CORE: Robust Out-of-Distribution Detection via Confidence and Orthogonal Residual Scoring

Computer Science > Artificial Intelligence [Submitted on 18 Mar 2026] CORE: Robust Out-of-Distribution Detection via Confidence and Orthogonal Residual Scoring Jin Mo Yang, Hyung-Sin Kim, Saewoong Bahk 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. Comments: 26 pages, 5 figures, includes supplementary material as appendix Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.18290 [cs.AI]   (or arXiv:2603.18290v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.18290 Focus to learn more Submission history From: Jin Mo Yang [view email] [v1] Wed, 18 Mar 2026 21:23:54 UTC (711 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)