Interventional Time Series Priors for Causal Foundation Models

2026-03-11

AI Summary

Existing time series benchmarks lack interventional data, hindering the training of causal foundation models. To address this gap, this work proposes CausalTimePrior, a framework that introduces the first synthetic time series structural causal model (TSCM) capable of generating paired observational and interventional data. The framework supports configurable causal graphs, nonlinear autoregressive mechanisms, state-switching dynamics, and diverse intervention types—including hard, soft, and time-varying interventions. Prior-data fitting networks (PFNs) trained within this framework demonstrate effective in-context estimation of causal effects on unseen TSCMs, underscoring the framework’s pivotal role in advancing causal foundation models for time series.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

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 \textbf{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.

Problem

• interventional time series
• causal foundation models
• synthetic data generation
• temporal structural causal models
• causal inference

Innovation

• CausalTimePrior
• temporal structural causal models
• interventional time series
• causal foundation models
• prior-data fitted networks