{
  "abstract": "Validating an LLM-as-a-judge requires estimating its agreement with humans, yet annotation budgets rarely allow every item to be multiply labeled. We prove that this overlap sparsity is the first-order determinant of wrong deployment decisions: at 5% pairwise overlap, wrong-decision rates reach 25% and the probability of selecting the wrong best judge among ten candidates is 65%. The two actionable levers are overlap quantity and allocation. For quantity, we derive a minimum-overlap formula showing $ρ\\geq 0.25$ suffices for non-borderline judges while borderline cases remain fundamentally hard. For allocation, a zero-cost stratified scheme halves false-rejection rates relative to random sampling when strata are informative. We validate on 10 LLM judges across four evaluation matrices spanning visual assessment, causal reasoning, and summarization.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.31857",
  "author_total": 3,
  "authors": [
    {
      "name": "Junxuan Li"
    },
    {
      "name": "Arko Mukherjee"
    },
    {
      "name": "Soumyabrata Pal"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6y4tcfp5r79v8.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.31857",
  "fulltext_url": null,
  "id": "6y4tcfp5r79v8",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.31857",
  "language": null,
  "licence": "CC-BY-NC-SA-4.0",
  "licence_label": "CC BY-NC-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "stat.AP"
    ],
    [
      "openalex",
      "3320|Artificial Intelligence in Law"
    ]
  ],
  "openalex": "W7214756010",
  "pdf_url": "https://arxiv.org/pdf/2609.31857",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-29",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/6y4tcfp5r79v8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:41Z",
      "native_id": "2609.31857",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.31857"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.AP",
      "subfield": "statistics"
    }
  ],
  "title": "LLM Judge Validation Under Sparse Overlap: From Inference to Design",
  "title_text": "LLM Judge Validation Under Sparse Overlap: From Inference to Design",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:41Z",
  "url": "https://research.draconitic.com/paper/6y4tcfp5r79v8",
  "venue": "arXiv",
  "versions": []
}