QuantOm: Bridging Experiment and Theory for Femtoscale Imaging

QuantOm is an interdisciplinary collaboration established to develop an event-level interpretation of experimental data for QCD analysis and the reconstruction of the hadronic structure. State-of-the-art theoretical frameworks based on QCD factorization theorems, sophisticated experimental simulations, and a scalable computational architecture that leverages AI/ML techniques are used to construct a new folding approach that bridges theoretical calculations and experimental measurements. This approach enables a joint theoretical-experimental workflow. Using generative AI, theoretical predictions are modeled in the context of how they would appear in real-world experiments. The QuantOm framework is based on a novel, simulation-based inference method designed with Generative Adversarial Networks (GANs). With a conceptual Bayesian framework, new techniques are developed to solve ill-posed inverse problems powered by advanced scientific computing and machine learning methods. The conceptual Bayesian GAN framework allows for accessible quantification of statistical uncertainties. The accurate estimation of statistical uncertainties is necessary to reveal systematic effects and bias. These methods provide high-fidelity and expressive extraction of Quantum Correlation Functions that can be seamlessly incorporated into an event-level framework for effective representation of physics experiments.