Machine-Learned Particle Flow as a Foundation Model for Collider Physics

Authors:
Open Access
Publisher website
Google Scholar
Abstract
The workflow from particle collision to physics analysis passes through a series of reconstruction steps that are traditionally modular and disconnected, with no shared representation linking low-level detector data to high-level analysis tasks. We show that casting event reconstruction as a machine learning problem naturally produces such a shared representation. We repurpose a machine learning model trained for particle-flow reconstruction (MLPF) to perform three distinct analysis tasks: jet flavor identification, jet energy regression, and missing momentum regression. By appending the per-particle latent representations learned during reconstruction as additional input features, we substantially improve over baselines that use conventional particle-level features alone. We further demonstrate that a single linear layer trained using only the latent representations achieves competitive performance against state-of-the-art baseline architectures, and outperforms the baseline for missing momentum regression with approximately 35 times fewer parameters. These results demonstrate that the latent representations learned during reconstruction encode essential physics information needed for downstream analysis, establishing MLPF as a foundation model and offering a concrete step toward an end-to-end pipeline from detector data to physics analysis.
All Related Versions
Funding Information
  • Research Corporation for Science Advancement (CS-CSA-2023-109)
  • U.S. Department of Energy (DE-SC0009919)
  • U.S. Department of Energy (DE-AC02-76SF00515)
  • Office of Science
  • High Energy Physics
  • National Science Foundation
  • Eesti Teadusagentuur (PSG864)
  • European Regional Development Fund (TK202)
  • Institute for Accelerating AI Algorithms for Data Driven Discovery (PHY-2117997)

This publication has 31 references indexed in Scilit: