AWhat changed
Uses implicit Hessian-vector products and inverse-Hessian approximations to estimate how training-point reweighting or perturbations affect model predictions, with selected data-debugging experiments.
Scientific scope
Uses implicit Hessian-vector products and inverse-Hessian approximations to estimate how training-point reweighting or perturbations affect model predictions, with selected data-debugging experiments. Inherits influence functions from robust statistics and second-order optimization. Formal local derivation needs differentiability and positive-definite Hessian; nonconvex/nonsmooth applications use approximations, not exact leave-one-out retraining. No universal reliability claim.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits influence functions from robust statistics and second-order optimization. Formal local derivation needs differentiability and positive-definite Hessian; nonconvex/nonsmooth applications use approximations, not exact leave-one-out retraining. No universal reliability claim.
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