Speaker
Description
Artificial Intelligence (AI) generative models have been successfully used in several field. In this contribution I will present results of the A(I)DAPT (AI for Data Analysis and Data PreservaTion) working group. Our objective is to develop AI-based tools to address the main challenges in Nuclear Physics and High Energy Physics measurements: unfold detector effects and preserve multi-dimensional correlations when working on large datasets.
In this contribution I will present a first closure test performed on pseudo-data matched on CLAS g11 experiment kinematics, where generative models were able to unfold detector effects on data and reproduce multi-differential contribution in data. I will also show the current progress in expanding this study towards more complex processes and detector layout, such as CLAS12 two pion electroproduction.
