ScatterPrism: convergence for generative simulation and inverse problems in particle and nuclear physics

Abstract

High-fidelity simulations and complex inverse problems, such as detector modeling and unfolding, are computationally intensive bottlenecks across subatomic physics, yet essential for accurate physical interpretation. While Conditional Flow Matching (CFM) offers a robust acceleration approach, we demonstrate its standard training loss is fundamentally misleading. Specifically, utilizing a Jefferson Lab Nuclear Physics (NP) kinematic dataset ($\gamma p\to {\rho }^{0}p\to {\pi }^{+}{\pi }^{-}p$), we expose that CFM loss plateaus prematurely, obscuring ongoing physical refinement. To verify this disconnect is a dataset-agnostic pathology, we introduce ScatterPrism, an efficient generative surrogate evaluated against both the NP data and synthetic stress tests modeling challenging 1D distribution topologies. Coupling these benchmarks, we establish that physics-informed metrics continue improving long after standard loss converges. Consequently, we propose a multi-metric diagnostic protocol to ensure true kinematic fidelity without data memorization. Driven by NP challenges relevant to the forthcoming Electron-Ion Collider (EIC), this unified machinery has strong potential to extend to High-Energy Physics (HEP) applications, such as jet modeling. Furthermore, the framework holds promise for broader domains requiring rigorous generative reliability, including medical imaging, astrophysics, and quantitative finance.

23 pages, 16 figures. Published in Journal of Instrumentation (AI4EIC 2025 proceedings)

References in corpus (11)

• MadGraph 5 : Going Beyond
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• How to GAN LHC Events
• OmniFold: A Method to Simultaneously Unfold All Observables
• The GlueX Beamline and Detector
• CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Improving Generative Model-based Unfolding with Schrödinger Bridges
• The Landscape of Unfolding with Machine Learning
• Full Event Particle-Level Unfolding with Variable-Length Latent Variational Diffusion
• PyTorchFire: A GPU-Accelerated Wildfire Simulator with Differentiable Cellular Automata