yakew7/Fair-Code

View on GitHub

Auditing algorithmic bias in criminal justice, hiring, lending, healthcare, welfare, and tenant screening: 7 open-source audits, measurable fairness gaps, and concrete fixes.

Stars: 47
Forks: 45
Open beginner issues: 3
Indexed issues: 17
Avg merge: 1h 56m
Merged PRs (30d): 96

Dominant language: HTML
License: MIT
Last GitHub push: Sep 17, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: good first issue help wanted

Beginner friendly Everything

Open All

17 open issues indexed

ROADMAP.md's checked-off "10-15 labelled issues open at all times" is currently false (7 open, 1 good-first-issue) Open

documentation

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

yakew7/Fair-Code#692 · Opened Sep 19, 2026
CONTRIBUTORS.md's Contributors list violates its own stated sort order for 2 entries Open

documentation good first issue

Difficulty 1/5 Under an hour Newbie friendliness 95/100

yakew7/Fair-Code#690 · Opened Sep 19, 2026
CHANGELOG.md and CONTRIBUTORS.md cite PR #632 and GitHub user @Voyagerroc-Lab, neither of which exist Open

bug documentation

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

yakew7/Fair-Code#689 · Opened Sep 19, 2026
07_tenant_screening_bias_audit.ipynb's Key Insight cites numbers that match nothing - not its own cells, not unfair.py/fair.py, not the README Open

documentation good first issue

Difficulty 1/5 Under an hour Newbie friendliness 94/100

yakew7/Fair-Code#688 · Opened Sep 19, 2026
06_healthcare_readmission_bias_audit.ipynb's Key Insight text contradicts the notebook's own printed output Open

documentation good first issue

Difficulty 1/5 Under an hour Newbie friendliness 95/100

yakew7/Fair-Code#687 · Opened Sep 19, 2026
02_hiring_bias_audit.ipynb is entirely broken - uses column names that don't exist anywhere in the dataset Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 74/100

yakew7/Fair-Code#686 · Opened Sep 19, 2026
01_compas_bias_audit.ipynb raises KeyError: 'race' and doesn't match its own claimed numbers even when patched Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 68/100

yakew7/Fair-Code#685 · Opened Sep 19, 2026
7 of 8 notebooks use repo-root-relative CSV paths that fail under normal Jupyter execution Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 78/100

yakew7/Fair-Code#684 · Opened Sep 19, 2026
profiler-ui.js's runText() misclassifies a valid .csv/.tsv file as JSON if its content starts with { or [ Open

bug

Difficulty 1/5 Under an hour Newbie friendliness 92/100

yakew7/Fair-Code#683 · Opened Sep 19, 2026
explainers-ui.js's resolveLinkTarget() computes paths as if running at site root, but its target pages live one directory down Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

yakew7/Fair-Code#682 · Opened Sep 19, 2026
Healthcare Readmission's Gender gap table hides that bias direction reverses between the biased and mitigated model Open

documentation

Difficulty 2/5 1-3 hours Newbie friendliness 92/100

yakew7/Fair-Code#681 · Opened Sep 19, 2026
scripts/freeze_paper_results.py's generated MANIFEST.md and docstring still say "what a paper should cite," contradicting the lifted freeze Open

bug documentation

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

yakew7/Fair-Code#680 · Opened Sep 19, 2026
Benefits Denial/fair.py's National-Origin proxy comment says "4.8%" where the real, printed gap is 4.40% Open

bug

Difficulty 1/5 Under an hour Newbie friendliness 95/100

yakew7/Fair-Code#679 · Opened Sep 19, 2026
All 7 audit READMEs' reproducibility checklists claim a stratified train/test split that no unfair.py/fair.py script performs Open

bug documentation

Difficulty 4/5 3-5 days Newbie friendliness 58/100

yakew7/Fair-Code#678 · Opened Sep 19, 2026
Explainer: What Is Distributionally Robust Optimization (DRO) for Fairness? Open

documentation help wanted

Difficulty 5/5 Over a week Newbie friendliness 48/100

yakew7/Fair-Code#544 · Opened Sep 9, 2026
Explainer: What Is Max-Min (Rawlsian) Fairness? Open

documentation help wanted

Difficulty 5/5 Over a week Newbie friendliness 35/100

yakew7/Fair-Code#543 · Opened Sep 9, 2026
model-drift.md cites a fabricated single-run gap/p-value for unfair.py (6.39%/p=0.348 instead of the real 7.16%/p=0.2564) Open

documentation good first issue help wanted

yakew7/Fair-Code#521 · 7 comments · 1 assignee · Opened Sep 9, 2026

yakew7/Fair-Code

Get new issues in your inbox