16aabf9069f17e48c8daad8aeabc29469eb7",
      "revision_pin_source": "inspect_evals/coconot/coconot.py COCONOT_DATASET_REVISION",
      "inspect_ai": "0.3.291",
      "inspect_evals": "0.29.0",
      "eval_id": "5ygL3GxBPcWFgmtNwpRRFf",
      "run_id": "VEF6HsRLAQSEFXsiZ8DgPX",
      "created": "2026-11-20T05:36:30+00:00",
      "gspc_axes": "safety, care (partial; substitute for gated XSTest)",
      "metrics": "{\"model_graded_qa.compliance_rate\": NaN}"
    }
  ]
}