Skip to content

fix: doc corrections for COMPAS reduction, Benefits Denial proxies, ROADMAP staleness (fixes #545, #546, #555) - #557

Merged
yakew7 merged 6 commits into
yakew7:mainfrom
slsgzs-cloud:fix-docs-545-546-554-555-556
Sep 10, 2026
Merged

fix: doc corrections for COMPAS reduction, Benefits Denial proxies, ROADMAP staleness (fixes #545, #546, #555)#557
yakew7 merged 6 commits into
yakew7:mainfrom
slsgzs-cloud:fix-docs-545-546-554-555-556

Conversation

@slsgzs-cloud

Copy link
Copy Markdown
Contributor

Fixes #545, #546, #555

Three documentation corrections found by cross-referencing audit configs with their README claims.

#545 — COMPAS '71%' used raw percentage points instead of relative reduction

Every other audit in the Results-at-a-Glance table uses (before − after) / before. COMPAS's row alone used the raw point difference (86.77 − 15.69 = 71.08 → '71%'). The correct relative reduction is (86.77 − 15.69) / 86.77 × 100 = 82%. Fixed in both COMPAS/README.md and the root README.md table.

#546 — Benefits Denial README omits fnlwgt from removed proxies

fair.py and audit.yaml both treat fnlwgt as a proxy, but the README listed only 4 proxies (Relationship, Marital Status, Hours, Occupation). Added fnlwgt to both Benefits Denial/README.md and the root table.

#555 — ROADMAP.md traction table stale

The table said 53 explainers / 28 contributors / 32 forks, contradicting the file's own Phase 1 status line ('60 explainers published') and METRICS.md badges. Updated to 60 explainers / 29 contributors / 33 forks. Also updated the Phase 1 status line to remove the 'expanding toward a 60+ library' phrasing since it has been reached.

@vercel

vercel Bot commented Sep 9, 2026

Copy link
Copy Markdown
Contributor

@slsgzs-cloud is attempting to deploy a commit to the yashkewlani2020-gmailcom's projects Team on Vercel.

A member of the Team first needs to authorize it.

@github-actions

github-actions Bot commented Sep 9, 2026

Copy link
Copy Markdown

@yakew7 @Shreyash0712 - new PR touching a path you own, please review.

@yakew7
yakew7 merged commit 18af05d into yakew7:main Sep 10, 2026
16 of 17 checks passed
yakew7 added a commit that referenced this pull request Sep 10, 2026
… numbers

PR #557's fix for issue #545 (COMPAS's "71%" reduction figure should be
"82%") did a substring replace of "71" that also matched two completely
unrelated statistics still containing that digit sequence:

- "Black Defendants | 84.71%" (COMPAS's fair-model high-risk rate) became
  "84.82%" - breaking the table's own arithmetic (84.82 - 69.02 = 15.80,
  not the stated 15.69% New Fairness Gap; the original 84.71% is the only
  value that reproduces 15.69% exactly).
- "Male applicants | 25.71%" / "Female applicants | 7.71%" (Benefits
  Denial's ineligibility rates, from a different audit entirely) became
  "25.82%" / "7.82%".

Both reverted to their real values, confirmed against each table's own
stated gap (84.71 - 69.02 = 15.69; 25.71 - 7.71 = 18.00) and against git
history (both lines were untouched by PR #558's more careful, scoped fix
for the same underlying issue, and by every other reference to these two
audits' rates elsewhere in the repo).
yakew7 added a commit that referenced this pull request Sep 10, 2026
Documents the newest explainer (#565), the CODEOWNERS grant to
@propcgamer20-png, 8 doc/code fixes (#557-564, #566, #567), and the
two direct fixes made during this review: the README.md regression
from #557's broad substring replacement, and the recurred
llms.txt/ROADMAP.md explainer-count drift after #565.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
yakew7 added a commit that referenced this pull request Sep 10, 2026
The combined #557/#558 bullet only credited the COMPAS-reduction and
Benefits Denial proxy fixes; #557 also updated ROADMAP.md's stale
traction table (29/33/60), which the bullet omitted.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

COMPAS's "71%" reduction figure uses the wrong formula - every other audit uses relative reduction, this one uses raw percentage points

2 participants