Aspen Open Jets: Unlocking LHC Data for Foundation Models in Particle Physics

arXiv (Cornell University)

Abstract

Foundation models are deep learning models pre-trained on large amounts of data which are capable of generalizing to multiple datasets and/or downstream tasks. This work demonstrates how data collected by the CMS experiment at the Large Hadron Collider can be useful in pre-training foundation models for HEP. Specifically, we introduce the AspenOpenJets dataset, consisting of approximately 178M high $p_T$ jets derived from CMS 2016 Open Data. We show how pre-training the OmniJet-$α$ foundation model on AspenOpenJets improves performance on generative tasks with significant domain shift: generating boosted top and QCD jets from the simulated JetClass dataset. In addition to demonstrating the power of pre-training of a jet-based foundation model on actual proton-proton collision data, we provide the ML-ready derived AspenOpenJets dataset for further public use.

Authors 9

1. Oz Amram
2. Luca Anzalone
3. Joschka Birk
4. Darius A. Faroughy
5. Anna Hallin
6. Gregor Kasieczka
7. Michael Krämer Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen

8. Ian Pang
9. Humberto Reyes-González Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen