Separating charm and bottom decay electrons with point-cloud deep learning on the charged-hadron environment
Abstract
Electrons from semi-leptonic decays of charm (D) and bottom (B) hadrons are important probes in high-energy collisions, while their separation remains challenging due to the similarity of the underlying decay topologies. In this work, the charged-hadron environment associated with each electron is represented as an unordered point cloud and combined with the electron kinematics and charge. Several set-based machine learning architectures, including DeepSets, Transformer, and graph neural networks, are used to distinguish electrons from prompt D and direct B decays without explicit vertex observables. The three architectures achieve comparable performance. Moreover, the Transformer is found to perform better than a boosted decision tree trained on physics-motivated high-level observables. At an efficiency of about 40\%, the classifier reaches a purity level close to 80\% on the test sample. The classifier response is strongly related to the geometric and topological properties of the charged-hadron environment. The information learned by the classifier is further studied using non-prompt D electrons and charged hadrons from different angular regions. Our results indicate that the learned separation is driven mainly by the later stages of the decay chain rather than by initial production effects. The angular-region study further shows that useful discriminating information extends beyond the near- and away-side cones. This method is also evaluated for mid-rapidity proton--proton collisions at both RHIC and LHC energies.
Related
- General solution of the Dirac equation for electrons bound by a charged atomic chain
- Quantized Hyperfine Field at an Implanted μ+ Site in PrPb3: Interplay between Localized f Electrons and an Interstitial Charged Particle
- Bottom-up open EFT for non-Abelian gauge theory with dynamical color environment
- Search for charged Higgs bosons decaying into top and bottom quarks in lepton+jets final states in proton-proton collisions at √s=13 TeV
- Separating active irradiation from passive outcome learning in radiotherapy: a finite-model computational benchmark
BibTeX
@misc{zhang2026separating,
title = {{Separating charm and bottom decay electrons with point-cloud deep learning on the charged-hadron environment}},
author = {Jingyu Zhang and Wanbing He and Long Ma},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2607.02225},
eprint = {2607.02225},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.02225},
}
RIS
TY - UNPB
TI - Separating charm and bottom decay electrons with point-cloud deep learning on the charged-hadron environment
AU - Jingyu Zhang
AU - Wanbing He
AU - Long Ma
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2607.02225
UR - https://arxiv.org/abs/2607.02225
AB - Electrons from semi-leptonic decays of charm (D) and bottom (B) hadrons are important probes in high-energy collisions, while their separation remains challenging due to the similarity of the underlying decay topologies. In this work, the charged-hadron environment associated with each electron is represented as an unordered point cloud and combined with the electron kinematics and charge. Several set-based machine learning architectures, including DeepSets, Transformer, and graph neural networks, are used to distinguish electrons from prompt D and direct B decays without explicit vertex observables. The three architectures achieve comparable performance. Moreover, the Transformer is found to perform better than a boosted decision tree trained on physics-motivated high-level observables. At an efficiency of about 40\%, the classifier reaches a purity level close to 80\% on the test sample. The classifier response is strongly related to the geometric and topological properties of the charged-hadron environment. The information learned by the classifier is further studied using non-prompt D electrons and charged hadrons from different angular regions. Our results indicate that the learned separation is driven mainly by the later stages of the decay chain rather than by initial production effects. The angular-region study further shows that useful discriminating information extends beyond the near- and away-side cones. This method is also evaluated for mid-rapidity proton--proton collisions at both RHIC and LHC energies.
ER -