Rev# 1: We thank the reviewer for the encouraging remarks

Rev#1: We thank the reviewer for the encouraging remarks. Why the attention mechanism is only based on the Y series..... latent factors X,F?: This is a good observation indeed Details about what the loss function is specifically to train the mean and residual forecasters in the local models?: These details are implicitly specified in Algorithm 1. The residual forecaster is trained using the same loss, but with respect to the true residual values in the future time-range. We will add a text description in our revised version.