Towards a Rigorous Science of Interpretable Machine Learning.¶
Doshi-Velez, F., & Kim, B. (2017). Towards a Rigorous Science of Interpretable Machine Learning. arXiv preprint.
Cited by¶
2 citations across 2 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Causal Layered Analysis (CLA)
- Doshi-Velez and Kim (2017) make a closely related point about machine-learning interpretability, arguing that explanation must address multiple levels — surface predictions, model mechanics, and the design assumptions framing the problem.
This sourceDefines ML interpretability and proposes a taxonomy of evaluation, arguing explanation must address multiple levels (surface predictions, model mechanics, and the design assumptions framing the problem).
- Doshi-Velez and Kim (2017) make a closely related point about machine-learning interpretability, arguing that explanation must address multiple levels — surface predictions, model mechanics, and the design assumptions framing the problem.
- Interpretation
- … shows the structural pattern survives the loss of human convention; what remains is the directed move from medium to meaning under a framework — exactly the activity Doshi-Velez and Kim (2017) frame as the proper object of interpretability research, the explanation of a model's decision in terms a human can audit.
This sourceFrames ML interpretability as the activity of producing explanations of model decisions in terms a human auditor can evaluate, and proposes a taxonomy of evaluation (application-grounded, human-grounded, functionally-grounded) for that activity.
- … shows the structural pattern survives the loss of human convention; what remains is the directed move from medium to meaning under a framework — exactly the activity Doshi-Velez and Kim (2017) frame as the proper object of interpretability research, the explanation of a model's decision in terms a human can audit.
Verification¶
Does it exist? Not checked yet. This entry carries no identifier to resolve. It was extracted from the citation as written in the article, normalized, and deduplicated against the rest of the registry.
Does it back the claim? Not recorded. Neither this nor any other of the 2 citations of this work carries a recorded support check.
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:b8102f9c5f71 · see in the full table