AWhat changed
Fits example-specific surrogate functions to outcomes of models retrained on sampled training subsets, supporting prediction-counterfactual analysis, data relationships and leakage inspection.
Scientific scope
Fits example-specific surrogate functions to outcomes of models retrained on sampled training subsets, supporting prediction-counterfactual analysis, data relationships and leakage inspection. Models the distribution induced by a fixed learning algorithm, not one checkpoint’s complete explanation. Linear/L1 surrogates and subset distributions are choices, with substantial retraining cost; empirical correlations do not certify all out-of-distribution subsets. First three authors explicitly equal.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Models the distribution induced by a fixed learning algorithm, not one checkpoint’s complete explanation. Linear/L1 surrogates and subset distributions are choices, with substantial retraining cost; empirical correlations do not certify all out-of-distribution subsets. First three authors explicitly equal.
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