This release adds 5 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+9 more
Affected surfaces
Summary
AI summaryAdds a clinical AI bias audit and four new explainers on foundational AI topics.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Add explainer: Why AI Hallucinates Add explainer: Why AI Hallucinates Source: llm_adapter@2026-06-09 Confidence: high |
— |
| Feature | Medium |
Add explainer: What Is Proxy Entanglement Add explainer: What Is Proxy Entanglement Source: llm_adapter@2026-06-09 Confidence: high |
— |
| Feature | Medium |
Add reinforcement‑learning.md explainer Add reinforcement‑learning.md explainer Source: llm_adapter@2026-06-09 Confidence: high |
— |
| Feature | Medium |
Add bias audit: Healthcare Readmission (Diabetes 130‑US Hospitals) with proxy entanglement analysis Add bias audit: Healthcare Readmission (Diabetes 130‑US Hospitals) with proxy entanglement analysis Source: llm_adapter@2026-06-09 Confidence: high |
— |
| Dependency | Low |
Update matplotlib requirement to >=3.10.9 Update matplotlib requirement to >=3.10.9 Source: llm_adapter@2026-06-09 Confidence: high |
— |
| Dependency | Low |
Update pandas requirement to >=3.0.3 Update pandas requirement to >=3.0.3 Source: llm_adapter@2026-06-09 Confidence: high |
— |
| Dependency | Low |
Update numpy requirement to >=2.4.6 Update numpy requirement to >=2.4.6 Source: llm_adapter@2026-06-09 Confidence: high |
— |
| Dependency | Low |
Update scikit-learn requirement to >=1.9.0 Update scikit-learn requirement to >=1.9.0 Source: llm_adapter@2026-06-09 Confidence: high |
— |
| Bugfix | Medium |
Fix First Interaction Trigger Change and enhance Audits Workflow Fix First Interaction Trigger Change and enhance Audits Workflow Source: llm_adapter@2026-06-09 Confidence: high |
— |
| Refactor | Low |
Refactor dataset structure documentation in README.md Refactor dataset structure documentation in README.md Source: llm_adapter@2026-06-09 Confidence: high |
— |
Full changelog
Fair Code's second tagged release. Adds the sixth bias audit — clinical AI — plus four new explainers covering foundational AI concepts.
What's included
1 bias audit
Healthcare Readmission (Diabetes 130-US Hospitals, 101,766 records) — Race: 25% reduction, Age: 68% reduction, Gender: +100% ↑ (gap worsened — proxy removal backfired. Payer code was suppressing the gender signal while also encoding it. Remove it, and the suppression disappears. This is proxy entanglement — and pre-processing mitigation can't fix it. That's a future audit.)
4 explainers
What Happens Inside a Neural Network
Why AI Hallucinates
What Is Reinforcement Learning
What Is Proxy Entanglement
6 Jupyter notebooks — full walkthrough of every audit with visualisations and proxy detection
Live website — fair-code-five.vercel.app
CI pipeline — all audit scripts run automatically on every push and PR
What's Changed
- Update matplotlib requirement from >=3.10.8 to >=3.10.9 by @dependabot[bot] in https://github.com/yakew7/Fair-Code/pull/37
- Update pandas requirement from >=3.0.2 to >=3.0.3 by @dependabot[bot] in https://github.com/yakew7/Fair-Code/pull/38
- Update numpy requirement from >=2.4.4 to >=2.4.6 by @dependabot[bot] in https://github.com/yakew7/Fair-Code/pull/39
- Update scikit-learn requirement from >=1.8.0 to >=1.9.0 by @dependabot[bot] in https://github.com/yakew7/Fair-Code/pull/41
- Refactor dataset structure in README.md by @yakew7 in https://github.com/yakew7/Fair-Code/pull/42
- Explainer: Why AI Hallucinates Added by @Shreyash0712 in https://github.com/yakew7/Fair-Code/pull/43
- Update README with new document and formatting changes by @yakew7 in https://github.com/yakew7/Fair-Code/pull/44
- Update CHANGELOG.md for version 1.1.0 by @yakew7 in https://github.com/yakew7/Fair-Code/pull/45
- Fix: First Interaction Trigger Change, Audits Workflow Enhancement and Version Upgrade by @Shreyash0712 in https://github.com/yakew7/Fair-Code/pull/46
- Delete .github/workflows/update-changelog.yml by @yakew7 in https://github.com/yakew7/Fair-Code/pull/47
- Create reinforcement-learning.md by @evanjain-dot in https://github.com/yakew7/Fair-Code/pull/48
- Create explainer for Proxy Entanglement by @yakew7 in https://github.com/yakew7/Fair-Code/pull/49
- Add proxy-entanglement.md to contributing guidelines by @yakew7 in https://github.com/yakew7/Fair-Code/pull/50
New Contributors
- @dependabot[bot] made their first contribution in https://github.com/yakew7/Fair-Code/pull/37
- @yakew7 made their first contribution in https://github.com/yakew7/Fair-Code/pull/42
- @Shreyash0712 made their first contribution in https://github.com/yakew7/Fair-Code/pull/43
Full Changelog: https://github.com/yakew7/Fair-Code/compare/v1.0.0...v1.1.0
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About yakew7/Fair-Code
All releases →Related context
Related tools
Beta — feedback welcome: [email protected]