AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

SCOPED: Score–Curvature Out-of-distribution Proximity Evaluator for Diffusion

Brett Barkley, Preston Culbertson, David Fridovich-Keil

ICLR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use SCOPED (2F+2J) instead of DiffPath on average vision AUROCDiffusion OOD detection · Vision OOD averageAUROC: 0.918 -> 0.892Hurt
Use SCOPED instead of DiffPath on C10 vs C100Diffusion OOD detection · C10 vs C100AUROC: 0.590 -> 0.477Hurt
Add global sign correction to the typicality ratio (ablation)SCOPED two-step · Vision OOD averageAUROC: 0.81 -> 0.84Improved
Evaluate at mid-level timestep t=300 instead of early t=1 only (ablation)SCOPED single step · Vision OOD averageAUROC: 0.7985 -> 0.8835Improved
Combine early and mid timesteps instead of single t=300 (ablation)SCOPED · Vision OOD averageAUROC: 0.884 -> 0.892Improved
Choose the best timestep per dataset pair with oracle knowledge (ablation)SCOPED single step · Vision OOD averageAUROC: 0.884 -> 0.944Improved
Train detector on most diverse buffer (medium-replay) in D4RL (ablation)SCOPED · D4RL Hopper/Walker2d/AntAUROCHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy