Jefferson Lab > CIO > IR
Privacy and Security Notice


Publication Information

Title Toward a generative modeling analysis of CLAS exclusive $2\pi$ photoproduction
Authors Tareq Alghamdi, Yasir Alanazi, Marco Battaglieri, Lukasz Bibrzycki, Andrey Golda, Astrid Hiller Blin, Evgeny Isupov, Y. Li, Luca Marsicano, Wolodymyr Melnitchouk, Viktor Mokeev, Gloria Montana-Faiget, Alessandro Pilloni, Nobuo Sato, Adam Szczepaniak, Tommaso Vittorini
JLAB number JLAB-THY-23-3881
LANL number (None)
Other number DOE/OR/23177-6632
Document Type(s) (Journal Article) 
Associated with EIC: No
Supported by Jefferson Lab LDRD Funding: No
Funding Source: Nuclear Physics (NP)
Other Funding:JLab LDRD19-13
JLab LDRD20-18

Compiled for Physical Review D
Volume 108
Page(s) 094030
Publication Abstract: AI-supported algorithms, particularly generative models, have been successfully used in a variety of different contexts. In this work, we demonstrate for the first time that generative adversarial networks (GANs) can be used in high-energy experimental physics to unfold detector effects from multi-particle final states, while preserving correlations between kinematic variables in multidimensional phase space. We perform a full closure test on two-pion photoproduction pseudodata generated with a realistic model in the kinematics of the Jefferson Lab CLAS g11 experiment. The overlap of different reaction mechanisms leading to the same final state associated with the CLAS detector's nontrivial effects represents an ideal test case for AI-supported analysis. Uncertainty quantification performed via bootstrap provides an estimate of the systematic uncertainty associated with the procedure. The test demonstrates that GANs can reproduce highly correlated multidifferential cross sections even in the presence of detector-induced distortions in the training datasets, and provides a solid basis for applying the framework to real experimental data.
Experiment Numbers:
Document: pdf
Accepted Manuscript: PhysRevD.108.094030.pdf
Supporting Documents:
Supporting Datasets: