Initial measurements of Z-boson resonance parameters in e+e- annihilation

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 Λ 0 andK ± / π ± 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 Λ 0 reconstruction andK ± / π ± discrimination is presented. The algorithm is applied on exclusive Z → q q ¯ samples to examine the physics potential and is shown to isolate Z → s s ¯ events. Assuming all non- Z → q q ¯ backgrounds can be efficiently rejected, a 5 σ discovery significance for Z → s s ¯ can be achieved with an integrated luminosity of 60 nb - 1 ofe + e - collisions ats = 91.2 GeV , corresponding to less than a second of the FCC-ee run plan at the Z boson resonance.