Reproduce “Supervision Recovery for Time Series Anomaly Detection via Context-Anchored Pairing” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yifei Gao, Tian Lan, Yimeng Lu, Xuming An, Meng Wang, Wenjun He, Yijie Li, Chen Zhang
CAPS learns reusable anomaly semantics from simulated matched pairs, then applies them to target reference trajectories to construct counterpart examples with constructed support labels for detector training. Across nine benchmarks, its unweighted dataset-level means lead compared methods on Affiliation-F, F1T, Standard-F1, and VUS-PR. On F1T, CAPS scores 46.53 versus 41.21 for shuffled context-effect pairings, supporting context matching without explaining all gains.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.