Calibration of electromagnetic shower features in the CMS calorimeter with machine-learning techniques

Monte Carlo simulations are extensively used in high-energy particle physics analyses but suffer from discrepancies between simulated and real collision data due to incomplete physics descriptions. This paper presents two novel calibration methods based on machine-learning techniques, including a reweighting approach using a classifier to mitigate biases from mismodelling in electromagnetic shower features within the CMS calorimeter.