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 \(K_{S}^{0}\) and \(\Lambda ^{0}\) and \(K^{\pm }/\pi ^{\pm }\) 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 \(40\%\) can be achieved with a \(10\%\) ud-jet background efficiency. The performance improvement achieved by including \(K_{S}^{0}\) and \(\Lambda ^{0}\) reconstruction and \(K^{\pm }/\pi ^{\pm }\) discrimination is presented. The algorithm is applied on exclusive \(Z \rightarrow q\bar{q}\) samples to examine the physics potential and is shown to isolate \(Z \rightarrow s\bar{s}\) events. Assuming all non-\(Z \rightarrow q\bar{q}\) backgrounds can be efficiently rejected, a \(5\sigma \) discovery significance for \(Z \rightarrow s\bar{s}\) can be achieved with an integrated luminosity of \(60~\text {nb}^{-1}\) of \(e^{+}e^{-}\) collisions at \(\sqrt{s}=91.2~\textrm{GeV}\), corresponding to less than a second of the FCC-ee run plan at the Z boson resonance.