# Modeling Discrimination with Causal Abstraction

arXiv: https://arxiv.org/abs/2501.08429 · HTML: https://mlsanity.com/paper/2501.08429/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 82 references that are in the map.
- First posted on arXiv 14 Jan 2025.

## Builds on (most cited first, 16 of 16)

- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [Causal Consistency of Structural Equation Models](https://mlsanity.com/paper/1707.00819/) (2017)
- [Approximate Causal Abstraction](https://mlsanity.com/paper/1906.11583/) (2019)
- [Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation](https://mlsanity.com/paper/2205.04610/) (2022)
- [Causal Fairness Analysis](https://mlsanity.com/paper/2207.11385/) (2022)
- [What's Sex Got To Do With Fair Machine Learning?](https://mlsanity.com/paper/2006.01770/) (2020)
- [Causal Conceptions of Fairness and their Consequences](https://mlsanity.com/paper/2207.05302/) (2022)
- [Compositional Abstraction Error and a Category of Causal Models](https://mlsanity.com/paper/2103.15758/) (2021)
- [Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions](https://mlsanity.com/paper/2306.14351/) (2023)
- [Is Causal Reasoning Harder than Probabilistic Reasoning?](https://mlsanity.com/paper/2111.13936/) (2021)
- [Phenomenological Causality](https://mlsanity.com/paper/2211.09024/) (2022)
- [The Hardness of Reasoning about Probabilities and Causality](https://mlsanity.com/paper/2305.09508/) (2023)

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

- [Causal Counterfactuals Reconsidered](https://mlsanity.com/paper/2512.12804/) (2025)
- [Causal Feature Learning in the Social Sciences](https://mlsanity.com/paper/2503.12784/) (2025)

## Abstract (arXiv)

A person is directly racially discriminated against only if her race caused her worse treatment. This implies that race is an attribute sufficiently separable from other attributes to isolate its causal role. But race is embedded in a nexus of social factors that resist isolated treatment. If race is socially constructed, in what sense can it cause worse treatment? Some propose that the perception of race, rather than race itself, causes worse treatment. Others suggest that since causal models require textitmodularity, i.e. the ability to isolate causal effects, attempts to causally model discrimination are misguided. This paper addresses the problem differently. We introduce a framework for reasoning about discrimination, in which race is a high-level textitabstraction of lower-level features. In this framework, race can be modeled as itself causing worse treatment. Modularity is ensured by allowing assumptions about social construction to be precisely and explicitly stated, via an alignment between race and its constituents. Such assumptions can then be subjected to normative and empirical challenges, which lead to different views of when discrimination occurs. By distinguishing constitutive and causal relations, the abstraction framework pinpoints disagreements in the current literature on modeling discrimination, while preserving a precise causal account of discrimination.