{
  "abstract": "1. Learned sequence embeddings are increasingly proposed for fungal ITS classification and novelty detection, but are usually evaluated against weaker versions of themselves or default-configured alignment, by AUROC alone, and with queries treated as independent. We asked whether a purpose-trained encoder outperforms percent identity when both score identical queries under a firewalled open-world design, and which evaluation choices decide the answer. 2. From the UNITE release of 19 February 2025 we built ITS-core, ITS1 and ITS2 views and a genus-separated split with sealed calibration and test partitions. A convolutional encoder trained with genus-proxy, cross-view, hierarchical and episodic objectives was frozen and hash-sealed before test data were opened. We compared it with exhaustive, coverage-filtered VSEARCH identity on the same queries and references using genus-clustered paired intervals, and logged every post-opening correction before computing corrected metrics. 3. Three evaluation choices changed the comparison. Default VSEARCH heuristics returned a lower-identity hit than exhaustive search for 48.3% of benchmark queries; without a coverage filter, identity placed only 64.9% of novel ITS-core queries in the correct class, against 98.7% with it, because the conserved 5.8S let partial alignments win; and the encoder's embeddings depended on inference batching. Once corrected, identity exceeded the encoder in known-genus accuracy and novel-family placement at every view (family 80.0% to 84.6% against 53.8% to 64.8%) and detected more novel genera at a lower false-novelty rate. The encoder's novelty AUROC was within 0.023 of identity's, and no genus-clustered interval excluded zero. Identity's own development-to-test gap exceeded the encoder's, so that gap reflects partition composition rather than selection. Of the genera held out by a historical benchmark, 85% had been present in training; on a leakage-safe version, identity's AUROC advantage was 0.065, with a genus-clustered interval excluding zero. 4. Correctly configured alignment matched or exceeded the learned embedding throughout. The decisive results came from the evaluation, not the representation: baseline configuration, batch invariance, genus-level uncertainty, a parameter-free control for selection and a leakage audit each changed a conclusion, and each is inexpensive to apply to any learned barcode method.",
  "abstract_shown": true,
  "affiliations": [
    "Universidad Andres Bello"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "A. O'Brien"
    },
    {
      "name": "A. Gardette"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9xbfa94ke3xsq.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.17.752437",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752437v1.full",
  "id": "9xbfa94ke3xsq",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752437v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1110|Mycorrhizal Fungi and Plant Interactions"
    ]
  ],
  "openalex": "W7214111644",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752437v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-17",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9xbfa94ke3xsq.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:09Z",
      "native_id": "10.64898/2026.09.17.752437",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752437v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Open-world fungal ITS embeddings improve higher-rank placement and cross-view retrieval, but percent identity is stronger on a matched ITS2 novelty benchmark",
  "title_text": "Open-world fungal ITS embeddings improve higher-rank placement and cross-view retrieval, but percent identity is stronger on a matched ITS2 novelty benchmark",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:30Z",
  "url": "https://research.draconitic.com/paper/9xbfa94ke3xsq",
  "venue": "bioRxiv",
  "versions": []
}