We are pleased that the different conceptual aspects of BoxE are clear, and that our experiments are

We thank the reviewers for their valuable and insightful feedback, and respond to their comments and questions below. Model expressivity and compression: The bound in Theorem 5.1 is a worst-case bound that is only tight when all KB In fact, higher-arity experiments (see Section 6.2) are Furthermore, we have evaluated model robustness in Appendix H.1, and Adam optimizer, and hyper-parameters (including negative samples) are in Table 6. We will mention this in the paper. Novelty of the model: BoxE is substantially different from any existing box model. We will make these differences more explicit in the paper.