{
  "abstract": "Diffusion-based molecular docking requires learning a corrective score field across a broad corruption distribution, yet individual pose errors can differ substantially in their structural consequences. This creates a post-training conflict between preserving broad score-field coverage and concentrating supervision on corrections that appear more relevant to docking geometry. Using DiffDock, a fixed-budget study compares broad continuation with torsional supervision focused on Cartesian consequence or conditional target consistency, and with a broad/focused mixture. Evaluation separates fixed score fidelity, generated-pose quality, best-of-10 sampling capacity, and confidence-selected Top-1 docking performance. At <5 Angstrom, broad continuation had the highest mean Top-1 success among trained policies, and focused or mixed supervision showed no consistent advantage under the tested budget. The starting model had better fixed score fidelity, whereas the evaluated broad-continuation model had higher mean Top-1 success with the same aggregate best-of-10 recovery. Focusing supervision on structurally consequential or more consistently specified corrections did not consistently improve returned-pose success over broad continuation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.08249",
  "author_total": 5,
  "authors": [
    {
      "name": "Michael Brown"
    },
    {
      "name": "Maryam Rahimimovassagh"
    },
    {
      "name": "Mehdi Yazdani-Jahromi"
    },
    {
      "name": "Sanjeda Sara Jennifer"
    },
    {
      "name": "Ivan Garibay"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7kkb3sank1xsq.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.08249",
  "fulltext_url": null,
  "id": "7kkb3sank1xsq",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.08249",
  "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.LG"
    ],
    [
      "arxiv",
      "q-bio.BM"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.08249",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7kkb3sank1xsq.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T18:21:35Z",
      "native_id": "2611.08249",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.08249"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "arxiv:q-bio.BM",
      "subfield": "biophysics"
    }
  ],
  "title": "Geometric Relevance Is Not Sufficient: Evaluating Focused Post-Training Supervision in Diffusion Docking",
  "title_text": "Geometric Relevance Is Not Sufficient: Evaluating Focused Post-Training Supervision in Diffusion Docking",
  "type": "preprint",
  "updated_at": "2026-11-09T00:20:50Z",
  "url": "https://research.draconitic.com/paper/7kkb3sank1xsq",
  "venue": "arXiv",
  "versions": []
}