Aspen Open Jets: Unlocking LHC Data for Foundation Models in Particle Physics
This work addresses the need for accessible, real-world data to enhance foundation models in high-energy physics, though it is incremental as it builds on existing models and datasets.
The paper tackled the problem of pre-training foundation models for particle physics by introducing the AspenOpenJets dataset with 178M jets from LHC data, showing that pre-training OmniJet-α on it improves performance on generative tasks like boosted top and QCD jets from JetClass.
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.