Erlangen 2026 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

T: Fachverband Teilchenphysik

T 101: Searches/BSM VI

T 101.6: Talk

Friday, March 20, 2026, 10:15–10:30, KH 02.018

Anomaly detection for multi-jet resonances. — •Chitrakshee Yede, Louis Moureaux, Gregor Kasieczka, and Tore von Schwartz — University of Hamburg, Hamburg, Germany

The search for physics beyond the standard model is one of the main focuses in high-energy physics. Conventional searches at the LHC, though comprehensive, have not yet shown signs for new physics. Machine learning based anomaly detection has emerged as a powerful tool to widen the discovery horizon, offering a model-agnostic path as a way to enhance the sensitivity of generic searches as compared to those targeting specific signal models. CATHODE (Classifying Anomalies THrough Outer Density Estimation), one of these methods, is a two-step method that combines a data driven background estimation with a classifier flagging potential signal. To date, most studies have mainly focused on dijet resonances. In this work, we explore signals with multiple decays modes, leading to a more challenging detection scenario. We present the first application of CATHODE to multi-jet resonances, which enhance the sensitivity beyond the dijet regime and increase the robustness of weakly supervised anomaly detection, thereby broadening its applicability.

Keywords: Anomaly detection; CATHODE; Machine Learning; Multi-jet resonances