Aspen Open Jets: unlocking LHC data for foundation models in particle physics

Authors:
Open Access
Publisher website
Google Scholar
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 (AOJs) dataset, consisting of approximately 178 M high p T jets derived from CMS 2016 Open Data. We show how pre-training the OmniJet-α foundation model on AOJs 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 AOJs dataset for further public use.
Funding Information
  • National Energy Research Scientific Computing Center (DE-AC02-05CH11231)
  • RWTH Aachen University (rwth0934)
  • Fermi Research Alliance, LLC (DE-AC02-07CH11359)
  • US Department of Energy (DOE- SC0010008)
  • Deutsche Forschungsgemeinschaft (396021762 – TRR 257)
  • Università di Bologna
  • Aspen Center for Physics (PHY-2210452)

This publication has 32 references indexed in Scilit: