{
  "abstract": "An element-resolved audit of 44,688 oxide structures generated by MatterGen under chemical-system conditioning revealed that the aggregate composition compliance (73.27% exact match) concealed a severe chemistry-specific failure. Cobalt was omitted from 71.27% of the structures requesting it, against 8.12 ± 3.28% for the other 19 requested elements, and 98.17% of the cobalt omissions removed cobalt alone. Cell size, cation substitutability, stability gain and a general training-frequency effect did not account for the anomaly. Tracing the failure upstream showed that only one of the 8,924 cobalt oxides in the public Alex-MP-20 reference set passed the stability filter. The deficit was traced to a single anomalous reference-energy entry distorting the Co–O convex hull; excluding it raises the number of training-eligible cobalt oxides from 1 to 2,499. Four independent DFT calculations and the current Materials Project value agree within 0.024 eV atom-1, whereas the value implied by the released file deviates from them by 6.26 eV atom-1. A pre-registered intervention experiment showed that neither removal of the stability condition nor stronger diffusion guidance normalised the blind spot. These results show how a single high-leverage reference-energy anomaly can be amplified through stability filtering into a training deficit at the scale of a chemical family. Two audits that detect this class of failure without retraining are presented, namely an element-resolved condition-fidelity audit and a reference-hull vertex audit.",
  "abstract_shown": true,
  "affiliations": [
    "School of Materials Science and Engineering",
    "Kumoh National Institute of Technology"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Dowon Song",
      "orcid": "0009-0007-7330-8523"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/645dsa3maw2a3.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008501/v1",
  "fulltext_url": null,
  "id": "645dsa3maw2a3",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008501/v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7211969223",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008501/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-08",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/645dsa3maw2a3.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:17Z",
      "native_id": "10.26434/chemrxiv.15008501",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008501/v2"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "A single reference-energy outlier nearly eliminates Co–O chemistry from a generative model's training distribution",
  "title_text": "A single reference-energy outlier nearly eliminates Co–O chemistry from a generative model's training distribution",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:24Z",
  "url": "https://research.draconitic.com/paper/645dsa3maw2a3",
  "venue": "ChemRxiv",
  "versions": []
}