Inclusive Jet Measurements in Pb-Pb Collisions at 5.02 TeV with ALICE using Machine Learning Techniques

TL;DR

This paper presents advanced jet spectrum and nuclear modification factor measurements in Pb-Pb collisions at 5.02 TeV using machine learning for background correction, enabling analysis at lower transverse momenta and larger jet sizes.

Contribution

It introduces a machine learning-based background correction method that improves jet measurements in heavy-ion collisions, allowing for lower momentum thresholds and larger jet resolution parameters.

Findings

Reduced residual fluctuations in jet background correction

Extended measurement capabilities to lower transverse momenta

Comparison of results with theoretical predictions

Abstract

These proceedings report on measurements of the jet spectrum and nuclear modification factor for inclusive full jets (containing both charged and neutral constituents) in Pb-Pb and pp collisions at $\sqrt{s_{\rm NN}} = 5.02$ TeV recorded with the ALICE detector. These measurements use a machine learning based background correction, which reduces residual fluctuations. This method allows for measurements to lower transverse momenta and larger jet resolution parameter (R) than previously possible in ALICE. In this method, machine learning techniques are used to correct the jet transverse momentum on a jet-by-jet basis using jet parameters such as information about the constituents of the jet. Studies that investigate the effect of the potential fragmentation bias introduced by learning from constituents will also be discussed. With these studies in mind, the results are compared to theoretical predictions.