{
  "abstract": "Genomic language models can write synthetic DNA that carries no record of its origin. A generation-time watermark could provide a provenance signal, if a verifier can detect it using only the DNA sequence, a key, and published detector settings, without knowing where the generated region starts, which strand it lies on, or how it was divided into six-base tokens. We embed the SynthID tournament watermark in two genomic language models, Carbon and GENERator-v2. The verifier searches both strands, every start position, and four window lengths, and corrects its decision for the whole search. In a detection cohort of 1,544 held-out prompts, it found all 3,088 marked sequences per model, unedited and after one substituted, inserted, or deleted base. For ordinary sequences, the one-sided 95% upper confidence bound on the false-positive rate was at most 0.850%; one bound for the wrong-key control reached 1.015% (Carbon, after a deletion). In a development cohort, neither model showed a detectable change in likelihood or in predefined sequence measures. Under random edits placed without reference to the detector, detection stayed complete or nearly complete up to a 2% per-base edit rate. These results show statistical detection, not biological function, secret-key security, or robustness to an editor who sees the detector.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.04763",
  "author_total": 3,
  "authors": [
    {
      "name": "Kimon Antonios Provatas1"
    },
    {
      "name": "Christos Galanopoulos"
    },
    {
      "name": "Ilias Georgakopoulos-Soares"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8d0b3sjjh3tsy.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.04763",
  "fulltext_url": null,
  "id": "8d0b3sjjh3tsy",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.04763",
  "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",
      "cs.CR"
    ],
    [
      "arxiv",
      "q-bio.GN"
    ],
    [
      "openalex",
      "1707|Advanced Steganography and Watermarking Techniques"
    ]
  ],
  "openalex": "W7220737930",
  "pdf_url": "https://arxiv.org/pdf/2610.04763",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8d0b3sjjh3tsy.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:11Z",
      "native_id": "2610.04763",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.04763"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.GN",
      "subfield": "genetics-genomics"
    }
  ],
  "title": "Tracing model-generated DNA with position-independent watermarking",
  "title_text": "Tracing model-generated DNA with position-independent watermarking",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:11Z",
  "url": "https://research.draconitic.com/paper/8d0b3sjjh3tsy",
  "venue": "arXiv",
  "versions": []
}