Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
Title:Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection
Abstract:Within-dataset class-split evaluation is widely used as a proxy for fully unconditional out-of-distribution anomaly detection. We show that this protocol can become ill-posed when the held-out anomaly class overlaps the normal mixture in representation space. In this regime, anomaly scores may collapse toward chance or even invert, and the preferred score direction can depend on the unknown anomaly class. We introduce a simple training-free diagnostic, neighborhood class leakage, and show that it predicts score-direction instability across Fashion-MNIST, CIFAR-10, and Imagenette, in both pixel and VAE latent spaces. Our results suggest that class-split AD benchmarks should be treated as geometry-dependent stress tests rather than unconditional evidence of anomaly-detection ability.
| Comments: | 4+1 pages, 1 figure, accepted at ICML 2026 Workshop on Hypothesis Testing |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2606.02601 [cs.LG] |
| (or arXiv:2606.02601v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2606.02601
arXiv-issued DOI via DataCite
|
Submission history
From: Alejandro Ascárate [view email][v1] Sat, 23 May 2026 06:27:42 UTC (114 KB)
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — Machine Learning
-
Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol
Jul 2
-
SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling
Jul 2
-
SemiScope: Disentangling Classifier Tuning and Joint Optimization in Semi-Supervised Security Classification
Jul 2
-
A Filtered Mixture-of-Generators for Fully Synthetic Survival Training
Jul 2
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.