"Fairness Set and Forgotten: Mining Fairness Toolkit Usage in Open-Source Machine Learning Projects"

This repository contains the full replication package for the paper “Fairness Set and Forgotten: Mining Fairness Toolkit Usage in Open-Source Machine Learning Projects” (submitted to Information and Software Technology).Materials provided:Dataset of Repositories – A CSV file cataloguing all 1,096 GitHub repositories that import at least one fairness toolkit (AIF360, Fairlearn, Aequitas, etc.). Each entry records repository URL, stars, primary language, detected toolkit(s), and our manual classification label (e.g., ML Project, Academic, Replication Package).ML-Projects Subset – Source-level snapshots and commit metadata (5,777 commits) for the 20 repositories identified as active ML projects.API Catalogue – A machine-readable list of 100 + fairness-related API endpoints, annotated as Analytics or Solutions.Analysis Scripts – Python scripts and command-line utilities to (i) parse ASTs, detect toolkit calls, and extract evolution data, (ii) reproduce tables and figures in the paper, and (iii) regenerate the topic-model analysis of commit messages.Reproduction Guide – Step-by-step instructions and environment configuration (Conda YAML) to enable one-click replication on any POSIX system.