Application of Machine Learning Based Top Quark and W Jet Tagging to Hadronic Four-Top Final States Induced by SM and BSM Processes

TL;DR

This paper compares cut-based and machine learning methods for identifying top quark and W boson jets in simulated four-top events, aiding LHC searches for new physics.

Contribution

It introduces a combined analysis of classical and ML techniques for jet tagging in four-top final states, including BSM scenarios.

Findings

ML techniques improve jet tagging efficiency over cut-based methods.

Reconstruction of scalar resonance mass shows potential for new physics detection.

Analysis demonstrates applicability to LHC search strategies.

Abstract

We apply both cut-based and machine learning techniques using the same inputs to the challenge of hadronic jet substructure recognition, utilizing classical subjettiness variables within the Delphes parameterized detector simulation framework. We focus on jets generated in simulated proton-proton collisions, identifying those consistent with the decay signatures of top quarks or W bosons. Such jets are employed in four-top quark events in fully hadronic final states stemming from both the Standard Model as well as from a new physics process of a hypothetical scalar resonance y0 decaying into a pair of top quarks. We reconstruct the resonance invariant mass and compare it properties over the falling background using the two tagging approaches, with implications to LHC searches.