Detecting anomalies in vector boson scattering

Measuring vector boson scattering(VBS)precisely is an important step toward understanding the electroweak symmetry breaking of and detecting new physics beyond the standard model(SM).Herein,we propose a neural network that compresses the features of the VBS data into a three-dimensional latent space.The consistency of the SM predictions and experimental data is tested via binned log-likelihood analysis in the latent space.We show that the network is capable of distinguishing different polarization modes of WWjj production in both di-and semileptonic channels.The method is also applied to constrain the effective field theory and two Higgs Doublet Model.The results demonstrate that the method is sensitive to general new physics contributing to the VBS.