# Modeling and Discovering Direct Causes for Predictive Models

arXiv: https://arxiv.org/abs/2412.02878 · HTML: https://mlsanity.com/paper/2412.02878/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 45 references that are in the map.
- First posted on arXiv 3 Dec 2024.

## Builds on (most cited first, 4 of 4)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [On The Reasons Behind Decisions](https://mlsanity.com/paper/2002.09284/) (2020)
- [Three Modern Roles for Logic in AI](https://mlsanity.com/paper/2004.08599/) (2020)

## Abstract (arXiv)

We introduce a causal modeling framework that captures the input-output behavior of predictive models (e.g., machine learning models). The framework enables us to identify features that directly cause the predictions, which has broad implications for data collection and model evaluation. We then present sound and complete algorithms for discovering direct causes (from data) under some assumptions. Furthermore, we propose a novel independence rule that can be integrated with the algorithms to accelerate the discovery process, as we demonstrate both theoretically and empirically.