Semi-leptonic t¯t Calibration of ATLAS GN2X Flavor-Tagging Algorithm

Identifying the origin of jets to their corresponding quarks is a critical part of the physics program of the ATLAS experiment at the Large Hadron Collider. GN2X is an implementation of a transformer neural network that identifies large-radius jets originating from boosted Higgs bosons decaying to b¯b and c¯c pairs. Using proton-proton collision data collected at a center-of-mass energy of √s = 13 TeV, the tagger is evaluated on semi-leptonic t¯t events that provide a background of non-b¯b large-radius jets.