Development and performance of a transformer-based lepton isolation algorithm with the ATLAS experiment
Abstract
The Prompt Lepton Isolation Tagger (PLIT) is a transformer-based algorithm designed to distinguish prompt leptons (electrons and muons) produced in the primary decays of electroweak gauge bosons from non-prompt leptons produced in hadron decays and from misidentified leptons. It is primarily used in measurements targeting multilepton final states with important backgrounds from non-prompt and misidentified leptons. PLIT exploits information from charged-particle tracks associated with the lepton candidate, together with lepton properties, using a transformer neural network to identify correlations between the tracks and improve the discrimination. Its performance is evaluated using simulated top-quark pair production events and compared with that of previously used lepton isolation algorithms, demonstrating improved prompt lepton efficiency while maintaining high rejection of non-prompt leptons. This article presents the development, performance, and calibration of PLIT for electrons and muons in proton--proton collisions at a centre-of-mass energy of √s=13.6 TeV recorded by the ATLAS experiment at the Large Hadron Collider. Operating points are defined for both electrons and muons, and their efficiencies are calibrated using Z→ l+l- events in Run 3 data, providing data-to-simulation correction factors for physics analyses.
Related
- Development and Commissioning of the Cryogenic Target Detectors for the Technical Run of the NUCLEUS Experiment
- Performance and Radiation Damage of the Heavy-Ion Silicon Beam Tracker in the BM@N Experiment
- Commissioning and Performance of the Time-of-Flight Detector for the T2K Neutrino Oscillation Experiment
- Equivalent linearization modeling and experimental validation of natural frequency and vibration isolation performance in metal braided hoses
- Comparison of spectral performance of three dual-energy CT scanners equipped with a deep-learning image reconstruction algorithm and one photon counting CT scanner: A phantom study
BibTeX
@misc{collaboration2026development,
title = {{Development and performance of a transformer-based lepton isolation algorithm with the ATLAS experiment}},
author = {ATLAS Collaboration},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.08194},
eprint = {2611.08194},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.08194},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Development and performance of a transformer-based lepton isolation algorithm with the ATLAS experiment
AU - ATLAS Collaboration
PY - 2026
DA - 2026/11/05
PB - arXiv
DO - 10.48550/arxiv.2611.08194
UR - https://arxiv.org/abs/2611.08194
AB - The Prompt Lepton Isolation Tagger (PLIT) is a transformer-based algorithm designed to distinguish prompt leptons (electrons and muons) produced in the primary decays of electroweak gauge bosons from non-prompt leptons produced in hadron decays and from misidentified leptons. It is primarily used in measurements targeting multilepton final states with important backgrounds from non-prompt and misidentified leptons. PLIT exploits information from charged-particle tracks associated with the lepton candidate, together with lepton properties, using a transformer neural network to identify correlations between the tracks and improve the discrimination. Its performance is evaluated using simulated top-quark pair production events and compared with that of previously used lepton isolation algorithms, demonstrating improved prompt lepton efficiency while maintaining high rejection of non-prompt leptons. This article presents the development, performance, and calibration of PLIT for electrons and muons in proton--proton collisions at a centre-of-mass energy of √s=13.6 TeV recorded by the ATLAS experiment at the Large Hadron Collider. Operating points are defined for both electrons and muons, and their efficiencies are calibrated using Z→ l^+l^- events in Run 3 data, providing data-to-simulation correction factors for physics analyses.
ER -