BWhat changed
Combined archive-parent sampling, code-novelty rejection and bandit-based model selection to allocate program-evolution attempts, testing sample efficiency across computational tasks.
Scientific scope
Combined archive-parent sampling, code-novelty rejection and bandit-based model selection to allocate program-evolution attempts, testing sample efficiency across computational tasks. Evolutionary program search and LLM mutation are inherited. Acquired method/framework is distinct from claiming every generated candidate is mathematically novel or correct; reported packing/optimization improvements require task-specific independent checks. No search/program execution was run here.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Evolutionary program search and LLM mutation are inherited. Acquired method/framework is distinct from claiming every generated candidate is mathematically novel or correct; reported packing/optimization improvements require task-specific independent checks. No search/program execution was run here.
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.
- ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
- Lange et al.: novelty-filtered sample-efficient program evolution — author/institutional project
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