ParticleNet and its application on CEPC jet flavor tagging

Abstract

AbstractQuarks (except top quarks) and gluons produced in collider experiments hadronize and fragment into sprays of stable particles, called jets. Identification of quark flavor is desired for collider experiments in high-energy physics, relying on flavor tagging algorithms. In this study, using a full simulation of the Circular Electron Positron Collider (CEPC), we investigate the flavor tagging performance of two different algorithms: ParticleNet, based on a Graph Neural Network, and LCFIPlus, based on the Gradient Booted Decision Tree. Compared to LCFIPlus, ParticleNet significantly enhances flavor tagging performance, resulting in a significant improvement in benchmark measurement accuracy, i.e., a 36% improvement for $$\sigma (ZH)\cdot Br(Z\rightarrow \nu \bar{\nu }, H\rightarrow c\bar{c})$$ σ ( Z H ) · B r ( Z → ν ν ¯ , H → c c ¯ ) measurement and a 75% improvement for $$|V_{cb}|$$ | V cb | measurement via W boson decay, respectively, when the CEPC operates as a Higgs factory at the center-of-mass energy of 240 GeV and collects an integrated luminosity of 5.6 ab$$^{-1}$$ - 1 . We compare the performance of ParticleNet and LCFIPlus at different vertex detector configurations, observing that the inner radius is the most sensitive parameter, followed by material budget and spatial resolution.