{"total":13,"rows":[{"id":"2605.25492","title":"SafetyRepro: Configuration-Conditional Rank Instability on Alignment Benchmarks","created":"2026-05-25","cited_by_count":15,"area":null},{"id":"2605.28873","title":"Pre-Registering the Detectable Effect: A Paired-MDE Budget for 4-bit Quantization Benchmarks, with a Pilot Audit","created":"2026-05-25","cited_by_count":8,"area":null},{"id":"2605.30237","title":"GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases","created":"2026-05-28","cited_by_count":7,"area":null},{"id":"2605.29253","title":"OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2608.07556","title":"MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures","created":"2026-08-02","cited_by_count":4,"area":null},{"id":"2606.04867","title":"AICompanionBench: Benchmarking LLMs-as-Judges for AI Companion Safety","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2607.02586","title":"Auditing the Audit: Five Failure Modes in Benchmark-Validity Audits","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2607.19913","title":"JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2605.22568","title":"Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.30089","title":"Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.30651","title":"Can Physician Expertise Improve Machine Learning Identification of Delirium?","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2610.17685","title":"LatentRiskBench: Measuring State-Dependent Risks in Enterprise Agents","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18603","title":"AgentStripes: An Evidence-Graded Maturity Model for AI Agents","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}