# Causal Discovery for Explainable AI: A Dual-Encoding Approach

arXiv: https://arxiv.org/abs/2601.21221 · HTML: https://mlsanity.com/paper/2601.21221/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 8 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 5 of 5)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Causal-learn: Causal Discovery in Python](https://mlsanity.com/paper/2307.16405/) (2023)
- [Causal Discovery from Time Series with Hybrids of Constraint-Based and Noise-Based Algorithms](https://mlsanity.com/paper/2306.08765/) (2023)
- [Detecting Statistically Significant Fairness Violations in Recidivism Forecasting Algorithms](https://mlsanity.com/paper/2511.11575/) (2025)

## Built on by (most cited first, 2 of 2)

- [LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations](https://mlsanity.com/paper/2605.16538/) (2026)
- [A Causal Argumentation Method for Explainability of Machine Learning Models](https://mlsanity.com/paper/2605.21758/) (2026)

## Abstract (arXiv)

Understanding causal relationships among features is fundamental for explaining machine learning model decisions. However, traditional causal discovery methods face challenges with categorical variables due to numerical instability in conditional independence testing. We propose a dual-encoding causal discovery approach that addresses these limitations by running constraint-based algorithms with complementary encoding strategies and merging results through majority voting. Applied to the Titanic dataset, our method identifies causal structures that align with established explainable methods.