{"total":16,"rows":[{"id":"2605.12673","title":"Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack","created":"2026-05-12","cited_by_count":14,"area":null},{"id":"2601.08778","title":"Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboards","created":"2026-01-13","cited_by_count":13,"area":null},{"id":"2506.10954","title":"SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks","created":"2025-06-12","cited_by_count":7,"area":null},{"id":"2510.06296","title":"VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code","created":"2025-10-07","cited_by_count":7,"area":null},{"id":"2603.16140","title":"Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards","created":"2026-03-17","cited_by_count":5,"area":null},{"id":"2605.26321","title":"Anchor: Mitigating Artifact Drift in Agent Benchmark Generation","created":"2026-05-25","cited_by_count":5,"area":null},{"id":"2604.12268","title":"CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2608.04975","title":"SciCode-Verified: How Benchmark Defects Underestimated the Scientific-Coding Ability of Language Models","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2601.08806","title":"APEX-SWE","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2609.37315","title":"Do Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments","created":"2026-09-29","cited_by_count":2,"area":null},{"id":"2601.15728","title":"Benchmarking Text-to-Python against Text-to-SQL: The Impact of Explicit Logic and Ambiguity","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2604.04324","title":"RESCORE: LLM-Driven Simulation Recovery in Control Systems Research Papers","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2607.28587","title":"PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.13547","title":"QuoteBench: How Matched Scores Can Hide Command-Path Failures","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2606.14357","title":"No Accidental Software Agent First Canonical Code for Human Code Entropy Reduction and 30 to 500 times Lower Frontier Model Requirements","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2608.18280","title":"What Makes Software Issue Resolution Tasks Difficult for Agents?","created":"2026-08-18","cited_by_count":0,"area":null}],"next_cursor":null}