All reviewers

We would like to thank all the reviewers for their positive assessment of our work. We would like to politely disagree with your statement that "the proposed model seems to underperform the We found that increasing the block size beyond 16 for the TriTPP model did not improve the performance. In contrast, the RNN did benefit from larger hidden sizes (32 or 64). In the scalability experiment (Section 6.1) we made sure that both models have approximately the We found that stacking the nonlinearities (splines) did not improve the performance on the validation set. Thank you, we will run more experiments to see if this will allow us to improve the performance.