Abstract
Jet flavour tagging is crucial in experimental high-energy physics. A tagging algorithm, \texttt{DeepJetTransformer}, is presented, which exploits a transformer-based neural network that is substantially faster to train than state-of-the-art graph neural networks.
The \texttt{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 $Z \to q\bar{q}$ samples to examine the physics potential and is shown to isolate $Z \to s\bar{s}$ events. Assuming all non-$Z \to q\bar{q}$ backgrounds can be efficiently rejected, a $5\sigma$ discovery significance for $Z \to s\bar{s}$ can be achieved with an integrated luminosity of $60~\text{nb}^{-1}$ of $e^{+}e^{-}$ collisions at $\sqrt{s}=91.2~\mathrm{GeV}$, corresponding to less than a second of the FCC-ee run plan at the $Z$ boson resonance.
The \texttt{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 $Z \to q\bar{q}$ samples to examine the physics potential and is shown to isolate $Z \to s\bar{s}$ events. Assuming all non-$Z \to q\bar{q}$ backgrounds can be efficiently rejected, a $5\sigma$ discovery significance for $Z \to s\bar{s}$ can be achieved with an integrated luminosity of $60~\text{nb}^{-1}$ of $e^{+}e^{-}$ collisions at $\sqrt{s}=91.2~\mathrm{GeV}$, corresponding to less than a second of the FCC-ee run plan at the $Z$ boson resonance.
| Original language | English |
|---|---|
| Article number | 165 |
| Number of pages | 24 |
| Journal | European Physical Journal C - Particles & Fields |
| Volume | 85 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - 10 Feb 2025 |
Bibliographical note
Funding Information:We want to thank our CMS colleagues at the IIHE in Brussels, especially A.R. Sahasransu and Lode Vanhecke for their preparatory work, and Emil Bols for valuable discussions regarding DeepJetTransformer . We would also like to thank Kyle Cormier at the UZH for helpful discussions regarding the feature importance studies. We are grateful to Frank Gaede, Loukas Gouskos, and Michele Selvaggi for their feedback on the manuscript. This project is supported by the European Union\u2019s Horizon 2020 research and innovation programme under grant agreement No 951754. Kunal Gautam and Eduardo Ploerer are supported by FWO (Belgium, Grant no. G0E2221N) and SNF (Switzerland, Grant no. 200021L). Freya Blekman acknowledges support from DESY (Hamburg, Germany), a member of the Helmholtz Association HGF, and support by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany\u2019s Excellence Strategy\u2014EXC 2121 \u201CQuantum Universe\u201D\u2014390833306. Armin Ilg is supported by SNF in Switzerland. Funding was supported by Schweizerischer Nationalfonds zur F\u00F6rderung der Wissenschaftlichen Forschung (200021L), Fonds Wetenschappelijk Onderzoek (Grant no. G0E2221N).
Publisher Copyright:
© The Author(s) 2025.