SciPost Submission Page

Casting a graph net to catch dark showers

by Elias Bernreuther, Thorben Finke, Felix Kahlhoefer, Michael Krämer, Alexander Mück

Submission summary

As Contributors: Elias Bernreuther · Thorben Finke · Michael Krämer
Arxiv Link: https://arxiv.org/abs/2006.08639v3 (pdf)
Date accepted: 2021-02-10
Date submitted: 2021-01-08 10:20
Submitted by: Bernreuther, Elias
Submitted to: SciPost Physics
Academic field: Physics
Specialties:
  • High-Energy Physics - Phenomenology

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.

Published as SciPost Phys. 10, 046 (2021)



Author comments upon resubmission

We have made a few more changes to the manuscript following the suggestions made by the reviewers.

Reports on this Submission

Anonymous Report 2 on 2021-2-2 Invited Report

Report

I am happy with the minor changes that have been made and am happy to recommend publication.

  • validity: -
  • significance: -
  • originality: -
  • clarity: -
  • formatting: -
  • grammar: -

Anonymous Report 1 on 2021-1-8 Invited Report

Report

Thank you for taking into account my feedback. I am happy to recommend publication of the current manuscript.

  • validity: -
  • significance: -
  • originality: -
  • clarity: -
  • formatting: -
  • grammar: -

Login to report or comment