{
  "abstract": "How much fitting evidence, and which materials descriptors, are needed to prioritize porous materials? We analyze archived computational uptake labels for 279,010 metal–organic frameworks at four CO2/CH4 conditions (298 K). In retrospective experiments using target-informed example selection, each condition reaches at least 90% of its B = 1000 top-5% recall endpoint by B = 500. Local-chemistry RAC descriptors improve methane top-5% recall by 0.175 at 5.8 bar but only 0.039 at 65 bar, consistent with a pressure-dependent balance between chemical and geometric signals. These values describe predictor-fitting budgets, not total acquisition cost: the random-split setting also uses approximately 44,642 labeled structures for conformal calibration. Missing historical split identities and reference-informed candidate selection constrain transfer and shortlist claims. Thus, adsorption conditions appear to modify representation utility, while prospective label efficiency and physical attribution require independent, leakage-audited validation.",
  "abstract_shown": true,
  "affiliations": [
    "Lucy Cavendish College",
    "University of Cambridge",
    "School of Chemical Engineering, Faculty of Engineering",
    "University of Tehran"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Natalia Lydia Papadantonaki"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Angelo Di Bella"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Shayan Abaei",
      "orcid": "0009-0001-5794-0314"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Mehrdad Asgari"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/e6khntynvab71.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15010304/v1",
  "fulltext_url": null,
  "id": "e6khntynvab71",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010304/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": "W7221605497",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010304/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-12",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/e6khntynvab71.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:22Z",
      "native_id": "10.26434/chemrxiv.15010304",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010304/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Adsorption regime changes the information needed for data-driven metal–organic framework screening",
  "title_text": "Adsorption regime changes the information needed for data-driven metal–organic framework screening",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:22Z",
  "url": "https://research.draconitic.com/paper/e6khntynvab71",
  "venue": "ChemRxiv",
  "versions": []
}