oCNT5PcMSQ / logbook.json
nkapila6's picture
Update logbook: Repro: CapBencher - Give Your LLM Benchmark a Built-in Alarm
3f36141 verified
Raw
History Blame Contribute Delete
2.05 kB
{
"schema_version": 1,
"title": "Repro: CapBencher - Give Your LLM Benchmark a Built-in Alarm",
"emoji": "๐Ÿ”’",
"space_id": "nkapila6/oCNT5PcMSQ",
"paper": null,
"tags": [
"icml2026-repro",
"paper-oCNT5PcMSQ",
"benchmark",
"contamination"
],
"updated_at": "2026-07-17T06:15:07+00:00",
"root": {
"slug": "index",
"title": "Repro: CapBencher - Give Your LLM Benchmark a Built-in Alarm",
"file": "pages/index.md",
"children": [
{
"slug": "00-scorecard",
"title": "00 - Scorecard",
"file": "pages/00-scorecard/page.md",
"children": []
},
{
"slug": "sources-protocol",
"title": "Sources & Protocol",
"file": "pages/sources-protocol/page.md",
"children": []
},
{
"slug": "claim-1-capping-mechanism",
"title": "Claim 1: Capping mechanism",
"file": "pages/claim-1-capping-mechanism/page.md",
"children": []
},
{
"slug": "claim-2-monotonic-relationship",
"title": "Claim 2: Monotonic relationship",
"file": "pages/claim-2-monotonic-relationship/page.md",
"children": []
},
{
"slug": "claim-3-exact-binomial-tests",
"title": "Claim 3: Exact binomial tests",
"file": "pages/claim-3-exact-binomial-tests/page.md",
"children": []
},
{
"slug": "claim-4-model-merge-detection",
"title": "Claim 4: Model merge detection",
"file": "pages/claim-4-model-merge-detection/page.md",
"children": []
},
{
"slug": "conclusion",
"title": "Conclusion",
"file": "pages/conclusion/page.md",
"children": []
},
{
"slug": "claim-5-real-llm-capping-demonstration",
"title": "Claim 5: Real LLM capping demonstration",
"file": "pages/claim-5-real-llm-capping-demonstration/page.md",
"children": []
}
]
},
"agent_view_tokens": 2946,
"revision": "1784268907475072000"
}