About This Project

An educational resource for understanding how changes to training data affect AI model behavior.

Work in Progress

What is This?

Data Counterfactuals is an interactive explainer and research reference designed to help people understand the relationship between training data and model outcomes. It connects several research areas that are often studied separately:

The core insight is that all of these questions are asking variations of the same thing: "What would happen if we trained on different data?"

Current Status

This project is under active development. The interactive Grid explorer works, but many features are still being refined. The paper collections are curated but not comprehensive — they represent a starting point for exploring these research areas, not a complete literature review.

Contributions, corrections, and suggestions are welcome.

How Discussions Work

The Discuss/Feedback page connects to external discussion platforms where you can:

Discussions are hosted on GitHub to keep everything in one place alongside the source code. You can also open issues or pull requests directly on the repository.

Who Made This?

This project is part of a broader effort to make AI/ML concepts more accessible. It's open source and welcomes contributions.

View the source on GitHub

Related Projects