EveNet: A Foundation Model for Particle Collision Data Analysis

2026-01-23

AI Summary

This work proposes EveNet, the first event-level foundation model in high-energy physics capable of transferring to real experimental data. Addressing the limitations of deep learning—namely computational inefficiency and sensitivity to systematic uncertainties—in collider data analysis, EveNet is pretrained on 500 million simulated collision events and integrates self-supervised learning with physics-informed supervision. By leveraging a shared particle-cloud representation, it unifies diverse physics tasks under a single framework, achieving high data efficiency and robustness against systematic errors. The model effectively encodes fundamental structures of particle interactions and outperforms existing methods in tasks such as heavy resonance searches and exotic Higgs decays. Notably, when applied to CMS open data, EveNet successfully reconstructs the ϒ meson and precisely extracts noise-resilient quantum correlation observables.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

While deep learning is transforming data analysis in high-energy physics, computational challenges limit its potential. We address these challenges in the context of collider physics by introducing EveNet, an event-level foundation model pretrained on 500 million simulated collision events using a hybrid objective of self-supervised learning and physics-informed supervision. By leveraging a shared particle-cloud representation, EveNet outperforms state-of-the-art baselines across diverse tasks, including searches for heavy resonances and exotic Higgs decays, and demonstrates exceptional data efficiency in low-statistics regimes. Crucially, we validate the transferability of the model to experimental data by rediscovering the $\Upsilon$ meson in CMS Open Data and show its capacity for precision physics through the robust extraction of quantum correlation observables stable against systematic uncertainties. These results indicate that EveNet can successfully encode the fundamental physical structure of particle interactions, which offers a unified and resource-efficient framework to accelerate discovery at current and future colliders.

Problem

• particle collision data analysis
• computational challenges
• deep learning
• high-energy physics
• event-level modeling

Innovation

• foundation model
• particle collision
• self-supervised learning
• physics-informed supervision
• transferability