Derives an exact telescoping decomposition of the naive RLVR reward-design estimator into null, elicitation, and reward-design terms on a tabular-GRPO simulator, measures the components across prior strengths, and validates via pre-registered factorial experiments plus re-audits of prior papers.
2103.03098 , archivePrefix=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Presents a fail-closed certification protocol for determining when forecasting leaderboard winners are deployment-actionable, using a traffic dataset to show friction-induced reversals and an audit to prevent overclaiming.
Configuration choices alone flip pairwise safety verdicts on every tested alignment benchmark, isolated via a finite-envelope proposition linking disagreement rate to strict ordering reversal.
QuickScope uses modified COUP Bayesian optimization to find truly difficult questions in dynamic LLM benchmarks more sample-efficiently than baselines while cutting false positives.
citing papers explorer
-
A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR
Derives an exact telescoping decomposition of the naive RLVR reward-design estimator into null, elicitation, and reward-design terms on a tabular-GRPO simulator, measures the components across prior strengths, and validates via pre-registered factorial experiments plus re-audits of prior papers.
-
From Forecasting Leaderboards to Deployment Decisions: A Fail-Closed Certification Protocol
Presents a fail-closed certification protocol for determining when forecasting leaderboard winners are deployment-actionable, using a traffic dataset to show friction-induced reversals and an audit to prevent overclaiming.
-
SafetyRepro: Configuration-Conditional Rank Instability on Alignment Benchmarks
Configuration choices alone flip pairwise safety verdicts on every tested alignment benchmark, isolated via a finite-envelope proposition linking disagreement rate to strict ordering reversal.
-
QuickScope: Certifying Hard Questions in Dynamic LLM Benchmarks
QuickScope uses modified COUP Bayesian optimization to find truly difficult questions in dynamic LLM benchmarks more sample-efficiently than baselines while cutting false positives.