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

TL;DR

This paper introduces the AspenOpenJets dataset from CMS LHC data and demonstrates how pre-training a foundation model on it enhances jet generation tasks in particle physics.

Contribution

It presents a new large-scale dataset and shows how pre-training a foundation model on real collider data improves generative performance under domain shift.

Findings

Pre-training on AspenOpenJets improves jet generation quality.

The dataset enables better generalization to new particle physics tasks.

Foundation models benefit from real collider data pre-training.

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-$\alpha$ 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.