Speaker
Description
The spectrum of hadrons consists of bound states of quarks and gluons, whose dynamics are governed by Quantum Chromodynamics (QCD). A distinctive feature of strong interactions is confinement, which prevents quarks and gluons from appearing as free particles, and uncovering its underlying mechanisms remains a central goal of hadron physics. A new generation of dedicated experiments is pursuing this goal, several already in operation and more planned at world-leading laboratories, producing petabyte-scale datasets that probe the structure of visible matter at the femtometer scale. Fully exploiting and preserving this information increasingly relies on AI-driven strategies for data analysis and modeling. In this contribution, I will present the hadron spectroscopy program at Jefferson Lab with the CLAS and CLAS12 detectors, highlighting key results on meson and baryon resonances alongside progress in developing Machine-Learning-based Physics Event Generators (MLEGs), built on Generative Adversarial Networks and Diffusion Models trained directly on scattering data. These tools aim to reproduce reaction dynamics, unfold detector effects to recover truth-level distributions, and enable model-independent analyses of elementary scattering processes, supported by a rigorous uncertainty-quantification framework. Developed within an international collaboration of experimentalists, theorists, and computer scientists, this approach has been validated in inclusive and semi-inclusive deep-inelastic electron–proton scattering and in exclusive hadron photoproduction, with direct relevance to ongoing CLAS12 spectroscopy analyses.