This paper proposes ONESHOT, which uses a single confirmed anomaly to weight the pool rather than to choose one detector from it, and shows that a single confirmed anomaly is enough to come close to the best detector for the series.
Abstract
Time series (TS) anomaly detection (AD) lacks a universal detector, with the best choice determined by the series rather than by the algorithm. Existing methods therefore either select one detector for each series or average a pool of them. However, both assume that no label ever arrives, while a deployed monitor does receive them, since an operator confirms the alarms it raises. In this paper, we propose ONESHOT, which uses a single confirmed anomaly to weight the pool rather than to choose one detector from it. Specifically, we score each detector on the confirmed anomaly, and those scores become the weights of a soft mixture over the whole pool. We show that a single confirmed anomaly is enough to come close to the best detector for the series. Across 152 univariate and 73 multivariate series, ONESHOT outperforms the strongest single detector, averaging the whole pool, and even picking the best detector on the confirmed event. Code is available at: https://github.com/seunghan96/one_shot.
Time-series anomaly detection trades off predictive accuracy, computational efficiency, and interpretability. We use a large language model not as the detector but as the author of one: an autonomous research loop in which the model repeatedly edits a single short NumPy program under a leakage-free objective, keeping t...
Anomaly detection is a fundamental task for time-series analytics, with important implications for the downstream performance of many applications. Despite the large number of anomaly detection methods proposed in the literature, recent benchmark studies have shown that no single detector performs best across highly he...
Christos Panourgias, Roberto Stanzione, Adrien Petralia et al.· 0 citations
Time-series anomaly detection (TSAD) is difficult to generalize across datasets because heterogeneous temporal dynamics imply different notions of normality and favor different detection criteria. While time-series foundation models provide transferable representations, coupling them with a fixed anomaly-scoring mechan...
Tian Lan, Yi-Fei Gao, Yi-Meng Lu et al.· 0 citations
This work investigates a multi-model fusion strategy to improve robustness under heterogeneous detector behavior and proposes fusion techniques including majority voting, probability averaging, the ordered weighted averaging operator, the Choquet integral, and the Takagi-Sugeno model.
Łukasz Gałka, Grzegorz Kozieł, Marta Dziuba-Kozieł· IEEE Access· 0 citations
Large Language Models (LLMs) are increasingly explored for time series anomaly detection (TSAD), yet their direct use often remains inferior to methods designed specifically for TSAD. In this work, we study whether this limitation arises primarily from weak forecasting or from insufficient exploitation of forecast resi...
Hakan Akdag, A. T. Bui, Natalie Hußfeldt et al.· Proceedings of the 35th ACM...· 0 citations
A pool per domain is generated by prompting a multimodal LLM with in-context example windows from that domain by prompting a multimodal LLM with in-context example windows from that domain, and the generated pools match the hand-crafted one under matched selection, and the two cover different domains.
Youssef Attia El Hili, Malik Tiomoko, Corinne Ancourt· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
