New jet tagging techniques at CMS

TL;DR

This paper introduces new machine learning-based jet tagging techniques at CMS that significantly improve the identification of various particle origins in LHC Run 2 data.

Contribution

It presents novel machine learning algorithms for jet tagging that outperform traditional methods in particle physics analysis.

Findings

Machine learning techniques outperform classical taggers

Enhanced identification of quark, gluon, and boson jets

Improved analysis capabilities for LHC data

Abstract

The CMS experiment makes use of a large variety of algorithms to identify the origin of particle jets measured in the detector. Through the study of jet substructure properties, jets originating from quarks, gluons, W/Z/Higgs bosons, top quarks and pileup interactions are identified and categorized. We present new techniques based on machine learning approaches developed for the analysis of the data collected during the LHC Run 2 that significantly surpass the performances of classical taggers.