logbook.json

{
  "schema_version": 1,
  "title": "Repro - AgentSuite: Toward More Reliable Agent Evaluation with a Component-Based Benchmark Auditing Pipeline",
  "emoji": "🎯",
  "space_id": "alreadyinuse003/2Exmr1eIKZ",
  "paper": null,
  "tags": [
    "icml2026-repro",
    "paper-2Exmr1eIKZ"
  ],
  "updated_at": "2026-07-21T16:47:56+00:00",
  "root": {
    "slug": "index",
    "title": "Repro - AgentSuite: Toward More Reliable Agent Evaluation with a Component-Based Benchmark Auditing Pipeline",
    "file": "pages/index.md",
    "children": [
      {
        "slug": "summary-of-reproduction",
        "title": "Summary of reproduction",
        "file": "pages/summary-of-reproduction/page.md",
        "children": []
      },
      {
        "slug": "manifests-hashes",
        "title": "Manifests & Hashes",
        "file": "pages/manifests-hashes/page.md",
        "children": []
      },
      {
        "slug": "run-receipts",
        "title": "Run Receipts",
        "file": "pages/run-receipts/page.md",
        "children": []
      },
      {
        "slug": "deviation-ledger-learnings",
        "title": "Deviation Ledger & Learnings",
        "file": "pages/deviation-ledger-learnings/page.md",
        "children": []
      },
      {
        "slug": "finding-1-judge-nondeterminism-substituted-config",
        "title": "Finding 1 — judge nondeterminism (substituted config)",
        "file": "pages/finding-1-judge-nondeterminism-substituted-config/page.md",
        "children": []
      }
    ]
  },
  "agent_view_tokens": 2802,
  "revision": "1784652476505235467"
}