{"total":22,"rows":[{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380,"area":null},{"id":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85,"area":null},{"id":"2311.08702","title":"Debate Helps Supervise Unreliable Experts","created":"2023-11-15","cited_by_count":43,"area":null},{"id":"2206.00512","title":"Neural Network Verification with Proof Production","created":"2022-06-01","cited_by_count":22,"area":null},{"id":"2506.13609","title":"Avoiding Obfuscation with Prover-Estimator Debate","created":"2025-06-16","cited_by_count":14,"area":null},{"id":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2211.17096","title":"PAC Verification of Statistical Algorithms","created":"2022-11-28","cited_by_count":8,"area":null},{"id":"2405.15722","title":"Models That Prove Their Own Correctness","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2412.08897","title":"Neural Interactive Proofs","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2410.13852","title":"Retrospective Learning from Interactions","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2503.22989","title":"FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2607.03561","title":"How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2602.23248","title":"Mitigating Legibility Tax with Decoupled Prover-Verifier Games","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2306.04505","title":"Hardness of Deceptive Certificate Selection","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2507.07532","title":"Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2608.06422","title":"Sharding Prevents LLM Oversight Failures and Adversarial Exploitation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.24895","title":"Human-LLM Deliberation as Interactive Proof: Conditions for Verifiability Without Transparency","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.32061","title":"Contract monitoring: governing AI via separation of powers","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.01514","title":"How the Audit Rule Shapes Faithful Factor Explanations in LLMs","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01995","title":"Can AI Oversight Be Zero Knowledge?","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02557","title":"How to Have a Sensitive Debate: An Instance-Optimal Protocol for AI Debate","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.17697","title":"LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}