arXiv stat.ML
· Papers
Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration
arXiv:2607.21673v1 Announce Type: cross Abstract: Test-time adaptive out-of-distribution (OOD) detectors update a memory bank from the unlabelled stream. We show this adaptation obeys a provable dynamical law. Modelling bank impurity as a generalized P'olya urn, we prove almost-sure convergence to a mean-field equilib