DOE OSTI · 3008288
Weakly supervised anomaly detection with event-level variables
Abstract
We introduce a new topology for weakly supervised anomaly detection searches, diobject 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 dijet searches focusing on jet substructure anomalies can be applied to event-level anomaly detection in this topology. To robustly capture event-level features of multiparticle 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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Brennan, Liam [Univ. of California, Santa Barbara, CA (United States)] (ORCID:0000000306361846), Vami, Tamas Almos [Univ. of California, Santa Barbara, CA (United States)] (ORCID:0000000209599211), Amram, Oz [Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)] (ORCID:0000000237653123), Sekhar, Sanjana [Johns Hopkins Univ., Baltimore, MD (United States)] (ORCID:0000000283077518), Takahashi, Yuta [Univ. of Florida, Gainesville, FL (United States)] (ORCID:0000000151842265), Moureaux, Louis [University of Hamburg] (ORCID:0000000223109266), Sommerhalder, Manuel [University of Hamburg] (ORCID:0000000157467371), Maksimovic, Petar [Johns Hopkins University] (ORCID:0000000223582168), Cai, Tianji [Tongji University; Tongji University] (ORCID:0000000232359486), Craig, Nathaniel [University of California Santa Barbara; Kavli Institute for Theoretical Physics] (ORCID:0000000322148447). 2025-09-26. Weakly supervised anomaly detection with event-level variables. https://doi.org/10.1103/rk29-518p
Cite the original work for its findings. Save a collection to share your selection of sources.