the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2017

    Fair prediction with disparate impact: A study of bias in recidivism prediction instruments

    Alexandra Chouldechova (first author) · 2017

    Read the original

    DOI 10.1089/big.2016.0047arXiv 1703.00056OpenAlex W2543774860

    On the reading lists

    Why it matters

    Independently demonstrated incompatibilities between calibration and error-rate fairness across groups.

    Condensed from the expert lists' notes.

    The record

    First released
    2017 (from arXiv 1703.00056)
    Citations
    2,158 citations, as counted by OpenAlex (CC0)
    Named by
    the chatgpt list only
    Score
    0.303 · computed rank 602 · consensus 0.29, must-read 0, citations percentile 0.617 (2010s · safety), awards 0, existing lists 0. Method

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.