AWhat changed
Addressed training/test prediction shift by ordering examples so supporting predictions and target statistics exclude the current label, combining practical ordered boosting and categorical-feature processing.
Scientific scope
Addressed training/test prediction shift by ordering examples so supporting predictions and target statistics exclude the current label, combining practical ordered boosting and categorical-feature processing. Original2017dynamic-boosting six-person byline differs from2018NeurIPS five-person CatBoost paper; source labels Liudmila Ostroumova Prokhorenkova/Prokhorenkova retained without resolving identity variants. Unbiased refers to specified residual/statistical mechanisms and assumptions, not a universally unbiased final estimator, absence of all leakage or dominance over every dataset.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Original2017dynamic-boosting six-person byline differs from2018NeurIPS five-person CatBoost paper; source labels Liudmila Ostroumova Prokhorenkova/Prokhorenkova retained without resolving identity variants. Unbiased refers to specified residual/statistical mechanisms and assumptions, not a universally unbiased final estimator, absence of all leakage or dominance over every dataset.
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