{
  "abstract": "Predicting the glass-transition temperature (Tg) helps select polymers for a service-temperature window, but accuracy on familiar structures may not transfer to a new family. We compare validation protocols on 7367 curated homopolymers. Histogram gradient boosting gives R2 = 0.899 and mean absolute error (MAE) = 23.9 K under random cross-validation, 0.857 and 28.5 K under scaffold holdout, a class-macro mean of 0.355 and 43.3 K under curator-class holdout, and −3.79 and 79.5 K under high-Tg extrapolation. Similarity explains only 6–11% of within-protocol absolute-error variance in the first three settings. A separate density functional theory (DFT) band-gap dataset shows a moderate fingerprint-cluster holdout penalty and poor property-range extrapolation for the tested baselines. Random-forest split-conformal empirical coverage falls from 0.899 under random splitting to 0.683 and 0.214 under class and property holdout; the tested prospective similarity gate provides little protection. A fold-fitted group-contribution prior is more sensitive to uniform additive bias in a squared-loss penalty than as a neural-network input, but this comparison is architecture-dependent. Class-holdout intervals and tests are descriptive or nominal because training sets overlap. The 279 multiply reported polymers support only the between-source variability analysis. Validation should match the intended polymer family and property range.",
  "abstract_shown": true,
  "affiliations": [
    "College of Transportation, Ludong University, Yantai 264025, China",
    "Analysis and Testing Center, Ludong University, Yantai 264025, China",
    "Graduate School of Convergence Science and Technology, Seoul National University, Seoul 08826, Republic of Korea",
    "National Engineering Laboratory for Advanced Tire Equipment and Key Materials, Qingdao University of Science and Technology, Qingdao 266061, China"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Deao Han"
    },
    {
      "affs": [
        0
      ],
      "name": "Yangkun Shao"
    },
    {
      "affs": [
        0
      ],
      "name": "Xueru Zhong"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Zhanzhao Song"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Quanzhong Zhang"
    },
    {
      "affs": [
        3
      ],
      "name": "Chuansheng Wang"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Deshang Han",
      "orcid": "0000-0003-0418-0953"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Lin Wang",
      "orcid": "0009-0008-7990-1771"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3h3kar842z1xj.bib",
  "cited_by": 0,
  "doi": "10.3390/polym18192445",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13667063/?tool=EBI",
  "id": "3h3kar842z1xj",
  "issns": [
    "2073-4360"
  ],
  "landing_url": "https://europepmc.org/article/PMC/PMC13667063",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7220926952",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13667063/pdf/?tool=EBI",
  "pmcid": "PMC13667063",
  "pmid": null,
  "published": "2026-10-01",
  "publisher": "MDPI AG",
  "ris": "https://research.draconitic.com/paper/3h3kar842z1xj.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:31Z",
      "native_id": "PMC:PMC13667063",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13667063"
    },
    {
      "first_seen": "2026-10-30T12:18:44Z",
      "native_id": "10.3390/polym18192445",
      "source": "crossref",
      "url": "https://www.mdpi.com/2073-4360/18/19/2445"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "What Random Splits Measure in Polymer Glass-Transition Prediction: Chemistry Holdouts, Applicability Domains, and Prior Integration",
  "title_text": "What Random Splits Measure in Polymer Glass-Transition Prediction: Chemistry Holdouts, Applicability Domains, and Prior Integration",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:18:44Z",
  "url": "https://research.draconitic.com/paper/3h3kar842z1xj",
  "venue": "Polymers",
  "versions": []
}