{"total":21,"rows":[{"id":"2512.00193","title":"A Rosetta Stone for AI Benchmarks","created":"2025-11-28","cited_by_count":36,"area":null},{"id":"2605.21801","title":"Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2605.30504","title":"Auditing LLM Benchmarks with Item Response Theory","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2606.14516","title":"Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2604.01418","title":"Cost-Efficient Estimation of General Abilities Across Benchmarks","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2606.15643","title":"Extending Item Response Theory for Efficient and Meaningful Multilingual Evaluation","created":"2026-06-14","cited_by_count":2,"area":null},{"id":"2608.14425","title":"Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations","created":"2026-08-14","cited_by_count":2,"area":null},{"id":"2606.26429","title":"DualEval: Joint Model-Item Calibration for Unified LLM Evaluation","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2608.02966","title":"Every Wrong Answer Counts: Option-Level Psychometrics for LLM Multiple-Choice Benchmarks","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2602.12424","title":"RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.23514","title":"DepthCharge: A Domain-Agnostic Framework for Measuring Depth-Dependent Knowledge in Large Language Models","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.12843","title":"Growing Pains: Extensible and Efficient LLM Benchmarking Via Fixed Parameter Calibration","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.17110","title":"Capturing LLM Capabilities via Evidence-Calibrated Query Clustering","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.07422","title":"The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.09878","title":"FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2608.00014","title":"CoT-Core: Accelerating LLM Evaluation via CoT-Aware Coreset Selection","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.12426","title":"Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.14903","title":"Frontier AI Forecasting Has a Measurement Problem: An Audit of Progress Evidence","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.20392","title":"Evaluation-as-Search: Adaptive Discovery of Grounding Failures in Meeting Assistants","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.12475","title":"Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.18248","title":"Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}