{
  "abstract": "Experimental High Energy Physics (HEP) has adopted the transformer architecture for identification of jets, particularly the state-of-the-art Particle Transformer (ParT) which injects explicit information about particle correlations into the attention mechanism. While able to achieve state-of-the-art results in accuracy, interpretability to its effectiveness has been limited. In this paper we propose component attribution methods using Kolmogorov-Arnold Networks (KANs) that directly tie back to the physical descriptors of jets, to probe whether mechanisms such as Multi-Head Attention (MHA), or the ParT architecture, are able to learn these as discriminating features.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.08656",
  "author_total": 5,
  "authors": [
    {
      "name": "Lauri Laatu"
    },
    {
      "name": "Aritra Bal"
    },
    {
      "name": "Benedikt Maier"
    },
    {
      "name": "Markus Klute"
    },
    {
      "name": "Michael Spannowsky"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9vspkyrscd9rd.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.08656",
  "fulltext_url": null,
  "id": "9vspkyrscd9rd",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.08656",
  "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.LG"
    ],
    [
      "arxiv",
      "hep-ex"
    ],
    [
      "arxiv",
      "hep-ph"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.08656",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9vspkyrscd9rd.ris",
  "sources": [
    {
      "first_seen": "2026-11-10T06:21:04Z",
      "native_id": "2611.08656",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.08656"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:hep-ex",
      "subfield": "high-energy"
    }
  ],
  "title": "Higher Order Component Attribution via Learned Surrogates in High Energy Physics",
  "title_text": "Higher Order Component Attribution via Learned Surrogates in High Energy Physics",
  "type": "preprint",
  "updated_at": "2026-11-10T06:21:04Z",
  "url": "https://research.draconitic.com/paper/9vspkyrscd9rd",
  "venue": "arXiv",
  "versions": []
}