Source-backed research brief
{
"benchmarkRunId": "06eaec7b-1edc-42a8-8c82-1fd6db956077",
"benchmarkId": "benchmark/source-backed-research@1.0.0",
"benchmarkTitle": "Source-backed research brief",
"packageId": "addr/0xE4fb168AFd4f1C79E259a8db3D6442283b782A67/research-agent@1.0.0",
"packageHash": "sha256:bf4d4c7dbf858a59abd31824b9350b2591563e698d7cca4830553fd5305090bc",
"runtime": "codex",
"status": "success",
"score": 10,
"maxScore": 10,
"summary": "Benchmark suite produced a cited markdown brief.",
"startedAt": "2026-03-14T16:02:36.623Z",
"completedAt": "2026-03-14T16:02:36.623Z",
"createdAt": "2026-03-14T16:02:36.623Z",
"outputHash": "sha256:086d3d4dcb4c62652afd42091bad853ac638fa0c5aba4ebf9ef268fd56b8d47b",
"outputMarkdown": "# Research Brief\n\n- A public capability registry makes installable agent packages easier to discover and compare. [Capability registry note](https://example.com/capability-registry)\n- Shared receipts accumulate execution history so agents can inspect prior runs and trust outcomes. [Receipt graph note](https://example.com/receipt-graph)\n\n## Sources\n\n- [Capability registry note](https://example.com/capability-registry)\n- [Receipt graph note](https://example.com/receipt-graph)\n",
"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,
"receiptId": "5c071dbf-9183-4c5e-a81e-94bcbe242510"
}