AI Paper Atlas

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

Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AI

Bogdan Raonic, Siddhartha Mishra, Samuel Lanthaler

ICLR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 1 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 joint likelihood p(x,y_pred) as certificate instead of other joint-score certificatesJLBC · Average over 5 datasetsAUROC: 0.945 vs 0.927 (JDPath), 0.906, 0.925, 0.923Improved
use joint likelihood certificate on mixture-of-distributions Navier-StokesJLBC · NS-MIXAUROC: 0.992 vs 0.918 (JDPath)Improved
use joint likelihood certificate on MERRA2 humidityJLBC · MERRA2ID/OOD accuracy: 0.956 vs 0.989 (JDPath)Hurt
use joint likelihood certificate on brain segmentationJLBC · BrainAUROC: 0.808 vs 0.808 (JDPath)No clear effect
use only input likelihood p(x) instead of joint p(x,y_pred) (ablation)JLBC · NS-MIXcorrelation with L1 errorHurt
train the diffusion model for more epochs (up to 500) (ablation)JLBC · Wave equationlikelihood-error alignmentImproved
use more decision samples from the training distribution (4 up to 32) (ablation)JLBC · Wave equationID/OOD boundary stabilityImproved
swap CNO regression model for ViT, UNet or C-FNO (ablation)JLBC · Wave equationlikelihood-error correlationNo clear effect
use joint likelihood certificate instead of MC-Dropout and Rate-InJLBC · Wave equationaccuracy and AUROCImproved

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