Speaker
Description
Jet tagging, i. e. determining the origin of high-energy hadronic jets, is a key challenge in particle physics. Jets are ubiquitous observables in collider experiments, made of complex collections of particles, that need to be classified. Over the past decade, machine learning-based classifiers have greatly enhanced our jet tagging capabilities, with increasingly sophisticated models driving further improvements. This raises a fundamental question: How far are we from the theoretical limit of jet tagging performance? To explore this, we employ transformer-based generative models to produce realistic synthetic data with a known probability density function. By testing various state-of the-art taggers on this dataset, we find a significant gap between their performance and the theoretical optimum, signalling a significant room for improvement. Our dataset and software are made public to provide a benchmark task for future developments in jet tagging and other areas of particle physics.
Significance
We explore, for the first time, the jet-tagging capabilities of state-of-the-art taggers on synthetic data with a known optimum. We uncover a big gap between the theoretical optimum (the LLR) and the performance of the taggers. We set a new benchmark for future ML-based jet tagger developments.
References
arXiv:2411.02628
