An end-to-end pipeline for uncertainty-aware validation of generative AI

Density estimation with generative AI is a common task in the physical sciences, with applications ranging from particle physics to gravitational-wave parameter estimation.Many of the existing methods, however, do not provide a way to estimate epistemic uncertainties, which is essential for reliable hypothesis testing necessary for scientific discovery. We propose an end-to-end framework combining generative modeling with principled uncertainty quantification. A normalizing-flow ensemble is trained to synthesize events; ensemble-based epistemic uncertainties are computed and propagated into a learned likelihood–ratio goodness-of-fit (GoF) test. This yields to robust distributional estimates that allow for oversampling and enables uncertainty-aware scientific discoveries.