PreprintCC BY 4.0arXiv
Collider event distances from the phase space sphere
Abstract
Can the distribution of collider events in phase space be used to distinguish the processes that produced them? We present a distance-based classification method that uses the global topology of Lorentz-invariant phase space and retains reconstructed masses. To tackle particularly challenging classification tasks that may benefit from higher event resolution, we develop a polynomial-time approximation to compute the distances. The resulting classifiers achieve strong discrimination across several simulated benchmarks, including fully hadronic four-top production against tt̅+jets.
Related
- Scaling Collider Event Generation with Residual-Quantized Tokens
- A Unified Geometric Framework for Understanding Collider Event Manifolds
- GUT-induced collider signatures of the LUX-ZEPLIN event
- Full-event anomaly detection for new physics searches at the Electron-Ion Collider
- The LHC is not enough: the LZ High-Recoil Event at FCC-hh and a Muon Collider
BibTeX
@misc{craig2026collider,
title = {{Collider event distances from the phase space sphere}},
author = {Nathaniel Craig and Brian Henning and Andrew J. Larkoski and Iñigo Valenzuela Lombera},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.24319},
eprint = {2610.24319},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.24319},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Collider event distances from the phase space sphere
AU - Nathaniel Craig
AU - Brian Henning
AU - Andrew J. Larkoski
AU - Iñigo Valenzuela Lombera
PY - 2026
DA - 2026/10/16
PB - arXiv
DO - 10.48550/arxiv.2610.24319
UR - https://arxiv.org/abs/2610.24319
AB - Can the distribution of collider events in phase space be used to distinguish the processes that produced them? We present a distance-based classification method that uses the global topology of Lorentz-invariant phase space and retains reconstructed masses. To tackle particularly challenging classification tasks that may benefit from higher event resolution, we develop a polynomial-time approximation to compute the distances. The resulting classifiers achieve strong discrimination across several simulated benchmarks, including fully hadronic four-top production against tt̅+jets.
ER -