Counterfactual Explanations Without Opening the Black Box

Wachter, S., Mittelstadt, B., & Russell, C. (2018). Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR. Harvard Journal of Law & Technology, 31(2), 841-887.

Type

Journal article

Intellectual base

Primary research

Year

2018

Volume

31

Issue

2

Pages

841-887

DOI

10.2139/ssrn.3063289

DOI registrant

Elsevier

Link

https://doi.org/10.2139/ssrn.3063289

Cited from

psychology

Cited by

1 citation across 1 artifact.

Each citation links to the sentence it supports in the citing article.

Primes

• Counterfactual Reasoning
  • AI/ML fairness audits and counterfactual explanations. Wachter-Mittelstadt-Russell (2018)

    This sourceProposes generating the smallest input change that flips an automated decision, providing recourse and fairness audits.

    Supported in partVerified against the work's full text

    Wachter et al. do propose counterfactual explanations of automated decisions and say they can reveal dependence on protected variables, but they stress these are not a tool for systematic fairness audits.

    “counterfactuals can provide evidence that an algorithmic decision is affected by a protected variable (e.g. race)”

    Read by an automated reader; not a human review. How support was checked

Verification

Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.

Does it back the claim? Read against the text for 1 of 1 citation: 1 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.

Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.

See how references were verified.

Registry ID ref:fd24483c1fc6 · see in the full table