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-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 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-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 misassociation of decay products can result in vertices with artificially large measured lifetimes. This paper presents two approaches to mitigate correlations between NN scores and candidate lifetimes at large lifetime, and evaluates the performance of the resulting models.
Related
- Density-Selected Topological Pathways in the Melting of Single-Particle-Thick Stripes
- Long-lived quasinormal modes, shadows and particle motion in four-dimensional quasi-topological gravity
- Entanglement from particle number fluctuations in a second-order topological insulator
- A geometric resolution limit from vacuum entanglement: Topological Structure and Particle-Wave Asymmetry
- Node role discovery reveals novel structural decompositions and topological shifts in complex networks
BibTeX
@misc{albrecht2026decorrelation,
title = {{Decorrelation of neural networks from particle lifetimes in the LHCb topological $b$ trigger}},
author = {Johannes Albrecht and Alessandro Bertolin and James Connaughton and Jonathan Davies and Blaise Delaney and Agnieszka Dziurda and Conor Fitzpatrick and Maciej Giza and Vava V. Gligorov and James A. Gooding and Nicole Schulte and Nicole Skidmore and Mika Vesterinen and Mike Williams and Shunan Zhang and Valeriia Zhovkovska},
howpublished = {arXiv},
year = {2026},
month = jul,
doi = {10.48550/arxiv.2607.22281},
eprint = {2607.22281},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.22281},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Decorrelation of neural networks from particle lifetimes in the LHCb topological b trigger
AU - Johannes Albrecht
AU - Alessandro Bertolin
AU - James Connaughton
AU - Jonathan Davies
AU - Blaise Delaney
AU - Agnieszka Dziurda
AU - Conor Fitzpatrick
AU - Maciej Giza
AU - Vava V. Gligorov
AU - James A. Gooding
AU - Nicole Schulte
AU - Nicole Skidmore
AU - Mika Vesterinen
AU - Mike Williams
AU - Shunan Zhang
AU - Valeriia Zhovkovska
PY - 2026
DA - 2026/07/24
PB - arXiv
DO - 10.48550/arxiv.2607.22281
UR - https://arxiv.org/abs/2607.22281
AB - The LHCb topological beauty trigger is the primary set of algorithms for selecting collision events containing 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 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-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 misassociation of decay products can result in vertices with artificially large measured lifetimes. This paper presents two approaches to mitigate correlations between NN scores and candidate lifetimes at large lifetime, and evaluates the performance of the resulting models.
ER -