SEP 6, 2026 · PREPRINT
Are Verifier Errors Independent Within a GRPO Group? Evidence from Qwen2.5 Rollouts
arXiv
An empirical analysis of verifier error dependence in a large dataset from a single model, identifying a real statistical phenomenon (within-group correlation of 0.530) that challenges an independence assumption in RLVR; the work is descriptive and exploratory rather than hypothesis-testing, has not been peer reviewed, and does not evaluate a clinical or therapeutic intervention.
PreliminaryEsther Xin
Reported
Pooled within-group verifier-erro…0.530
95% confidence interval for corre…0.500–0.560
Design-effect-adjusted effective…1.70