A Proof System with Causal Labels (Part II): checking Counterfactual Fairness

2025/07/19 by Ceragioli, Leonardo, Primiero, Giuseppe
#F.4 #FOS: Computer and information sciences #I.2.3 #I.2.4 #Logic in Computer Science (cs.LO)

paper · doi:10.48550/arxiv.2507.14655

Abstract

In this article we propose an extension to the typed natural deduction calculus TNDPQ to model verification of counterfactual fairness in probabilistic classifiers. This is obtained formulating specific structural conditions for causal labels and checking that evaluation is robust under their variation.

Citations

• A Proof System with Causal Labels (Part I): checking Individual Fairness and Intersectionality
• Trustworthiness Preservation by Copies of Machine Learning Systems
• Evaluating AI fairness in credit scoring with the BRIO tool

Related

• A Proof System with Causal Labels (Part I): checking Individual Fairness and Intersectionality
• Probabilistic Reasoning across the Causal Hierarchy
• Shortcomings of Counterfactual Fairness and a Proposed Modification
• PC-Fairness: A Unified Framework for Measuring Causality-based Fairness
• Learning Counterfactually Fair Models via Improved Generation with Neural Causal Models