Jet flavor tagging with particle transformer for Higgs factories

We study the performance of the Particle Transformer (ParT) for jet flavor tagging using ILD full-simulation events (1 M jets) as well as fast simulation samples (10 M and 1 M jets). We perform 3-category ( b / c / d ), 6-category ( b / c / d / u / s / g ), and 11-category trainings (including quark–antiquark separation), incorporating multivariate hadron particle identification information from dE/dx d E / d x and time-of-flight. For b / c tagging, we observe a factor of 5–10 times better rejection of different flavors at the same efficiency over previous BDT-based taggers, and we obtain reasonable performance for strange tagging and quark/antiquark separation. The 10 M-jet fast simulation study indicates that further gains are possible with higher training statistics.