AI Paper Atlas

Research map / Time series / Anomaly detection

COGNOS: Universal Enhancement for Time Series Anomaly Detection via Constrained Gaussian-Noise Optimization and Smoothing

Wenlong Shang, Shihao Tian, Xutong Wan, Peng Chang

ICML 2026 · Time series › Anomaly detection · approach: Time series anomaly detection evaluation · 0 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
add COGNOSnine backbones (average) · GECCOAffiliation F1: 0.5475 -> 0.9388Improved
add COGNOSnine backbones (average) · MSLAffiliation F1: 0.4794 -> 0.9308Improved
add COGNOSnine backbones (average) · SWANAffiliation F1: 0.1997 -> 0.4577Improved
add COGNOSnine backbones (average) · SWaTAffiliation F1: 0.4026 -> 0.9557Improved
add COGNOSTimeMixer++ · SMAPAffiliation F1: 0.3764 -> 0.4063Improved
add COGNOSTimesNet · MSLRange-AUC-ROC: 0.6968 -> 0.6663Hurt
add COGNOSKAN-AD · PSMRange-AUC-ROC: 0.7005 -> 0.6799Hurt
add ARKS to KAN-AD without GWNR (ablation)KAN-AD · MSLStandard F1: 0.8115 -> 0.8083No clear effect
add ARKS to KAN-AD without GWNR (ablation)KAN-AD · PSMStandard F1: 0.8946 -> 0.9433Improved
add GWNR alone without ARKS (ablation)KAN-AD · GECCOStandard F1: 0.4738 -> 0.3440Hurt
add ARKS on top of GWNR (ablation)KAN-AD · MSLStandard F1: 0.8704 -> 0.9165Improved
replace ARKS with moving average (ablation)KAN-AD + GWNR · MSLStandard F1: 0.9165 -> 0.1626Hurt

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