arXiv Machine Learning
Causal Analysis for Time Series Foundation Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jul 7
Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependence
arXiv:2607. 02623v1 Announce Type: new Abstract: Time series foundation models (TSFMs) have shown strong zero-shot forecasting performance, but their generalization in covariate-driven, non-stationary settings is underexplored.
arXiv AI
Jun 30
MACROCAST: A Vintage-Consistent Time Series Foundation Model for Real-Time Macroeconomic Forecasting
arXiv:2606. 28670v1 Announce Type: cross Abstract: We introduce MACROCAST, a lightweight Time Series Foundation Model (TSFM) for real-time macroeconomic forecasting.
arXiv Machine Learning
Jun 8
Time series Foundation Models based on Physics-Informed Synthetic Histories for Cold-Start Photovoltaic Forecasting
arXiv:2606. 07457v1 Announce Type: new Abstract: At commissioning time, Photovoltaic (PV) operators must forecast production before target-site observations are available, limiting the direct use of standard supervised forecasters.
arXiv Machine Learning
Jul 3
Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics
arXiv:2607. 01966v1 Announce Type: new Abstract: Low-voltage load forecasting is an important component in current and future energy systems with a high degree of electrification and decentralized generation.
arXiv Machine Learning
1d ago
Foundations without Fundamentals: Zero-Shot Blind Spots in Time Series FMs
The paper introduces SimpleTimeBench, a diagnostic suite testing basic temporal primitives like monotonic trends, periodic signals, and leading indicator covariates. It finds that prominent multivariate Time Series Foundation Models (Chronos‑2, Moirai, and Toto) often produce suboptimal zero‑shot forecasts for these simple patterns, and that fine‑tuning can improve specific tasks while harming performance on other fundamentals. These failures persist in real‑world sensor forecasting, indicating that current TSFMs may lack the inductive biases needed to capture straightforward relationships, thereby limiting their practical reliability.
arXiv Machine Learning
Sep 22
Time Series Foundation Models for Process Model Forecasting
arXiv:2512.07624v2 Announce Type: replace Abstract: Process Model Forecasting (PMF) aims to predict how the control-flow structure of a process evolves over time by modeling the temporal dynamics of...