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

Abstract

Abstract Jet flavour tagging is crucial in experimental high-energy physics. A tagging algorithm, - , is presented, which exploits a transformer-based neural network that is substantially faster to train than state-of-the-art graph neural networks. The 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 $$K_{S}^{0}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msubsup> <mml:mi>K</mml:mi> <mml:mrow> <mml:mi>S</mml:mi> </mml:mrow> <mml:mn>0</mml:mn> </mml:msubsup> </mml:math> and $$\Lambda ^{0}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msup> <mml:mi>Λ</mml:mi> <mml:mn>0</mml:mn> </mml:msup> </mml:math> and $$K^{\pm }/\pi ^{\pm }$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:msup> <mml:mi>K</mml:mi> <mml:mo>±</mml:mo> </mml:msup> <mml:mo>/</mml:mo> <mml:msup> <mml:mi>π</mml:mi> <mml:mo>±</mml:mo> </mml:msup> </mml:mrow> </mml:math> 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 $$40\%$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mn>40</mml:mn> <mml:mo>%</mml:mo> </mml:mrow> </mml:math> can be achieved with a $$10\%$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mn>10</mml:mn> <mml:mo>%</mml:mo> </mml:mrow> </mml:math> ud -jet background efficiency. The performance improvement achieved by including $$K_{S}^{0}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msubsup> <mml:mi>K</mml:mi> <mml:mrow> <mml:mi>S</mml:mi> </mml:mrow> <mml:mn>0</mml:mn> </mml:msubsup> </mml:math> and $$\Lambda ^{0}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msup> <mml:mi>Λ</mml:mi> <mml:mn>0</mml:mn> </mml:msup> </mml:math> reconstruction and $$K^{\pm }/\pi ^{\pm }$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:msup> <mml:mi>K</mml:mi> <mml:mo>±</mml:mo> </mml:msup> <mml:mo>/</mml:mo> <mml:msup> <mml:mi>π</mml:mi> <mml:mo>±</mml:mo> </mml:msup> </mml:mrow> </mml:math> discrimination is presented. The algorithm is applied on exclusive $$Z \rightarrow q\bar{q}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>Z</mml:mi> <mml:mo>→</mml:mo> <mml:mi>q</mml:mi> <mml:mover> <mml:mrow> <mml:mi>q</mml:mi> </mml:mrow> <mml:mrow> <mml:mo>¯</mml:mo> </mml:mrow> </mml:mover> </mml:mrow> </mml:math> samples to examine the physics potential and is shown to isolate $$Z \rightarrow s\bar{s}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>Z</mml:mi> <mml:mo>→</mml:mo> <mml:mi>s</mml:mi> <mml:mover> <mml:mrow> <mml:mi>s</mml:mi> </mml:mrow> <mml:mrow> <mml:mo>¯</mml:mo> </mml:mrow> </mml:mover> </mml:mrow> </mml:math> events. Assuming all non- $$Z \rightarrow q\bar{q}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>Z</mml:mi> <mml:mo>→</mml:mo> <mml:mi>q</mml:mi> <mml:mover> <mml:mrow> <mml:mi>q</mml:mi> </mml:mrow> <mml:mrow> <mml:mo>¯</mml:mo> </mml:mrow> </mml:mover> </mml:mrow> </mml:math> backgrounds can be efficiently rejected, a $$5\sigma $$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mn>5</mml:mn> <mml:mi>σ</mml:mi>

Topics & Concepts