Casting a graph net to catch dark showers

TL;DR

This paper demonstrates that dynamic graph convolutional neural networks significantly improve the identification of semi-visible jets from dark showers at the LHC, outperforming other neural network methods and enhancing detection sensitivity.

Contribution

The study introduces the use of dynamic graph convolutional neural networks for semi-visible jet classification, showing superior performance over traditional methods and proposing strategies to reduce model dependence.

Findings

Dynamic graph networks outperform jet image CNNs.

Training on mixed samples reduces model dependence.

LHC sensitivity to dark sectors can be increased tenfold.

Abstract

Strongly interacting dark sectors predict novel LHC signatures such as semi-visible jets resulting from dark showers that contain both stable and unstable dark mesons. Distinguishing such semi-visible jets from large QCD backgrounds is difficult and constitutes an exciting challenge for jet classification. In this article we explore the potential of supervised deep neural networks to identify semi-visible jets. We show that dynamic graph convolutional neural networks operating on so-called particle clouds outperform convolutional neural networks analysing jet images as well as other neural networks based on Lorentz vectors. We investigate how the performance depends on the properties of the dark shower and discuss training on mixed samples as a strategy to reduce model dependence. By modifying an existing mono-jet analysis we show that LHC sensitivity to dark sectors can be enhanced by more than an order of magnitude by using the dynamic graph network as a dark shower tagger.