AWhat changed
Introduces model-parameter and data-label randomization tests for explanation methods, revealing that some visually persuasive saliency procedures can ignore learned model or label structure.
Scientific scope
Introduces model-parameter and data-label randomization tests for explanation methods, revealing that some visually persuasive saliency procedures can ignore learned model or label structure. Sensitivity to these tests is a necessary task-dependent diagnostic, not sufficient proof of explanation correctness. Invariance findings are scoped to tested methods, metrics and architectures; signed and absolute visualizations can behave differently. Star denotes Google residency, not equal contribution.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Sensitivity to these tests is a necessary task-dependent diagnostic, not sufficient proof of explanation correctness. Invariance findings are scoped to tested methods, metrics and architectures; signed and absolute visualizations can behave differently. Star denotes Google residency, not equal contribution.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction