Description
We present a new algorithm for tagging the production flavour of neutral $B^0$ and $B_s^0$ mesons in proton-proton collisions. It is based on a deep neural network, DeepSets, and exploits a comprehensive set of tracks associated with the hadronization process. The algorithm is calibrated on data collected by the LHCb experiment at a centre-of-mass energy of 13 TeV. This inclusive approach enhances the flavour tagging performance beyond the established same-side and opposite-side tagging methods.The gains in tagging power offer significant benefits for precision measurements of $CP$ violation and mixing in the neutral $B$ meson systems.
| Secondary track | T07 - Flavour Physics and CP Violation |
|---|
