Decorrelation of neural networks from particle lifetimes in the LHCb topological b trigger

Abstract The LHCb topological beauty trigger is the primary set of algorithms for selecting collision events containing $$b $$ b -hadrons in the fully software-based LHCb trigger. The algorithms apply monotonic Lipschitz neural networks (NNs) to select vertices of charged particles consistent with the distinct topology of a $$b $$ b decay, i.e. , those with large lifetimes and transverse momentum. Many analyses of the events recorded require that the selection must be unbiased with respect to the $$b $$ b -hadron lifetime at large lifetimes. Accurate reconstruction is challenging in busier detector environments, in which several visible proton–proton collisions occur simultaneously per bunch crossing, such that mis-association of decay products can result in vertices with artificially large measured lifetimes. This paper presents and evaluates two approaches to mitigate correlations between NN scores and candidate lifetimes at large lifetime: distance correlation and moment decomposition. Both methods are found to mitigate lifetime biases at large lifetimes, with moment decomposition achieving more effective decorrelation.

Authors

Institutions

Publication Details

Journal
The European Physical Journal C
Published
2026-11-17
DOI
https://doi.org/10.1140/epjc/s10052-026-16561-8
Primary Topic
Particle physics theoretical and experimental studies
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Decorrelation of neural networks from particle lifetimes in the LHCb topological b trigger

Joe Davies, M. A. Giza, James Connaughton, J Albrecht et al.
The European Physical Journal C
Particle physics theoretical and experimental studies
article

Decorrelation of neural networks from particle lifetimes in the LHCb topological b trigger

Joe Davies, M. A. Giza, James Connaughton, J Albrecht, N Skidmore, V V Gligorov, Mike Williams, James A. Gooding, Shunan Zhang, Conor Fitzpatrick, Nicole Schulte, Blaise Delaney, Mika Vesterinen, Alessandro Bertolin, Agnieszka Dziurda, Valeriia Zhovkovska
article en

Abstract

Abstract The LHCb topological beauty trigger is the primary set of algorithms for selecting collision events containing $$b $$ b -hadrons in the fully software-based LHCb trigger. The algorithms apply monotonic Lipschitz neural networks (NNs) to select vertices of charged particles consistent with the distinct topology of a $$b $$ b decay, i.e. , those with large lifetimes and transverse momentum. Many analyses of the events recorded require that the selection must be unbiased with respect to the $$b $$ b -hadron lifetime at large lifetimes. Accurate reconstruction is challenging in busier detector environments, in which several visible proton–proton collisions occur simultaneously per bunch crossing, such that mis-association of decay products can result in vertices with artificially large measured lifetimes. This paper presents and evaluates two approaches to mitigate correlations between NN scores and candidate lifetimes at large lifetime: distance correlation and moment decomposition. Both methods are found to mitigate lifetime biases at large lifetimes, with moment decomposition achieving more effective decorrelation.

The European Physical Journal CVol. 86(11)
Centre National de la Recherche Scientifique (FR), TU Dortmund University (DE), University of Manchester (GB), Department for Work and Pensions (GB), University of Warwick (GB), Sorbonne Université (FR), University of Oxford (GB), Istituto Nazionale di Fisica Nucleare, Sezione di Padova (IT), Institute of Nuclear Physics, Polish Academy of Sciences (PL), Institut National de Physique Nucléaire et de Physique des Particules (FR), The NSF AI Institute for Artificial Intelligence and Fundamental Interactions (US), Massachusetts Institute of Technology (US), European Organization for Nuclear Research (CH)
National Science Foundation, European Commission, Deutsche Forschungsgemeinschaft, Bundesministerium für Bildung und Forschung, Ministerstwo Edukacji i Nauki, Horizon 2020 Framework Programme
Particle physics theoretical and experimental studies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon