{
  "abstract": "Machine-learned conformer generators are scored on GEOM-DRUGS by proximity to a reference ensemble that standard benchmark metrics implicitly treat as ground truth. We test whether that finite set is complete on the GFN2-xTB surface used to construct it. Across five public generators, settled, low-energy structures remain outside the $0.75$\\,Å reference radius after removing reflections, incorrect stereochemistry, and post-relaxation connectivity changes ($2.3$--$7.0\\%$ of submitted conformers, depending on architecture). In a targeted DFT audit, $107$ of $113$ chemically screened novel/reference pairs remain outside that radius after full $ω$B97X-D3BJ re-optimization. A threshold-free complementary test needs no radius and no energy window at all: on $15.0\\%$ $[8.0, 22.0]$ of molecules some generator has already found a chemically intact structure lying below the \\emph{entire} released ensemble. A complementary CREST search reproduces the minimum released in $65$ of $69$ molecules, and in $11$ of them it reaches more than $0.5$\\,kcal/mol below the complete released ensemble. Augmenting the references with conformers proposed by held-out architectures raises absolute coverage-precision for every generator tested, by $1.48$--$2.99$ points. Together, these results show that GEOM-DRUGS precision is sensitive not only to generator quality but also to incomplete reference support.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.12523",
  "author_total": 4,
  "authors": [
    {
      "name": "Alvand Vahediahmar"
    },
    {
      "name": "Aaron Zweig"
    },
    {
      "name": "Mingxuan Zhang"
    },
    {
      "name": "Elham Azizi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4cwhe32etsjxs.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.12523",
  "fulltext_url": null,
  "id": "4cwhe32etsjxs",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.12523",
  "language": null,
  "licence": "CC-BY-NC-SA-4.0",
  "licence_label": "CC BY-NC-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "physics.chem-ph"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7221546020",
  "pdf_url": "https://arxiv.org/pdf/2610.12523",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-08",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/4cwhe32etsjxs.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:28:36Z",
      "native_id": "2610.12523",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.12523"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "arxiv:physics.chem-ph",
      "subfield": "physical"
    }
  ],
  "title": "The Reference Set Is Not the Answer Set: GEOM-DRUGS Is Missing Low-Energy Conformers on Its Own Energy Surface",
  "title_text": "The Reference Set Is Not the Answer Set: GEOM-DRUGS Is Missing Low-Energy Conformers on Its Own Energy Surface",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:36Z",
  "url": "https://research.draconitic.com/paper/4cwhe32etsjxs",
  "venue": "arXiv",
  "versions": []
}