Improved Constraints on Effective Top Quark Interactions using Edge Convolution Networks

TL;DR

This paper demonstrates that Graph Neural Networks can enhance the sensitivity of SMEFT analyses in top quark pair production by effectively utilizing multidimensional phase space correlations, surpassing traditional cut-based methods.

Contribution

It introduces a GNN-based approach to improve EFT parameter fits in collider data, leveraging all available final state correlations for better discrimination of BSM effects.

Findings

GNNs improve discrimination of BSM effects in top quark production.

Selection strategies based on GNN outputs enhance fit sensitivity.

GNNs effectively utilize multidimensional phase space information.

Abstract

We explore the potential of Graph Neural Networks (GNNs) to improve the performance of high-dimensional effective field theory parameter fits to collider data beyond traditional rectangular cut-based differential distribution analyses. In this study, we focus on a SMEFT analysis of $pp \to t\bar t$ production, including top decays, where the linear effective field deformation is parametrised by thirteen independent Wilson coefficients. The application of GNNs allows us to condense the multidimensional phase space information available for the discrimination of BSM effects from the SM expectation by considering all available final state correlations directly. The number of contributing new physics couplings very quickly leads to statistical limitations when the GNN output is directly employed as an EFT discrimination tool. However, a selection based on minimising the SM contribution enhances the fit's sensitivity when reflected as a (non-rectangular) selection on the inclusive data samples that are typically employed when looking for non-resonant deviations from the SM by means of differential distributions.