Weaknesses: - I could not follow the motivation for the simplified estimation procedure (and subsequent theoretical analysis in 3.1) that ignores timestamps (using event counts to estimate the branching ratio). It would be helpful if the authors could explain what advantages this approach brings compared to a "standard" block model inference in networks with a weighted adjacency matrix and the assumption that "event counts" (i.e. For instance, how do the results for the misclustering error rate compare to existing works on dectectability limits in the (weighted) block model? I would guess that there is a difference due to the use of the variance of event counts within blocks, which is not used for parameter estimation in some of the simpler block modelling approaches. However, this simpler version of the model is not included in the experimental evaluation.