All reviewers agree that this paper describes a technically impressive contribution to machine learning research. Although the field of "physics and ML" is relatively small, it is growing, and the techniques underpinning this work offer clear learnings for the wider ML community. Therefore, it appears clear that the audience for this paper is the NeurIPS audience, and the level of contribution is at the level of NeurIPS papers. All reviewers, and R3 in particular had some questions about the style of presentation, and I am content with the rebuttal's statement that the authors will take the feedback on style for a final version.