# CORE: Robust Out-of-Distribution Detection via Confidence and Orthogonal Residual Scoring Source: [CORE: Robust Out-of-Distribution Detection via Confidence and Orthogonal Residual Scoring]() Collection index: [llms.txt]() Data updated: 2026-03-21T05:00:04.296Z Authors: Jin Mo Yang, Hyung-Sin Kim, Saewoong Bahk Published: 2026-03-18T21:23:54.000Z ## Abstract Out-of-distribution (OOD) detection is essential for deploying deep learning models reliably, yet no single method performs consistently across architectures and datasets -- a scorer that leads on one benchmark often falters on another. We attribute this inconsistency to a shared structural limitation: logit-based methods see only the classifier's confidence signal, while feature-based methods attempt to measure membership in the training distribution but do so in the full feature space where confidence and membership are entangled, inheriting architecture-sensitive failure modes. We observe that penultimate features naturally decompose into two orthogonal subspaces: a classifier-aligned component encoding confidence, and a residual the classifier discards. We discover that this residual carries a class-specific directional signature for in-distribution data -- a membership signal invisible to logit-based methods and entangled with noise in feature-based methods. We propose CORE (COnfidence + REsidual), which disentangles the two signals by scoring each subspace independently and combines them via normalized summation. Because the two signals are orthogonal by construction, their failure modes are approximately independent, producing robust detection where either view alone is unreliable. CORE achieves competitive or state-of-the-art performance across five architectures and five benchmark configurations, ranking first in three of five settings and achieving the highest grand average AUROC with negligible computational overhead. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Out-of-Distribution Detection on CIFAR-100 (AUROC, FPR@95%TPR)](): Out-of-Distribution Detection; CIFAR-100; AUROC: 82.1. - [Out-of-Distribution Detection on ImageNet](): Out-of-Distribution Detection; ImageNet; AUROC: 90.7. ## Original sources and implementation [Original paper]() [PDF]()