BWhat changed
Combined a prompt-component budget controller, iterative token compression and small-model distribution alignment to compress inputs for an otherwise black-box language model.
Scientific scope
Combined a prompt-component budget controller, iterative token compression and small-model distribution alignment to compress inputs for an otherwise black-box language model. Inherits selective-context/self-information compression. Removing low-perplexity tokens does not guarantee preserved meaning or answers on arbitrary inputs. Compression-model tuning/compute costs remain and historical API price savings are not current prices.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits selective-context/self-information compression. Removing low-perplexity tokens does not guarantee preserved meaning or answers on arbitrary inputs. Compression-model tuning/compute costs remain and historical API price savings are not current prices.
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