BWhat changed
Maintained weighted key/value covariance statistics and solved regularized test-time regressions using Chebyshev iteration, adding adaptive regularization, input-dependent decay and chunk-wise kernels.
Scientific scope
Maintained weighted key/value covariance statistics and solved regularized test-time regressions using Chebyshev iteration, adding adaptive regularization, input-dependent decay and chunk-wise kernels. Kalman-inspired ridge optimality applies to the stated regression, not arbitrary language-model prediction. Finite solver iterations approximate the solution; conditioning, precision, state dimension and gating matter. Constant memory is in sequence length, not model width or batch size; inherited Kalman filtering, ridge regression and Chebyshev iteration are not claimed new.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Kalman-inspired ridge optimality applies to the stated regression, not arbitrary language-model prediction. Finite solver iterations approximate the solution; conditioning, precision, state dimension and gating matter. Constant memory is in sequence length, not model width or batch size; inherited Kalman filtering, ridge regression and Chebyshev iteration are not claimed new.
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