Classifier Surrogates: Sharing AI-based Searches with the World

In recent years, neural network-based classification has been used to improve data analysis at collider experiments. While this strategy proves to be hugely successful, the underlying models are not commonly shared with the public and rely on experiment-internal data as well as full detector simulations. We show a concrete implementation of a newly proposed strategy, so-called Classifier Surrogates, to be trained inside the experiments, that only utilise publicly accessible features and truth information. These surrogates approximate the original classifier distribution, and can be shared with the public. Subsequently, such a model can be evaluated by sampling the classification output from high-level information without requiring a sophisticated detector simulation. Technically, we show that Continuous Normalizing Flows are a suitable generative architecture that can be efficiently trained to sample classification results using Conditional Flow Matching. We further demonstrate that these models can be easily extended by Bayesian uncertainties to indicate their degree of validity when confronted with unknown inputs by the user. For a concrete example of tagging jets from hadronically decaying top quarks, we demonstrate the application of flows in combination with uncertainty estimation through either inference of a mean-field Gaussian weight posterior, or Monte Carlo sampling network weights.