{
  "abstract": "Can a genome model retain a detectable record of the synthetic sequences used to train it? We study watermark inheritance through distillation with GenoTrace, a codon-aware extension of green-list watermarking. Two token-level factors modulate the teacher's generation bias using codon position and organism-specific codon usage. The resulting sequences train a smaller student, whose outputs are audited without an active watermark processor. In a three-seed GenomeOcean-500M-to-100M experiment, the joint configuration achieves a mean audit score of 17.88 and 94.5% detection at a fixed threshold. It retains 49.0% detection after key-aware token substitution, compared with 0% for the available single-seed plain-watermark comparator, and 47.0% after combined mechanism-targeted nucleotide edits. Additional experiments establish inherited signal across five organism-conditioned datasets and teacher-student size ratios up to 40. Component ablations and computational sequence-quality assays reveal distinct operating points for detection strength and coding coverage. GenoTrace provides a practical token-level construction and an empirical account of how genomic structure shapes inherited watermark signals. The findings concern shared-tokenizer distillation and the tested editing procedures, with calibration and biological utility treated as separate evaluation requirements.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.35881",
  "author_total": 2,
  "authors": [
    {
      "name": "Guang Yang"
    },
    {
      "name": "Fengchen Liu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4mtyem54ts459.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.35881",
  "fulltext_url": null,
  "id": "4mtyem54ts459",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.35881",
  "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",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-bio.GN"
    ],
    [
      "openalex",
      "1707|Advanced Steganography and Watermarking Techniques"
    ]
  ],
  "openalex": "W7214885903",
  "pdf_url": "https://arxiv.org/pdf/2609.35881",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/4mtyem54ts459.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:50Z",
      "native_id": "2609.35881",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.35881"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.GN",
      "subfield": "genetics-genomics"
    }
  ],
  "title": "GenoTrace: Inheritable Watermarks for Genome Foundation Model Distillation",
  "title_text": "GenoTrace: Inheritable Watermarks for Genome Foundation Model Distillation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:50Z",
  "url": "https://research.draconitic.com/paper/4mtyem54ts459",
  "venue": "arXiv",
  "versions": []
}