{
  "abstract": "Finding which phenomena occur in a tokamak discharge, and when, is often a manual task. Previous efforts at labeling events have been task-specific, each with its own corpus of data. We introduce Tokamak-SI, which combines the labels and labeling methods of many earlier studies into a single scalable, time-aligned, and categorical dataset covering observations from confinement, detachment, alfven eigenmodes (AE), edge localized modes (ELM), sawtooth, tearing modes (TM), and resistive wall modes in DIII-D tokamak. Models based on this, which can extend the labels to new shots, match or beat earlier detectors on its labels, including for AE, ELM, and TM detection. Tokamak-SI is intended to enable task-specific benchmarking, physics-searchable archives, and direct identification of key events during an experiment.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.32264",
  "author_total": 6,
  "authors": [
    {
      "name": "Nathaniel Chen"
    },
    {
      "name": "Alvin Garcia"
    },
    {
      "name": "Ricardo Shousha"
    },
    {
      "name": "Jalal Butt"
    },
    {
      "name": "Azarakhsh Jalalvand"
    },
    {
      "name": "Egemen Kolemen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ba9fgbkxfj1y8.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.32264",
  "fulltext_url": null,
  "id": "ba9fgbkxfj1y8",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.32264",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "physics.plasm-ph"
    ],
    [
      "openalex",
      "3106|Magnetic confinement fusion research"
    ]
  ],
  "openalex": "W7223652122",
  "pdf_url": "https://arxiv.org/pdf/2610.32264",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ba9fgbkxfj1y8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:15Z",
      "native_id": "2610.32264",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.32264"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.plasm-ph",
      "subfield": "plasma"
    }
  ],
  "title": "Tokamak-SI: Interpreting Tokamak Discharges with Labeled Catalogs",
  "title_text": "Tokamak-SI: Interpreting Tokamak Discharges with Labeled Catalogs",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:15Z",
  "url": "https://research.draconitic.com/paper/ba9fgbkxfj1y8",
  "venue": "arXiv",
  "versions": []
}