AWhat changed
Combined constrained crowdsourcing and validation of Winograd-style twin sentences with a lightweight filtering algorithm using fixed neural embeddings and ensembles of linear classifiers.
Scientific scope
Combined constrained crowdsourcing and validation of Winograd-style twin sentences with a lightweight filtering algorithm using fixed neural embeddings and ensembles of linear classifiers. Original v1 distinguishes 43,985 full instances from a 25,680-instance filtered set. Filtering reduces biases exposed by the selected representation and classifier family; it does not remove every possible shortcut.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Original v1 distinguishes 43,985 full instances from a 25,680-instance filtered set. Filtering reduces biases exposed by the selected representation and classifier family; it does not remove every possible shortcut.
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