A deep neural network to search for new long-lived particles decaying to jets

TL;DR

This paper introduces a deep neural network-based algorithm for identifying displaced jets from long-lived particle decays in CMS detector data, enhancing the search for new physics beyond the standard model.

Contribution

It presents a novel multiclass classifier that is parameterized by decay length and trained with domain adaptation, improving LLP jet detection in collider data.

Findings

Achieves a rejection factor of 10,000 for standard model jets.

Maintains 30-80% efficiency for LLP jets with decay lengths from 1 mm to 10 m.

Demonstrates potential to explore split supersymmetry parameter space.

Abstract

A tagging algorithm to identify jets that are significantly displaced from the proton-proton (pp) collision region in the CMS detector at the LHC is presented. Displaced jets can arise from the decays of long-lived particles (LLPs), which are predicted by several theoretical extensions of the standard model. The tagger is a multiclass classifier based on a deep neural network, which is parameterised according to the proper decay length $\mathrm{c}\tau_0$ of the LLP. A novel scheme is defined to reliably label jets from LLP decays for supervised learning. Samples of pp collision data, recorded by the CMS detector at a centre-of-mass energy of 13 TeV, and simulated events are used to train the neural network. Domain adaptation by backward propagation is performed to improve the simulation modelling of the jet class probability distributions observed in pp collision data. The potential performance of the tagger is demonstrated with a search for long-lived gluinos, a manifestation of split supersymmetric models. The tagger provides a rejection factor of 10 000 for jets from standard model processes, while maintaining an LLP jet tagging efficiency of 30-80% for gluinos with 1 mm $\leq$ $c\tau_0$ $\leq$ 10 m. The expected coverage of the parameter space for split supersymmetry is presented.