{
  "abstract": "Polymer-property machine learning is often evaluated as if representation choice, random-split accuracy, chemical extrapolation, transfer learning, uncertainty, and chemical interpretation were a single problem. Here, these questions are separated in a six-stage Polymer Informatics Atlas built from 7,973 unique RDKit-valid polymer repeat units in the NeurIPS Open Polymer Prediction 2025 dataset. Thirty-six interpretable composition/structure descriptors and radius-4, 2,048-dimensional count Morgan fingerprints were evaluated independently and as a hybrid representation for glass-transition temperature (Tg), fractional free volume (FFV), thermal conductivity (Tc), density, and radius of gyration (Rg). Frozen property-specific models achieved untouched random-holdout R2 values of 0.608, 0.704, 0.825, 0.920, and 0.703, respectively. However, chemistry-separated testing changed this interpretation substantially: Tc fell to R2 = 0.326, whereas density remained comparatively robust at R2 = 0.874. Representation-block permutation showed that density was predominantly captured by interpretable global chemistry, while Tc and Rg depended more strongly on local/topological structure; Tg and FFV required mixed information. Masked multitask learning on the overlapping Tc-Density-Rg block used incomplete labels more efficiently than complete-case training, but gains over matched single-task neural networks were small and seed dependent. Five-member ensembles combined with splitconformal calibration produced 90% nominal intervals with empirical coverages of 95.7% (Tc), 92.3% (density), and 98.5% (Rg). Finally, 28 predictive Morgan indices were decoded to atom-centred environments after exact fingerprint-regeneration audits, and an integrated descriptor/fingerprint manifold was used for chemical-space visualization, archetype selection, and an illustrative high-Tc/low-density Pareto analysis. The results support a property-specific, domain-aware view of polymer informatics in which predictive accuracy is reported together with chemical support, uncertainty, and explicit claim boundaries rather than as a single global score.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Industrial Chemistry, Faculty of Applied Physical Sciences",
    "Enugu State University of Science and Technology (ESUT"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Dennis Obinna Orji",
      "orcid": "0009-0009-1674-0883"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8nda2gc5wtsa5.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008969/v1",
  "fulltext_url": null,
  "id": "8nda2gc5wtsa5",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008969/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": "W7213444340",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008969/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-17",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/8nda2gc5wtsa5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:19Z",
      "native_id": "10.26434/chemrxiv.15008969",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008969/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Polymer Informatics Atlas: Property-Specific Representations, Chemistry-Aware Generalization, and Reliability-Aware Machine Learning Across Five Polymer Properties",
  "title_text": "Polymer Informatics Atlas: Property-Specific Representations, Chemistry-Aware Generalization, and Reliability-Aware Machine Learning Across Five Polymer Properties",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:19Z",
  "url": "https://research.draconitic.com/paper/8nda2gc5wtsa5",
  "venue": "ChemRxiv",
  "versions": []
}