%0 Electronic Article
%A Blekman, Freya
%A Canelli, Florencia
%A De Moor, Alexandre
%A Gautam, Kunal
%A Ilg, Armin
%A Macchiolo, Anna
%A Ploerer, Eduardo
%T Tagging more quark jet flavours at FCC-ee at 91 GeV with a transformer-based neural network
%N arXiv:2406.08590
%M PUBDB-2024-07333
%M arXiv:2406.08590
%M DESY-24-086
%D 2024
%Z Version submitted to the European Physical Journal C
%X Jet flavour tagging is crucial in experimental high-energy physics. A tagging algorithm, DeepJetTransformer, is presented, which exploits a transformer-based neural network that is substantially faster to train. The DeepJetTransformer network uses information from particle flow-style objects and secondary vertex reconstruction as is standard for b- and c-jet identification supplemented by additional information, such as reconstructed V<sup>0</sup>s and K<sup>±</sup>/π<sup>±</sup> discrimination, typically not included in tagging algorithms at the LHC. 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 impact of including V<sup>0</sup>s and K<sup>±</sup>/π<sup>±</sup> discrimination is presented. The network is applied on exclusive Z → q―q samples to examine the physics potential and is shown to isolate Z → s―s events. Assuming all other backgrounds can be efficiently rejected, a 5σ discovery significance for Z → s―s can be achieved with an integrated luminosity of 60 \textnb<sup>−1</sup>, corresponding to less than a second of the FCC-ee run plan at the Z resonance.
%F PUB:(DE-HGF)25
%9 Preprint
%R 10.3204/PUBDB-2024-07333
%U https://bib-pubdb1.desy.de/record/619033