Weaknesses: 1) The main weakness of the paper is the way it uses the phrase "worst case OOD detection", which is misleading and not discussed rigorously. In fact, as stated in the abstract, this means "worst case" *within the L_infinity balls around some specific OOD examples*. This paper is *not* providing guarantees about *arbitrary* OOD data, which is, to me, what the phrase "worst case OOD detection" sounds like it refers to. Low confidence can only be guaranteed locally around specific outliers. The empirical results suggest that this may be sufficient in practice in many cases, since exposure on (only) examples from Tiny Images helps provide provable levels of robustness on other OOD datasets at test time.

With the rapid development of signed social networks in which therelationships between two nodes can be either positive (indicatingrelations such as like) or negative (indicating relations such asdislike), producing a personalized ranking list with positive linkson the top and negative links at the bottom is becoming anincreasingly important task. To accomplish it, we propose ageneralized AUC (GAUC) to quantify the ranking performance ofpotential links (including positive, negative, and unknown statuslinks) in partially observed signed social networks. In addition, wedevelop a novel link recommendation algorithm by directly optimizingthe GAUC loss. We conduct experimental studies based upon Wikipedia,MovieLens, and Slashdot; our results demonstrate the effectivenessand the efficiency of the proposed approach.