{
  "abstract": "AI-guided materials design increasingly connects candidate generation with processing and experimental planning, yet recognizing a material’s final thermal endpoint is not the same as reconstructing how it gets there. We benchmarked closed-book reconstruction of source-qualified differential scanning calorimetry event maps for 30 molecular materials using GPT-5.6 Luna, GPT-6 Luna, GPT-5.6 Sol, and Claude Opus 5.5. In the primary API experiment, models recovered terminal melting in 194/216 opportunities (89.8%) but other thermal transitions and pathways in only 105/318 (33.0%). Additional frontier-model configurations reproduced this endpoint-pathway gap. Providing source-reported preparation and scan conditions did not improve pathway reconstruction: recall changed by −6.5 percentage points (95% CI, −14.5 to +0.9) for Sol and −4.9 points (−13.6 to +4.5) for Opus. Frontier models can therefore recognize where a material’s thermal trajectory ends while failing to reconstruct the state changes determining how it gets there.",
  "abstract_shown": true,
  "affiliations": [
    "Stern College for Women",
    "Yeshiva University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Olga Lavinda",
      "orcid": "0000-0003-3577-5984"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bvreh33qhrvre.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009710/v1",
  "fulltext_url": null,
  "id": "bvreh33qhrvre",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009710/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": "W7215101614",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009710/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/bvreh33qhrvre.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:21Z",
      "native_id": "10.26434/chemrxiv.15009710",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009710/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Thermal pathway reconstruction exposes a reliability gap for AI-guided materials design",
  "title_text": "Thermal pathway reconstruction exposes a reliability gap for AI-guided materials design",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:21Z",
  "url": "https://research.draconitic.com/paper/bvreh33qhrvre",
  "venue": "ChemRxiv",
  "versions": []
}