{
  "abstract": "Transition states are defined by reaction pathways, yet most machine-learning methods predict them as isolated geometries. We introduce MARC-TS, a two-stage framework that learns a continuous, endpoint-conditioned path, queries it at any resolution and uses local path context to refine a transition-state candidate. We construct T1x-IRC-8K, a dataset of 8,209 reactions and 1,088,725 path-resolved geometries. On held-out reactions, the path model reduced complete-path error by 48.4% relative to endpoint interpolation, and the localizer achieved a mean aligned structural error of 0.127 Å. Quantum-chemical optimization and vibrational analysis yielded 405 frequency-confirmed first-order saddle-point candidates from 410 predictions. In a 100-reaction nudged elastic band comparison, learned-path initialization reached a joint geometry-and-force target for 66% of reactions, compared with 12% for geometric interpolation after 100 optimizer steps. By treating the path as a reusable representation rather than an auxiliary output, MARC-TS connects transition-state prediction, mechanistic interpretation and quantum-chemical refinement.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.25523",
  "author_total": 2,
  "authors": [
    {
      "name": "Yexiang Yang"
    },
    {
      "name": "Linlin Zhong"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8txj9xgp2wbdh.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.25523",
  "fulltext_url": null,
  "id": "8txj9xgp2wbdh",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.25523",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "physics.chem-ph"
    ],
    [
      "arxiv",
      "physics.comp-ph"
    ],
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7214084063",
  "pdf_url": "https://arxiv.org/pdf/2609.25523",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8txj9xgp2wbdh.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:39Z",
      "native_id": "2609.25523",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.25523"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "arxiv:physics.chem-ph",
      "subfield": "physical"
    },
    {
      "field": "physics",
      "origin": "arxiv:physics.comp-ph",
      "subfield": "computational"
    }
  ],
  "title": "Learning continuous reaction paths for transition-state prediction",
  "title_text": "Learning continuous reaction paths for transition-state prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:39Z",
  "url": "https://research.draconitic.com/paper/8txj9xgp2wbdh",
  "venue": "arXiv",
  "versions": []
}