Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection
Industrial AI
Summary
arXiv:2606.02601v1 Announce Type: new 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.
Why It Matters
This Industrial AI development deepens the link between AI compute and industrial productivity. For Asia, it is a signal worth tracking: it shapes who supplies, who scales, and who sets the standard over the next five years.
Key Facts
- SectorIndustrial AI
- Market—
- ImpactLow (42/100)
- SignalFunding Research