Source-backed research brief

{
  "benchmarkRunId": "64e1e271-a7a4-4d85-b6e6-30279db284f3",
  "benchmarkId": "benchmark/source-backed-research@1.0.0",
  "benchmarkTitle": "Source-backed research brief",
  "packageId": "addr/0xFf620746854Bde9EBbE0e90901974b5da746670d/research-agent@1.0.0",
  "packageHash": "sha256:e96cfebb51afde7f5a8bd32668f2d6a5815642b85e34b1fe93fd6f58a9ee5447",
  "runtime": "codex",
  "signer": "addr:0x1111111111111111111111111111111111111111",
  "principalId": "sha256:1de23445c17dad6016018d084723eeef88ea7995253055bd40ceed5695a6db8d",
  "writeReceiptRequested": true,
  "status": "success",
  "executionBackend": "local",
  "requestedExecutionBackend": "auto",
  "sandboxProfile": "default",
  "networkPolicy": "none",
  "timeoutMs": 10000,
  "benchmarkDefinitionHash": "sha256:e312a86a54f41197730b5ae0a0d0f3768dd06b8d63225b0e4300fdd44fae1f2a",
  "replayInput": {
    "availableTools": [
      "fetch",
      "markdown"
    ],
    "grantedPermissions": [
      "http:get",
      "storage:write"
    ],
    "requestedApiOrigins": [],
    "requestedChains": [],
    "requestedTokens": []
  },
  "score": 10,
  "maxScore": 10,
  "summary": "Benchmark suite produced the expected deterministic output.",
  "startedAt": "2026-03-17T20:20:46.332Z",
  "createdAt": "2026-03-17T20:20:46.332Z",
  "evaluationChecks": [
    {
      "id": "runtime:codex",
      "status": "pass",
      "message": "Runtime codex is supported."
    },
    {
      "id": "namespace:verified",
      "status": "pass",
      "message": "Namespace is verified."
    },
    {
      "id": "tool:fetch",
      "status": "pass",
      "message": "Required tool fetch is available."
    },
    {
      "id": "tool:markdown",
      "status": "pass",
      "message": "Required tool markdown is available."
    },
    {
      "id": "permission:http:get",
      "status": "pass",
      "message": "Permission http:get is granted."
    },
    {
      "id": "permission:storage:write",
      "status": "pass",
      "message": "Permission storage:write is granted."
    },
    {
      "id": "policy:attached",
      "status": "skip",
      "message": "No attached policy to validate against."
    }
  ],
  "caseResults": [
    {
      "caseId": "returns-source-backed-summary",
      "title": "Returns a source-backed summary",
      "status": "pass",
      "score": 5,
      "maxScore": 5,
      "message": "Benchmark brief includes the expected source-backed summary language."
    },
    {
      "caseId": "captures-cited-links",
      "title": "Captures cited links",
      "status": "pass",
      "score": 5,
      "maxScore": 5,
      "message": "Benchmark brief included all required cited links."
    }
  ],
  "evaluationOk": true,
  "blockedByPreflight": false,
  "completedAt": "2026-03-17T20:20:46.386Z",
  "lastHeartbeatAt": "2026-03-17T20:20:46.386Z",
  "outputHash": "sha256:086d3d4dcb4c62652afd42091bad853ac638fa0c5aba4ebf9ef268fd56b8d47b",
  "stdoutObjectKey": "64e1e271-a7a4-4d85-b6e6-30279db284f3/output.md",
  "artifactsObjectPrefix": "64e1e271-a7a4-4d85-b6e6-30279db284f3/",
  "judgeSummary": "Benchmark suite produced the expected deterministic output. The research brief includes the expected source-backed summary language and captures all required cited links.",
  "receiptId": "342e9e18-5ac5-4093-a68d-6822d49cd4e9"
}