A model-agnostic adaptive conformal anomaly detection approach uses weighted quantile bounds learned from past foundation model predictions to deliver interpretable p-value scores with stable calibration under shifts for time series monitoring.
arXiv preprint arXiv:2412.20512 (2024)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
Time-RA reformulates time series anomaly detection as a reasoning-intensive generative task and provides the RATs40K multimodal benchmark to evaluate and improve LLM-based diagnosis.
citing papers explorer
-
Adaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoring
A model-agnostic adaptive conformal anomaly detection approach uses weighted quantile bounds learned from past foundation model predictions to deliver interpretable p-value scores with stable calibration under shifts for time series monitoring.
-
Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback
Time-RA reformulates time series anomaly detection as a reasoning-intensive generative task and provides the RATs40K multimodal benchmark to evaluate and improve LLM-based diagnosis.