A Appendix A.1 Shower shape variables

We extend the list of shower shape variables described in Sec. Deepest layer in the shower with non-zero energy deposit. Figure 1 shows the average events for different variations of SUPA datasets and Figs. Figure 1 - 12 shows PointFlow PointFlow [Yang et al., 2019] is a flow based model with a PointNet-like encoder and a The overall architecture has 2.1M parameters. We train all the models with 100K training examples. Figs. 13 - 18 show the histograms of various shower shape variables for SUPAv1 and samples Figs.