Unmasking Clever Hans Predictors and Assessing What Machines Really Learn¶
Lapuschkin, S., Wäldchen, S., Binder, A., Montavon, G., Samek, W., & Müller, K. (2019). Unmasking Clever Hans Predictors and Assessing What Machines Really Learn. Nature Communications.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Mechanisms¶
- Model-Debugging Hypothesis Loop
- Its failure mode is declaring victory when the model only appears fixed — a spurious cue makes the behavior look explained while the real mechanism is untouched, the Clever Hans effect transplanted into ML.
This sourceShows that apparently successful machine-learning behavior can depend on spurious cues rather than the intended mechanism, a Clever Hans effect.
- Its failure mode is declaring victory when the model only appears fixed — a spurious cue makes the behavior look explained while the real mechanism is untouched, the Clever Hans effect transplanted into ML.
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? Not recorded. The single citation of this work carries no 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:03c1232aaeb7 · see in the full table