A survey on generative AI for detector effects unfolding in particle and nuclear physics

Authors:
  • TATareq Alghamdi
    Tareq Alghamdi
  • TVTommaso Vittorini
    Tommaso Vittorini
  • JXJitao Xu
    Jitao Xu
  • MBMarco Battaglieri
    Marco Battaglieri
  • DGDerek I. Glazier
    Derek I. Glazier
  • GMGlòria Montaña
    Glòria Montaña
  • GFGiorgio Foti
    Giorgio Foti
  • APAlessandro Pilloni
    Alessandro Pilloni
  • NSNobuo Sato
    Nobuo Sato
  • IGI-16146 Genova Infn Sezione di Genova
    I-16146 Genova Infn Sezione di Genova
  • NFNewport News Thomas Jefferson National Accelerator Facility
    Newport News Thomas Jefferson National Accelerator Facility

Abstract
In particle and nuclear physics, “detector effects unfolding” can be viewed as a highdimensional inverse problem whose goal is to recover the true event distributions from observed experimental data corrupted by detector-induced distortions. Recent advances in generative AI have positioned data-driven and machine learning-based approaches as powerful alternatives to traditional unfolding techniques, offering superior scalability to high-dimensional data, capability of learning complex detector responses, and the ability to operate directly at the event level. We survey state-ofthe-art generative AI-based models for detector folding and unfolding. We review existing architectures and training strategies, and highlight recent methodological advances and open challenges. Through a detailed discussion of latent space representations, uncertainty quantification, physics insights, and background removals, we demonstrate the potential to significantly advance the field.

This publication has 42 references indexed in Scilit: