{
  "abstract": "Min et al. (2026) provide a timely checklist for improving the transparency and trust of supervised machine learning (ML) research in psychology. I strongly endorse this goal and recognize that their focus on retrospective reporting is both valuable and the appropriate scope for an article. However, I suggest that two related issues warrant greater emphasis in their framework: information leakage and procedural overfitting. Both can produce optimistic estimates of model performance despite apparently transparent reporting. I propose two extensions to the checklist: reporting requirements that make information leakage auditable and prospective specification of key analytical decisions through preregistration. I argue that these additions would further strengthen the ability of readers and reviewers to evaluate the trustworthiness of supervised ML analyses in psychology. Moreover, comprehensive guidelines that do not sufficiently emphasize these issues may create unwarranted confidence that threats to valid model evaluation have been ruled out, allowing information leakage or procedural overfitting to remain undetected.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "name": "Rosa Lavelle-Hill"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bm68h708jbvjc.bib",
  "cited_by": 0,
  "doi": "10.31234/osf.io/cw348_v1",
  "fulltext_url": null,
  "id": "bm68h708jbvjc",
  "issns": [],
  "landing_url": "https://osf.io/preprints/psyarxiv/cw348_v1/",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "bepress",
      "Experimental Design and Sample Surveys"
    ],
    [
      "bepress",
      "Quantitative Methods"
    ],
    [
      "bepress",
      "Quantitative Psychology"
    ],
    [
      "bepress",
      "Social and Behavioral Sciences"
    ],
    [
      "bepress",
      "Statistical Methods"
    ],
    [
      "bepress",
      "Theory and Philosophy of Science"
    ],
    [
      "openalex",
      "1804|Meta-analysis and systematic reviews"
    ]
  ],
  "openalex": "W7223201381",
  "pdf_url": "https://osf.io/cw348/download",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bm68h708jbvjc.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:59Z",
      "native_id": "cw348",
      "source": "osf",
      "url": "https://osf.io/preprints/psyarxiv/cw348_v1/"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "bepress:Statistical Methods",
      "subfield": "statistics"
    }
  ],
  "title": "Transparency Is Necessary but Not Sufficient for Trust: Information Leakage and Procedural Overfitting in Supervised Machine Learning for Psychology",
  "title_text": "Transparency Is Necessary but Not Sufficient for Trust: Information Leakage and Procedural Overfitting in Supervised Machine Learning for Psychology",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:59Z",
  "url": "https://research.draconitic.com/paper/bm68h708jbvjc",
  "venue": "PsyArXiv",
  "versions": []
}