Learning to Identify Semi-Visible Jets

TL;DR

This paper develops a deep learning approach to identify semi-visible jets from dark matter decay by analyzing low-level jet constituents, revealing information beyond traditional jet substructure observables.

Contribution

It introduces a neural network method to detect semi-visible jets and investigates the underlying features, highlighting the importance of low-$p_T$ constituents for classification.

Findings

Deep network effectively identifies semi-visible jets.

Low-$p_T$ jet constituents carry significant classification information.

Current high-level observables miss critical features used by the network.

Abstract

We train a network to identify jets with fractional dark decay (semi-visible jets) using the pattern of their low-level jet constituents, and explore the nature of the information used by the network by mapping it to a space of jet substructure observables. Semi-visible jets arise from dark matter particles which decay into a mixture of dark sector (invisible) and Standard Model (visible) particles. Such objects are challenging to identify due to the complex nature of jets and the alignment of the momentum imbalance from the dark particles with the jet axis, but such jets do not yet benefit from the construction of dedicated theoretically-motivated jet substructure observables. A deep network operating on jet constituents is used as a probe of the available information and indicates that classification power not captured by current high-level observables arises primarily from low-$p_\textrm{T}$ jet constituents.