The paper introduces the mutatis mutandis (MM) comparator as a causal alternative to the ceteris paribus (CP) comparator in discrimination testing, arguing that MM enables more realistic complainant-comparator pairs and creates new opportunities for machine learning methods.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Proposes a formal DP-compatible framework with three unfairness measures (mutual information with TV proxy, MaxSAT-based repair, top-k tuple contribution) that satisfy positivity, monotonicity, and computability.
citing papers explorer
-
Mutatis Mutandis: Revisiting the Comparator in Discrimination Testing
The paper introduces the mutatis mutandis (MM) comparator as a causal alternative to the ceteris paribus (CP) comparator in discrimination testing, arguing that MM enables more realistic complainant-comparator pairs and creates new opportunities for machine learning methods.
-
Measuring Database Unfairness via Dependency Quantification Under Differential Privacy
Proposes a formal DP-compatible framework with three unfairness measures (mutual information with TV proxy, MaxSAT-based repair, top-k tuple contribution) that satisfy positivity, monotonicity, and computability.