E-PCN: Jet Tagging with Explainable Particle Chebyshev Networks Using Kinematic Features
The paper introduces E-PCN, an explainable graph neural network that integrates four distinct kinematic feature-weighted graph representations to achieve state-of-the-art jet classification performance on the JetClass dataset while identifying angular separation and transverse momentum as the dominant factors driving its decisions.
Md Raqibul Islam, Adrita Khan, Mir Sazzat Hossain, Choudhury Ben Yamin Siddiqui, Md. Zakir Hossan, Tanjib Khan, M. Arshad Momen, Amin Ahsan Ali, AKM Mahbubur Rahman2026-05-05⚛️ hep-ex