Application of Particle Transformer to quark flavor tagging in the ILC project

Abstract

International Linear Collider (ILC) is a next-generation $e^+e^-$ linear collider to explore Beyond-Standard-Models by precise measurements of Higgs bosons. Jet flavor tagging plays a vital role in the ILC project by identification of $H\to b\bar{b},\,c\bar{c},\,g\bar{g},\,s\bar{s}$ to measure Higgs coupling constants and of $HH\to b\bar{b}b\bar{b}$ and $b\bar{b}WW$ which are the main channels to measure the Higgs self-coupling constant. Jet flavor tagging relies on a large amount of jet information such as particle momenta, energies, and impact parameters, obtained from trajectories of particles within a jet. Since jet flavor tagging is a classification task based on massive amounts of information, machine learning techniques have been utilized for faster and more efficient analysis for the last several decades. Particle Transformer (ParT) is a machine learning model based on Transformer architecture developed for jet analysis, including jet flavor tagging. In this study, we apply ParT to ILD full simulation data to improve the efficiency of jet flavor tagging. Our research focused on evaluating the performance of ParT compared to that of the previously used flavor tagging software, LCFIPlus. We will also report the status of the performance of strange tagging on ILD full simulation dataset using ParT, which can be applied to the analysis of Higgs-strange coupling.