From strange-quark tagging to fragmentation tagging with machine learning

TL;DR

This paper explores machine learning methods, including Graph Attention Networks and Particle Transformers, to improve jet classification at the LHC, focusing on strange-quark tagging and fragmentation channel identification.

Contribution

It introduces the application of advanced neural network architectures to challenging jet classification problems, demonstrating significant improvements in bottom baryon versus meson tagging.

Findings

Sophisticated architectures improve bottom baryon vs. meson discrimination.

No significant gain in strange-quark vs. down-quark tagging from complex models.

Graph Attention Networks and Particle Transformers outperform simple MLPs in certain tasks.

Abstract

We apply advanced machine learning techniques to two challenging jet classification problems at the LHC. The first is strange-quark tagging, in particular distinguishing strange-quark jets from down-quark jets. The second, which we term fragmentation tagging, involves identifying the fragmentation channel of a quark. We exemplify the latter by training neural networks to differentiate between bottom jets containing a bottom baryon and those containing a bottom meson. The common challenge in these two problems is that neither quark lifetimes and masses nor parton showering provide discriminating tools, making it necessary to rely on differences in the distributions of the hadron types contained in each type of jet and their kinematics. For these classification tasks, we employ variations of Graph Attention Networks and the Particle Transformer, which receive jet and all constituent properties as inputs. We compare their performance to a simple Multilayer Perceptron that uses simple variables. We find that the more sophisticated architectures do not improve $s$-quark versus $d$-quark jet differentiation by a significant amount, but they do lead to a significant gain in $b$-baryon versus $b$-meson jet differentiation.