Metraipolis › archive › dc_7ba5089cea9c

Anlu: Enabling In-Context Time Series Anomaly Detection in Foundation Models via Counterfactual Supervision — arXiv:2610.06180

Source
arXiv
Original
https://arxiv.org/abs/2610.06180
License (as archived)
CC0-1.0
Archived
2026-10-06T05:27:29.509Z
SHA-256 of the archived text
979277d14f0fb8d844626fe2f84805db58e383d342e5ff0d19a99cd41a2fa921
Stable URL of this page
https://metraipolis.com/documento/dc_7ba5089cea9c

How to cite

Anlu: Enabling In-Context Time Series Anomaly Detection in Foundation Models via Counterfactual Supervision — arXiv:2610.06180 — arXiv, https://arxiv.org/abs/2610.06180 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ba5089cea9c (Metraipolis archive dc_7ba5089cea9c, sha256 979277d14f0fb8d844626fe2f84805db58e383d342e5ff0d19a99cd41a2fa921)
BibTeX
@misc{dc7ba5089cea9c,
  title = {Anlu: Enabling In-Context Time Series Anomaly Detection in Foundation Models via Counterfactual Supervision — arXiv:2610.06180},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06180},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ba5089cea9c; sha256 979277d14f0fb8d844626fe2f84805db58e383d342e5ff0d19a99cd41a2fa921},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06180. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Whether a time-series pattern is anomalous often depends on the operating regime of the monitored process. A missing event can signal a fault in one regime and be routine in another, and the query alone may not reveal which regime applies. We study in-context learning (ICL) for time series anomaly detection (TSAD) through reference-conditioned detection, where a reference record provides evidence about expected behavior and model parameters remain fixed at inference. Supplying the reference is not enough: when training anomalies are recognizable from the query alone, the detector can fit its targets while ignoring the reference. We therefore introduce counterfactual supervision, which pairs one query with two references that support different normal rules and labels the query under each. At positions where the two labels disagree, no detector that ignores the reference can fit both targets. Anlu learns from this supervision by adding a reference memory and zero-initialized gated adapters to a frozen time-series foundation model (TSFM) pretrained for anomaly detection. On the 350 TSB-AD-U evaluation sequences, Anlu raises the mean VUS-PR of the frozen TSFM from 0.542 to 0.607. Replacing the reference with zeros lowers Anlu's score to 0.499.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.06180 — 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 2026-10-06T05:24:06.126Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).