Two-Stage Machine Learning Strategy for Scalar and Vector Leptoquark Discrimination at the LHC
Abstract
We present a machine learning framework for the characterization of leptoquark (LQ) signals at the Large Hadron Collider, focusing on the discrimination between scalar (SLQ) and vector (VLQ) hypotheses. The method is based on a two-stage inference pipeline that combines a classifier trained to separate Standard Model backgrounds from a mixed LQ signal with a second classifier designed to distinguish between SLQ and VLQ scenarios, using the signal yield inferred from the first-stage classifier to guide the corresponding scalar and vector mass hypotheses. A test statistic is constructed from the classifier outputs and interpreted using reference probability density functions. The approach is applied to realistic LHC final states with hadronically decaying tau leptons, multiple jets, and missing transverse momentum, and its performance is assessed using simulated pseudo-experiments. We show that the proposed strategy provides a robust and statistically consistent procedure to discriminate between SLQ and VLQ signals across a wide range of masses and signal stregths. We find that the spin identification power closely follows the discovery potential, demonstrating that determining the spin nature of a newly discovered LQ does not require substantially larger datasets than those needed for discovery itself.
Related
- A comparative study of variational quantum classifiers and classical machine learning for tW−tt̅ discrimination at the LHC
- Enhancing electromagnetic calorimeter signal reconstruction with machine learning-based noise discrimination
- Pulse-shape discrimination with machine learning for CZT detectors at the DAΦNE beam test facility
- Quantum Encoding Agents: A Natural Language Interface for Data Embedding Strategy Selection in Quantum Machine Learning
- Small-supercell and Small-dataset Training Strategy of Machine Learning Interatomic Potentials for Point Defects
BibTeX
@misc{arganda2026twostage,
title = {{Two-Stage Machine Learning Strategy for Scalar and Vector Leptoquark Discrimination at the LHC}},
author = {Ernesto Arganda and Martín de los Rios and Andres D. Perez and Rosa M. Sandá Seoane and Alejandro Szynkman},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.00270},
eprint = {2609.00270},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.00270},
}
RIS
TY - UNPB
TI - Two-Stage Machine Learning Strategy for Scalar and Vector Leptoquark Discrimination at the LHC
AU - Ernesto Arganda
AU - Martín de los Rios
AU - Andres D. Perez
AU - Rosa M. Sandá Seoane
AU - Alejandro Szynkman
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.00270
UR - https://arxiv.org/abs/2609.00270
AB - We present a machine learning framework for the characterization of leptoquark (LQ) signals at the Large Hadron Collider, focusing on the discrimination between scalar (SLQ) and vector (VLQ) hypotheses. The method is based on a two-stage inference pipeline that combines a classifier trained to separate Standard Model backgrounds from a mixed LQ signal with a second classifier designed to distinguish between SLQ and VLQ scenarios, using the signal yield inferred from the first-stage classifier to guide the corresponding scalar and vector mass hypotheses. A test statistic is constructed from the classifier outputs and interpreted using reference probability density functions. The approach is applied to realistic LHC final states with hadronically decaying tau leptons, multiple jets, and missing transverse momentum, and its performance is assessed using simulated pseudo-experiments. We show that the proposed strategy provides a robust and statistically consistent procedure to discriminate between SLQ and VLQ signals across a wide range of masses and signal stregths. We find that the spin identification power closely follows the discovery potential, demonstrating that determining the spin nature of a newly discovered LQ does not require substantially larger datasets than those needed for discovery itself.
ER -