Interventional Time Series Priors for Causal Foundation Models

arXiv:2603.11090v2 Announce Type: replace Abstract: Prior-data fitted networks (PFNs) have emerged as powerful foundation models for tabular causal inference, yet their extension to time series remains limited by the absence of synthetic data generators that provide interventional targets. Existing time series benchmarks generate observational data with ground-truth causal graphs but lack the interventional data required for training causal foundation models. To address this, we propose extbf{CausalTimePrior}, a principled framework for generating synthetic temporal structural causal models (TSCMs) with paired observational and interventional time series. Our prior supports configurable causal graph structures, nonlinear autoregressive mechanisms, regime-switching dynamics, and multiple intervention types (hard, soft, time-varying). We demonstrate that PFNs trained on CausalTimePrior can perform in-context causal effect estimation on held-out TSCMs, establishing a pathway toward foundation models for time series causal inference.

Related

• Bi-level Heterogeneous Learning for Time Series Foundation Models: A Federated Learning Approach
• Time-Series Classification with Multivariate Statistical Dependence Features
• SBBTS: A Unified Schrodinger-Bass Framework for Synthetic Financial Time Series
• From Classical Machine Learning to Tabular Foundation Models: An Empirical Investigation of Robustness and Scalability Under Class Imbalance in Emergency and Critical Care
• Active Statistical Inference

Source: arXiv cs.LG | 2026-04-10