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.
Higher numbers are better for PA-F1, Affiliation-F, AUC-PR, VUS-PR; lower numbers are better for FPR, and calibration error (CalErr)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.