Weakly supervised anomaly detection with event-level variables

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Brennan, Liam, Vami, Tamas Almos, Amram, Oz, Sekhar, Sanjana, Takahashi, Yuta, Moureaux, Louis, Sommerhalder, Manuel, Maksimovic, Petar, Cai, Tianji, Craig, Nathaniel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915598053670912
author Brennan, Liam
Vami, Tamas Almos
Amram, Oz
Sekhar, Sanjana
Takahashi, Yuta
Moureaux, Louis
Sommerhalder, Manuel
Maksimovic, Petar
Cai, Tianji
Craig, Nathaniel
author_facet Brennan, Liam
Vami, Tamas Almos
Amram, Oz
Sekhar, Sanjana
Takahashi, Yuta
Moureaux, Louis
Sommerhalder, Manuel
Maksimovic, Petar
Cai, Tianji
Craig, Nathaniel
contents We introduce a new topology for weakly supervised anomaly detection searches, di-object plus~X. In this topology, one looks for a resonance decaying to two standard model particles produced in association with other anomalous event activity (X). This additional activity is used for classification. We demonstrate how anomaly detection techniques which have been developed for di-jet searches focusing on jet substructure anomalies can be applied to event-level anomaly detection in this topology. To robustly capture event-level features of multi-particle kinematics, we employ new physically motivated variables derived from the geometric structure of a collision's phase space manifold. As a proof of concept, we explore the application of this approach to several benchmark signals in the di-$τ$ and di-$μ$ plus~X final states. We demonstrate that our anomaly detection approach can reach discovery-level significances for signals that would be missed in a conventional bump-hunt approach.
format Preprint
id arxiv_https___arxiv_org_abs_2504_13249
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Weakly supervised anomaly detection with event-level variables
Brennan, Liam
Vami, Tamas Almos
Amram, Oz
Sekhar, Sanjana
Takahashi, Yuta
Moureaux, Louis
Sommerhalder, Manuel
Maksimovic, Petar
Cai, Tianji
Craig, Nathaniel
High Energy Physics - Phenomenology
High Energy Physics - Experiment
We introduce a new topology for weakly supervised anomaly detection searches, di-object plus~X. In this topology, one looks for a resonance decaying to two standard model particles produced in association with other anomalous event activity (X). This additional activity is used for classification. We demonstrate how anomaly detection techniques which have been developed for di-jet searches focusing on jet substructure anomalies can be applied to event-level anomaly detection in this topology. To robustly capture event-level features of multi-particle kinematics, we employ new physically motivated variables derived from the geometric structure of a collision's phase space manifold. As a proof of concept, we explore the application of this approach to several benchmark signals in the di-$τ$ and di-$μ$ plus~X final states. We demonstrate that our anomaly detection approach can reach discovery-level significances for signals that would be missed in a conventional bump-hunt approach.
title Weakly supervised anomaly detection with event-level variables
topic High Energy Physics - Phenomenology
High Energy Physics - Experiment
url https://arxiv.org/abs/2504.13249