Weakly supervised anomaly detection for resonant new physics in the dijet final state using proton-proton collisions at $\sqrt{s}=13$ TeV with the ATLAS detector

TL;DR

This paper presents a model-agnostic anomaly detection method using weakly supervised machine learning to search for new physics in dijet events at the LHC, finding no significant excesses but demonstrating sensitivity to various models.

Contribution

It introduces a novel weakly supervised machine learning approach for broad, model-independent anomaly detection in high-energy physics data from the ATLAS detector.

Findings

No significant local excesses observed in the data.

The methods show sensitivity to various new physics signal models.

The approach is optimized without relying on specific signal assumptions.

Abstract

An anomaly detection search for narrow-width resonances beyond the Standard Model that decay into a pair of jets is presented. The search is based on 139 fb$^{-1}$ of proton-proton collisions at $\sqrt{s}=13$ TeV recorded during 2015-2018 with the ATLAS detector at the Large Hadron Collider. The analysis is optimized without a particular signal model and aims to be sensitive to a broad range of new physics. It uses two different machine learning strategies to estimate the background in different signal regions. In each region, a weakly supervised classifier is trained to distinguish this background estimate from data. The analysis focuses on events with high transverse momentum jets reconstructed as large-radius jets. The mass and substructure of these jets are used as inputs to the classifiers. After a classifier-based selection, the distribution of the invariant mass of the two jets is used to search for potential local excesses. The model-independent results of both the anomaly detection methods show no signs of significant local excesses. In addition to model-independent results, a representative set of signal models is injected into the data, and the sensitivity of the methods to these scenarios is reported.