{
  "abstract": "Passing an exact-clone null gate does not entail passing a matched target-selection utility gate. We call a non-tie preference between exact duplicates dark current. On 102 prespecified fresh RewardBench 2 rows, all four configuration--criterion cells report 0/102 clone preferences. Both neutral utility arms pass, but strict utility lower bounds of .539 and .745 miss the .75 working threshold. Conversely, re-evaluation of the same rows on two additional configurations yields a neutral gpt-oss utility pass with 2/102 clone preferences, leaving low-null behavior uncertified. A separately frozen 485-row extension passes both aggregate working gates under both criteria on one local raw-text configuration, yet strict Precise Instruction Following (Precise IF) alignment is 58/154 (.377). Thus matched null and utility results can diverge, and aggregate passage can coexist with weak subset alignment. Interpretation is conditional on the declared configurations, fixed source mixtures, source-label targets, and study-specific working models. The bounds are marginal, the subset rate is descriptive, and non-certification does not prove a defect.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.15610",
  "author_total": 4,
  "authors": [
    {
      "name": "Hiroyasu Usami"
    },
    {
      "name": "Keisuke Hara"
    },
    {
      "name": "Ayato Tsuboi"
    },
    {
      "name": "Naohiko Matsuda"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bnrqmjacjy2vj.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.15610",
  "fulltext_url": null,
  "id": "bnrqmjacjy2vj",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.15610",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "astro-ph.IM"
    ],
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.CL"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "openalex",
      "1702|Topic Modeling"
    ]
  ],
  "openalex": "W7164913068",
  "pdf_url": "https://arxiv.org/pdf/2606.15610",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-12",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bnrqmjacjy2vj.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:06Z",
      "native_id": "2606.15610",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.15610"
    }
  ],
  "subjects": [
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.IM",
      "subfield": "instrumentation-methods"
    }
  ],
  "title": "LLM Judges Have Dark Current: Stratified Null and Utility Tests for LLM Judge Reliability",
  "title_text": "LLM Judges Have Dark Current: Stratified Null and Utility Tests for LLM Judge Reliability",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:06Z",
  "url": "https://research.draconitic.com/paper/bnrqmjacjy2vj",
  "venue": "arXiv",
  "versions": []
}