{
  "id": 15538086,
  "title": "Not All Test-Time Compute Is Evidence: Model-Specific Bias in LLM Reasoning",
  "url": "https://urgent.news/2026/10/16/not-all-test-time-compute-is-evidence-model-specific-bias-in-llm",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-16T09:48:02.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.23213v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Test-time scaling methods implicitly assume that additional computation from the same model provides independent evidence. We show that this assumption fails within a single reasoning model: errors are correlated across repeated samples, across reasoning depth, and in the model's own self-evaluation, so more compute from the same model is not more evidence. We introduce DIA…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}