Tagging more quark jet flavours at FCC-ee at 91 GeV with a transformer-based neural network

Jet flavour tagging is crucial in experimental high-energy physics. A tagging algorithm, DeepJet- Transformer, is presented, which exploits a transformer-based neural network that is substantially faster to train than state-of-the-art graph neural networks. The DeepJetTransformer algorithm uses information from particle flow-style objects and secondary vertex reconstruction for b- and c-jet identification, supplemented by additional information that is not always included in tagging algorithms at the LHC, such as reconstructed $$ and $$ and $$ discrimination. The model is trained as a multiclassifier to identify all quark flavours separately and performs excellently in identifying b- and c-jets. An s-tagging efficiency of $$ can be achieved with a $$ ud-jet background efficiency. The performance improvement achieved by including $$ and $$ reconstruction and $$ discrimination is presented. The algorithm is applied on exclusive $$ samples to examine the physics potential and is shown to isolate $$ events. Assuming all non- $$ backgrounds can be efficiently rejected, a $$ discovery significance for $$ can be achieved with an integrated luminosity of $$ of $$ collisions at $$ , corresponding to less than a second of the FCC-ee run plan at the Z boson resonance.