AWhat changed
Extends weight editing to many associations by solving covariance-regularized batch updates and distributing desired hidden-state residuals across mediating transformer MLP layers.
Scientific scope
Extends weight editing to many associations by solving covariance-regularized batch updates and distributing desired hidden-state residuals across mediating transformer MLP layers. Single-layer least-squares derivation assumes the old memory optimum; practical covariance estimation and multi-layer residual spreading are approximations. Thousands-of-edit evaluations do not imply arbitrary sequential editing or preservation of all knowledge.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Single-layer least-squares derivation assumes the old memory optimum; practical covariance estimation and multi-layer residual spreading are approximations. Thousands-of-edit evaluations do not imply arbitrary sequential editing or preservation of all knowledge.
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