ANVg7NnupP / logbook.json
DineshAI's picture
Add claim-complete verification for Remarks 4 and 6
e243be8 verified
Raw
History Blame Contribute Delete
2.78 kB
{
"schema_version": 1,
"title": "Repro - Demystifying LLM-as-a-Judge",
"emoji": "🎯",
"space_id": "DineshAI/ANVg7NnupP",
"paper": {
"arxiv_id": "2512.19905"
},
"tags": [
"icml2026-repro",
"paper-ANVg7NnupP"
],
"updated_at": "2026-07-26T00:00:00+00:00",
"root": {
"slug": "index",
"title": "Repro - Demystifying LLM-as-a-Judge",
"file": "pages/index.md",
"children": [
{
"slug": "current-verification",
"title": "Current verification: five claim contracts",
"file": "pages/current-verification/page.md",
"children": []
},
{
"slug": "claim-4-optimal-temperature",
"title": "Claim 4: optimal high-temperature formula",
"file": "pages/claim-4-optimal-temperature/page.md",
"children": []
},
{
"slug": "claim-5-scaling-comparison",
"title": "Claim 5: inference versus training-data scaling",
"file": "pages/claim-5-scaling-comparison/page.md",
"children": []
},
{
"slug": "evaluator-visibility-matrix",
"title": "Evaluator visibility matrix",
"file": "pages/evaluator-visibility-matrix/page.md",
"children": []
},
{
"slug": "llm-judge-scaling-repro",
"title": "llm-judge-scaling-repro",
"file": "pages/llm-judge-scaling-repro/page.md",
"children": []
},
{
"slug": "00-scored-evidence-summary",
"title": "00 - Scored evidence summary",
"file": "pages/00-scored-evidence-summary/page.md",
"children": []
},
{
"slug": "claim-1-aligned-reward",
"title": "Claim 1 - Aligned reward",
"file": "pages/claim-1-aligned-reward/page.md",
"children": []
},
{
"slug": "claim-2-finite-optimum",
"title": "Claim 2 - Finite optimum",
"file": "pages/claim-2-finite-optimum/page.md",
"children": []
},
{
"slug": "claim-3-inverse-square-best-of-k",
"title": "Claim 3 - Inverse-square best-of-k",
"file": "pages/claim-3-inverse-square-best-of-k/page.md",
"children": []
},
{
"slug": "methods-controls-and-provenance",
"title": "Methods, controls, and provenance",
"file": "pages/methods-controls-and-provenance/page.md",
"children": []
},
{
"slug": "limitations",
"title": "Limitations",
"file": "pages/limitations/page.md",
"children": []
},
{
"slug": "conclusion",
"title": "Conclusion",
"file": "pages/conclusion/page.md",
"children": []
}
]
},
"agent_view_tokens": 8000,
"revision": "candidate-awaiting-publication"
}