Our lab is committed to open science and reproducibility. We share datasets, software tools, tutorials, and educational resources that support causal AI research and its applications. Unless otherwise noted, resources are freely available for research and educational purposes.
Datasets
Dataset A: Lorem Ipsum Time Series (2025)
Lorem ipsum dolor sit amet, consectetur adipiscing elit. A dataset of synthetic and real-world time series for causal discovery tasks.
Links: Download | DOI
Dataset B: Climate Impact Simulation (2024)
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Large-scale simulations of climate variables with causal structure annotations.
Links: Download | Documentation
Software & Code Tools
Tool A: CausalNet
Lorem ipsum dolor sit amet, consectetur adipiscing elit. A Python library for scalable causal structure discovery in time series.
Links: GitHub | Docs
Tool B: CRL-Dynamics
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Toolkit for causal representation learning in dynamical systems.
Links: GitHub | Tutorial Notebook
Tutorials / Teaching Resources
Tutorial A: Introduction to Causal Inference
Slides and Jupyter notebooks for a short workshop on the basics of causal discovery and interventions.
Links: Slides PDF | Notebook
Tutorial B: Causal AI in Climate Science
Workshop materials covering applications of causal AI to climate data.
Links: Slides PDF | Code
External Resources
- CausalML Library — widely used Python package for causal inference.
- DoWhy — framework for causal inference with multiple backends.
- Causal Discovery Toolbox — collection of algorithms for causal structure learning.