AI Paper Atlas

Research map / Time series / Anomaly detection

Complexity- and Statistics-Guided Anomaly Detection in Time Series Foundation Models

Jongwon Kim, Samuel Yoon, Young Myoung Ko, Yerin Kim, Sung Il Kim, JAEUNG TAE

ICLR 2026 · Time series › Anomaly detection · approach: Time series anomaly detection evaluation

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
re-inject instance mean and standard deviation before the linear decoder (MOMENT-Stat) (ablation)MOMENT · TSB-AD-UVUS-PR: 0.3857 -> 0.3913Improved
MOMENT-Stat versus zero-shot MOMENTMOMENT · TSB-AD-UVUS-PR: 0.3790 -> 0.3913Improved
add complexity-aware ensemble with MOMENT-StatSub-PCA · TSB-AD-UVUS-PR: 0.4233 -> 0.4679Improved
add complexity-aware ensemble with MOMENT-StatSub-IForest · TSB-AD-UVUS-PR: 0.2230 -> 0.4318Improved
add complexity-aware ensemble with MOMENT-StatSR · TSB-AD-UVUS-PR: 0.3237 -> 0.4596Improved
add complexity-aware ensemble with MOMENT-StatSub-HBOS · TSB-AD-UVUS-PR: 0.2283 -> 0.3734Mixed
use continuous alpha weighting (CAE) instead of random selection (ablation)Sub-PCA + MOMENT-Stat · TSB-AD-UVUS-PR: 0.4073 -> 0.4679Improved
use continuous alpha weighting (CAE) instead of hard selection (CAS) (ablation)Sub-PCA + MOMENT-Stat · TSB-AD-UVUS-PR: 0.4400 -> 0.4679Improved
use dataset-level alpha instead of instance-level alpha (ablation)CAE Sub-PCA · TSB-AD-UVUS-PR: 0.4582 -> 0.4679Improved
use proposed complexity measure instead of Spectral Entropy (ablation)CAE Sub-PCA · TSB-AD-UVUS-PR: 0.4288 -> 0.4679Improved
use proposed complexity measure instead of Spectral Entropy (ablation)CAE Sub-HBOS · TSB-AD-UVUS-PR: 0.3835 -> 0.3734Hurt
ensemble two statistical models instead of statistical plus MOMENT-Stat (ablation)best Stat+Stat pair · TSB-AD-UVUS-PR: 0.4398 -> 0.4679Hurt

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