cs.LGNov 5, 2026

Higher Order Component Attribution via Learned Surrogates in High Energy Physics

Authors: Lauri Laatu, Aritra Bal, Benedikt Maier, Markus Klute, Michael Spannowsky

Organizations: Imperial College London, United Kingdom · Institute for Theoretical Physics (ITP), Karlsruhe Institute of Technology, Germany · Institute for Quantum Materials and Technologies (IQMT), Karlsruhe Institute of Technology, Germany · Institute of Experimental Particle Physics (ETP), Karlsruhe Institute of Technology, Germany

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.

Figures & tables

Explore similar work

CardsList
  1. Dissecting Jet-Tagger Through Mechanistic Interpretability

    May 11, 2026Saurabh Rai, Sanmay GangulyTransformer InterpretabilityAttention Head Analysis

  2. This is SParTA: A modular, efficient and scalable transformer architecture for jet-tagging

    Oct 19, 2026Rajneil Baruah, Subhadeep Mondal, Sunando Kumar Patra +1TransformerJet Tagging

  3. Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging

    May 20, 2026Aaron Wang, Zihan Zhao, Alan Xia +5Jet TaggingHierarchical Attention