Jet Tagging

Jet tagging is a crucial task in high-energy physics, aiming to classify collimated sprays of particles (jets) originating from different sources, such as quarks or gluons, to identify new physics beyond the Standard Model. Recent research heavily utilizes deep learning, employing various architectures including graph neural networks (GNNs) like ParticleNet and novel transformer-based models, to improve the accuracy and efficiency of jet classification. These advancements are vital for enhancing the sensitivity of analyses at the Large Hadron Collider and other particle accelerators, enabling more precise measurements and potentially revealing new particles or interactions.