Safety, alignment & interpretability· 2018
Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification
On the reading lists
- #126 in the Top 500 (2026 edition)
- #13 in Safety, alignment & interpretability (2026 edition)
Why it matters
Exposed severe intersectional performance disparities in deployed commercial facial analysis systems.
Condensed from the expert lists' notes.
Reading it
Difficulty: Introductory
Read this first: classification accuracy and error rates.
The record
- First released
- 2018 (from OpenAlex)
- Citations
- 5,825 citations, as counted by
Semantic Scholar (non-commercial licence) - Named by
- both expert lists
- Score
- 0.630 · computed rank 126 · consensus 0.76, must-read 1, citations percentile 0.862 (2010s · safety), awards 0, existing lists 0. Method
Editor's notes
- Readability check: pass: A short, clear audit that shaped how fairness is measured. (AI draft (Claude), not yet reviewed, 2026-10-29)
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0), and Semantic Scholar (used under its non-commercial API licence). Each count names its source. See the method.