{
  "id": 17183147,
  "title": "TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races",
  "url": "https://urgent.news/2026/10/29/textseal2-distortion-free-llm-watermarking-with-copula-mixing-and",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-29T17:54:12.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.40613v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative decoding: tokens that replace rejected drafts remain watermarked with the same keys, and the acceptance rate is unchanged. It also preserves output diversity and adds no measurable inference latency. Its predecessor, TextSeal, restores diversity in the Gumbel-max scheme by routing…",
  "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."
}