Re-evaluating four LLM code-efficiency benchmarks with 30-run statistical testing shows 93.89% of 'performant' implementations are indistinguishable from baselines; a multi-agent test-generation framework reveals hidden significant improvements in ~24% of previously non-significant tasks.
Breakthroughs in statistics: Methodology and distribution , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
CONDITIONAL 2representative citing papers
Neyman shot allocation driven by three closed-form GP pair sensitivities plus a 50% uniform floor yields 10–21% RMSE gains over uniform allocation for quantum-kernel Gaussian processes in the moderate-budget regime.
citing papers explorer
-
Rethinking Code Performance Benchmarks for LLMs
Re-evaluating four LLM code-efficiency benchmarks with 30-run statistical testing shows 93.89% of 'performant' implementations are indistinguishable from baselines; a multi-agent test-generation framework reveals hidden significant improvements in ~24% of previously non-significant tasks.
-
Active Quantum Kernel Acquisition for Gaussian Process Regression
Neyman shot allocation driven by three closed-form GP pair sensitivities plus a 50% uniform floor yields 10–21% RMSE gains over uniform allocation for quantum-kernel Gaussian processes in the moderate-budget regime.