Causal Analysis for Time Series Foundation Models
This paper proposes a causal analysis framework to identify biases and failure modes in time series foundation models like Chronos-2 and TimesFM-2.5 by intervening on synthetic data generators, revealing specific vulnerabilities such as persistence overestimation and regime switch failures that likely stem from pretraining data limitations.
Original paper licensed under CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). This is an AI-generated explanation of the paper below. It is not written or endorsed by the authors. For technical accuracy, refer to the original paper. Read full disclaimer
Drowning in papers in your field?
Get daily digests of the most novel papers matching your research keywords — with technical summaries, in your language.