{
  "abstract": "Scientific literature contains latent knowledge about materials behavior, but much of this knowledge is expressed through words, contexts, and recurring associations rather than explicit design principles. This raises a central question: how can large-scale scientific corpora be used for practical problems in materials discovery? Here, we present a literature-guided descriptor-based filtering framework for reducing composition search spaces. For a given performance metric, the framework selects two descriptors from a filtered vocabulary in a literature-trained word embedding model and uses the selected descriptors to construct a Pareto-based filter for candidate compositions. Across the evaluated performance metrics and composition search spaces, the framework filters out an average of 74.27\\% of the candidate compositions, with an average best-value error of 1.93\\% relative to experimental measurements. Compared with expert-chosen and random descriptors, our performance metric-dependent descriptors provide a more controlled balance between retained fraction and best-value error. These results show that literature-derived embeddings can support intuitive and reproducible filters for narrowing candidate composition spaces while preserving high-performing compositions.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.31650",
  "author_total": 2,
  "authors": [
    {
      "name": "Lei Zhang"
    },
    {
      "name": "Markus Stricker"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ezfdxa81hv2tf.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.31650",
  "fulltext_url": null,
  "id": "ezfdxa81hv2tf",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.31650",
  "language": null,
  "licence": "CC-BY-SA-4.0",
  "licence_label": "CC BY-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cond-mat.mtrl-sci"
    ],
    [
      "arxiv",
      "cs.CL"
    ],
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7214793630",
  "pdf_url": "https://arxiv.org/pdf/2609.31650",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ezfdxa81hv2tf.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:12Z",
      "native_id": "2609.31650",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.31650"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.mtrl-sci",
      "subfield": "condensed-matter"
    }
  ],
  "title": "A literature-guided descriptor-based framework for filtering composition search spaces",
  "title_text": "A literature-guided descriptor-based framework for filtering composition search spaces",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:12Z",
  "url": "https://research.draconitic.com/paper/ezfdxa81hv2tf",
  "venue": "arXiv",
  "versions": []
}