{
  "abstract": "A watermark detector can flag a text even when only a small fraction of its tokens are watermarked. We study sequential auditing to identify local passages whose watermark proportions exceed a prespecified threshold. Each alarm fixes a candidate passage's endpoint, while its start is chosen from earlier tokens. Reusing the same evidence to locate and test a passage can invalidate inference. We propose FissionGuard, which uses data fission to construct an alarm value and a validation value from each token-level $p$-value. The alarm values guide alarms and localization. The validation values yield passage-level $p$-values through partial conjunction, excluding as many of the strongest signals as the proportion null allows. These $p$-values are used to test the corresponding hypotheses at levels assigned by an online multiple-testing procedure. Under the stated watermark generation model, allowing dependence among token-level $p$-values at watermarked positions, we prove finite-sample false discovery rate (FDR) control among reported passages at every fixed finite horizon. We also derive a finite-sample lower bound on power for testing nonnull candidates. Experiments on synthetic streams and Mistral and Qwen generations across four marking layouts show gains in watermarked-token coverage over sample splitting, with empirical FDR below the target.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.11625",
  "author_total": 4,
  "authors": [
    {
      "name": "Zijian Wei"
    },
    {
      "name": "Yajie Bao"
    },
    {
      "name": "Haojie Ren"
    },
    {
      "name": "Zhen Chen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1w94r6fadavy2.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.11625",
  "fulltext_url": null,
  "id": "1w94r6fadavy2",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.11625",
  "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",
      "stat.ME"
    ],
    [
      "openalex",
      "1707|Advanced Steganography and Watermarking Techniques"
    ]
  ],
  "openalex": "W7221079489",
  "pdf_url": "https://arxiv.org/pdf/2610.11625",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-08",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/1w94r6fadavy2.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:28:03Z",
      "native_id": "2610.11625",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.11625"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ME",
      "subfield": "statistics"
    }
  ],
  "title": "FissionGuard: Testing Local Watermark Proportions with FDR Control",
  "title_text": "FissionGuard: Testing Local Watermark Proportions with FDR Control",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:03Z",
  "url": "https://research.draconitic.com/paper/1w94r6fadavy2",
  "venue": "arXiv",
  "versions": []
}