{"ID":3083929,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T05:32:54.120957816Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05932","arxiv_id":"2606.05932","title":"A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR","abstract":"Reinforcement learning from verifiable rewards (RLVR) improves reasoning even when the reward signal is spurious -- assigning credit to the group-plurality answer rather than a ground-truth verifier. Practitioners commonly interpret naive = acc(TRUE) - acc(RANDOM) as the reward-design effect. We prove this estimand is systematically biased: it conflates self-consistency elicitation (sharpening the policy toward its modal answer via majority pseudo-reward) with genuine reward-design signal. Using a controlled tabular-GRPO simulator we derive an exact telescoping decomposition total = null + elicit + rd and measure each term across five prior-strength levels. The reward-design fraction of the naive estimator ranges from 0.139 at weak prior (ps=0.20) to 0.05 at strong prior (ps=0.80), with the elicitation term flipping sign at the self-consistency crossover. A pre-registered 2x2x2 factorial confirms non-additivity (interaction ratio 0.385; AxC effect -0.089). A points-vs-bounds pilot gate shows strong-prior regimes are point-identified while near-crossover regimes are only bounded. Re-audits of two named published results yield ELICITATION DOMINATED (elicitation share 0.98) and REWARD DESIGN DOMINATED (rd share 1.18) verdicts respectively, demonstrating the diagnostic value of the partition. We pre-commit to submit regardless of flip outcome; a non-flip is a finding of equal standing. We release a reusable one-command harness for any alignment paper to run the same audit.","short_abstract":"Reinforcement learning from verifiable rewards (RLVR) improves reasoning even when the reward signal is spurious -- assigning credit to the group-plurality answer rather than a ground-truth verifier. Practitioners commonly interpret naive = acc(TRUE) - acc(RANDOM) as the reward-design effect. We prove this estimand is...","url_abs":"https://arxiv.org/abs/2606.05932","url_pdf":"https://arxiv.org/pdf/2606.05932v1","authors":"[\"Yuze Gao\"]","published":"2026-06-04T09:35:54Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}