the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2016

    Inherent Trade-Offs in the Fair Determination of Risk Scores

    Jon Kleinberg (first author) · 2016

    Read the original

    DOI 10.4230/lipics.itcs.2017.43arXiv 1609.05807OpenAlex W2962922665

    On the reading lists

    Why it matters

    Proved that fundamental group fairness criteria cannot generally be satisfied simultaneously.

    Condensed from the expert lists' notes.

    Reading it

    Difficulty: Intermediate

    Read this first: probability; calibration.

    The record

    First released
    2016 (from arXiv 1609.05807)
    Citations
    2,210 citations, as counted by Semantic Scholar logoSemantic Scholar (non-commercial licence)
    Named by
    both expert lists
    Score
    0.564 · computed rank 175 · consensus 0.85, must-read 1, citations percentile 0.596 (2010s · safety), awards 0, existing lists 0. Method

    Editor's notes

    • Readability check: pass: A short impossibility result every fairness discussion relies on. (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 logoSemantic Scholar (used under its non-commercial API licence). Each count names its source. See the method.