A modern framework for jet tagger development

TL;DR

This paper introduces a new, efficient framework for jet tagger development that reduces data storage needs, accelerates analysis turnaround, and enables advanced studies like neural network variants and adversarial techniques in jet flavor tagging.

Contribution

The framework offers a unified data structure, improves efficiency, and allows flexible investigation of neural network variants and adversarial effects without large disk usage.

Findings

Significantly reduces data storage requirements.

Speeds up analysis from months to days.

Enables studies of neural network variants and adversarial techniques.

Abstract

This paper presents a new tool to perform various steps in jet tagger development in an efficient and comprehensive way. A common data structure is used for training, as well as for performance evaluation in data. The introduction of this new framework reduces the amount of data to be stored while accomplishing the same tasks, and shortens waiting times between algorithm development and data-to-simulation results becoming available from months to days, taking typical CMS experiment pipelines as a reference. Proper utilization of high-throughput systems enables first data-to-simulation studies with a recent neural network architecture, Particle Transformer, adapted to jet flavour tagging. Unlike official implementations of the collaboration, the new framework allows investigating different variants, like different training paradigms, and their impact on data/simulation agreement, without producing any new large files on disk, and within the same run of the analysis framework. Besides being more time- and storage-efficient and thus enabling the first results of that kind to be available just few hours after finishing neural network training, the framework is currently the only realization capable of studying how adversarial techniques affect data/simulation agreement for tagger algorithm outputs as well as inputs.