Performance of the mass-decorrelated DeepDoubleX classifier for double-b and double-c large-radius jets with the CMS detector

For many searches for new physics at the LHC, it is important to distinguish jets that originate from the merged decay products of resonances produced with high transverse momentum from jets that originate from single partons. We present a neural network model, called DeepDoubleX, that is trained to distinguish the double-b and double-c decay modes of such resonances from light flavour jets, as well as distinguish between the two. The classifier is applicable to any resonance, such as H $\to$ bb or H $\to$ cc, in the mass range from 20 GeV to 200 GeV and with high enough energy for its decay products to be clustered in a single jet within a cone of size R=0.8. The performance of this classifier in simulation is the focus of this Detector Performance Summary.