Comprehensive reconstruction of collider events with hypergraph representation learning and graph-conditioned diffusion
Abstract
In particle collider experiments, event reconstruction is the task of inferring the kinematics of short-lived particles produced in the hard scatter from the stable final states recorded by detectors. We decompose event reconstruction into two primary tasks: assigning measured jets and charged leptons to parent particles, and predicting unmeasured neutrino kinematics. We present VyPER, a novel geometric learning framework that represents collider events as hypergraphs with a physics-inspired topology. VyPER combines the supervised classification of hyperedges for particle assignment with a diffusion model for predicting neutrino kinematics, leveraging a joint loss function to optimize both reconstruction tasks within a unified framework. We showcase VyPER across several proton-proton collision processes, comparing its performance to existing analytical and machine-learning-based reconstruction techniques. In doing so, we demonstrate that accurate event reconstruction is achievable across a diverse range of Standard Model physics processes, opening new avenues for precision measurements in the Higgs boson, electroweak, and top-quark sectors.
Related
- Image-Domain CT Metal Artifact Reduction Using an Endpoint-Conditioned Diffusion Bridge
- Nodal obstruction to conditioned-diffusion representations of the weak momentum
- On the use of the Belopol'skaya-Daletskii representation of a diffusion on a Riemann manifold to construct path integrals
- Representation Transitions Reveal Predictive Structure in Complex Systems: A Trajectory-Level Reconstruction in a Critical System
- From data to structure: Construction, breakdown, and reconstruction of an empirical representation in a black-box RC circuit
BibTeX
@misc{mao2026comprehensive,
title = {{Comprehensive reconstruction of collider events with hypergraph representation learning and graph-conditioned diffusion}},
author = {Lining Mao and Yvonne Peters and Ethan Simpson and Zihan Zhang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.18928},
eprint = {2609.18928},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.18928},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Comprehensive reconstruction of collider events with hypergraph representation learning and graph-conditioned diffusion
AU - Lining Mao
AU - Yvonne Peters
AU - Ethan Simpson
AU - Zihan Zhang
PY - 2026
DA - 2026/09/16
PB - arXiv
DO - 10.48550/arxiv.2609.18928
UR - https://arxiv.org/abs/2609.18928
AB - In particle collider experiments, event reconstruction is the task of inferring the kinematics of short-lived particles produced in the hard scatter from the stable final states recorded by detectors. We decompose event reconstruction into two primary tasks: assigning measured jets and charged leptons to parent particles, and predicting unmeasured neutrino kinematics. We present VyPER, a novel geometric learning framework that represents collider events as hypergraphs with a physics-inspired topology. VyPER combines the supervised classification of hyperedges for particle assignment with a diffusion model for predicting neutrino kinematics, leveraging a joint loss function to optimize both reconstruction tasks within a unified framework. We showcase VyPER across several proton-proton collision processes, comparing its performance to existing analytical and machine-learning-based reconstruction techniques. In doing so, we demonstrate that accurate event reconstruction is achievable across a diverse range of Standard Model physics processes, opening new avenues for precision measurements in the Higgs boson, electroweak, and top-quark sectors.
ER -