Generative Unfolding of Jets and Their Substructure

TL;DR

This paper introduces a novel three-stage generative unfolding framework capable of handling several hundred dimensions, enabling detailed reconstruction of jet substructure in high-energy physics data.

Contribution

It presents the first high-precision generative unfolding method for high-dimensional jet substructure, scalable to hundreds of dimensions.

Findings

Effective unfolding of jet-level kinematics and substructure.

Achieves high precision in high-dimensional jet substructure.

Scales to several hundred dimensions.

Abstract

Unfolding, for example of distortions imparted by detectors, provides suitable and publishable representations of LHC data. Many methods for unbinned and high-dimensional unfolding using machine learning have been proposed, but no generative method scales to the several hundred dimensions necessary to fully characterize LHC collisions. This paper proposes a 3-stage generative unfolding framework that is capable of unfolding several hundred dimensions. It is effective to unfold the jet-level kinematics as well as the full substructure of light-flavor jets and of top jets, and is the first generative unfolding study to achieve high precision on high-dimensional jet substructure.