Reply to Pith's review of your paper.
A verified author's reply is published word for word beside the review. Pith does not edit it.
The paper
Detection Is Not Early Warning: Evaluating Token-Level Alarms on Language Model Failures
Marco De Negri, Luca Sartori, Lorenzo Baggi, Moritz Reihs, Eduard Frank \v{D}urech, Mennatallah El-Assady, Valentina Pyatkin, Anna Hedstr\"om, Anna Hedstr\"om (2, 3) ((1) ETH Zurich, (2) ETH AI Center, (3) Solaris Research) · arXiv:2611.16803
Your reply
Pith publishes a reply beside its review only from a verified author of the paper, so that a reader knows who is answering.
Sign in to write your reply. An account is free. If you are not verified yet, this page then says how, and you can write the reply and keep it as a draft meanwhile.