SOURCE-LINKED INTELLIGENCE

LLM-Generated Feature Pools for Time Series Anomaly Detection

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

We study how far a simple statistical pipeline can go on univariate time series anomaly detection under a strict selection protocol. The method extracts a small pool of statistics over sliding windows, scores each window with a transductive robust (MAD) model, and selects a feature subset per domain on a held-out tuning split. On TSB-AD-U it reaches $0.529$ per-series VUS-PR, above the best neural ($0.45$) and statistical ($0.44$) entries on the public leaderboard and within $0.06$ of the strongest pretrained foundation model, several of which use more supervision than ours. Ablations locate t

Read original source ↗ Open in workspace

recordType

paper

region

Global