The reviewer consensus was that, despite requiring some improvements in terms of presentation, with some areas flagged by reviewers as necessitating more detail, and the toy-ish nature of the experiments, that this paper addresses an important problem with the NeurIPS community in attempting to reconcile deep networks with symbolic-like reasoning. The paper is thus deemed of an acceptable standard, but the authors should note that while they are not expected to change their experimental setting for the camera-ready, should the paper be included in the proceedings, they should pay careful attention to the reviewer comments and recommendations when revising their paper in order to insure that the points of clarification requested are expanded upon, possibly in an appendix.