Metraipolis › archive › dc_43589fb693aa

CAST: Context- and Anomaly Structure-Conditioned Time Series Anomaly Generation — arXiv:2609.27825

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.27825
License (as archived): CC0-1.0
Archived: 2026-10-08T10:57:21.607Z
SHA-256 of the archived text: d773a1757006220a493bb6f3ba17f588cd0133671b82c24876b6478cff0f5ba2
Stable URL of this page: https://metraipolis.com/documento/dc_43589fb693aa

How to cite

CAST: Context- and Anomaly Structure-Conditioned Time Series Anomaly Generation — arXiv:2609.27825 — arXiv (en), https://arxiv.org/abs/2609.27825 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43589fb693aa (Metraipolis archive dc_43589fb693aa, sha256 d773a1757006220a493bb6f3ba17f588cd0133671b82c24876b6478cff0f5ba2)

BibTeX

@misc{dc43589fb693aa,
  title = {CAST: Context- and Anomaly Structure-Conditioned Time Series Anomaly Generation — arXiv:2609.27825},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27825},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43589fb693aa; sha256 d773a1757006220a493bb6f3ba17f588cd0133671b82c24876b6478cff0f5ba2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27825. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Anomalous time series play a critical role in safety-critical domains, yet they are inherently scarce, heterogeneous, and costly to obtain. Existing time series generation methods predominantly focus on synthesizing normal data, providing limited value when anomalous samples are needed. We identify two fundamental challenges in anomaly generation: (i) the scarcity of anomaly data, and (ii) the heterogeneous morphological characteristics of anomalies. To address these challenges, we propose CAST, a Context- and Anomaly Structure-conditioned Time series anomaly generation framework with principled two-stage pretraining and finetuning strategy. In pretraining stage, we leverage abundant normal time series data to learn underlying system dynamics and substantially mitigate the limited availability of anomaly data. During finetuning, CAST explicitly conditions the generator on learned anomaly structure representations, enabling it to capture heterogeneous anomaly morphologies under similar contextual conditions. Extensive experiments on multiple real-world univariate and multivariate datasets demonstrate that CAST consistently outperforms state-of-the-art anomaly generation methods in terms of both generation fidelity and downstream task utility, highlighting the effectiveness of the proposed approach.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.27825 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T10:06:16.749Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).