{"total":29,"rows":[{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156,"area":null},{"id":"2509.11106","title":"Fluid Language Model Benchmarking","created":"2025-09-14","cited_by_count":35,"area":null},{"id":"2506.07673","title":"How Benchmark Prediction from Fewer Data Misses the Mark","created":"2025-06-09","cited_by_count":28,"area":null},{"id":"2511.04689","title":"Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks","created":"2025-10-26","cited_by_count":28,"area":null},{"id":"2507.18074","title":"Neural Architecture Discovery via Autonomous Evolution","created":"2025-07-24","cited_by_count":16,"area":null},{"id":"2510.26384","title":"Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings","created":"2025-10-30","cited_by_count":11,"area":null},{"id":"2510.10457","title":"Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data?","created":"2025-10-12","cited_by_count":8,"area":null},{"id":"2510.07959","title":"DISCO: Diversifying Sample Condensation for Efficient Model Evaluation","created":"2025-10-09","cited_by_count":5,"area":null},{"id":"2601.13885","title":"Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores","created":"2026-01-20","cited_by_count":5,"area":null},{"id":"2607.15190","title":"Can We Trust Item Response Theory for AI Evaluation?","created":"2026-07-16","cited_by_count":4,"area":null},{"id":"2603.00063","title":"Measuring What AI Systems Might Do: Towards A Measurement Science in AI","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2606.24020","title":"You Don't Need to Run Every Eval","created":"2026-06-22","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":"2604.23099","title":"ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation","created":"2026-04-25","cited_by_count":2,"area":null},{"id":"2605.25773","title":"Efficient Benchmarking Is Just Feature Selection and Multiple Regression","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.07616","title":"Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2606.07726","title":"Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2504.19811","title":"Can a Crow Hatch a Falcon? Lineage Matters in Predicting Large Language Model Performance","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2604.11328","title":"Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2607.20464","title":"Stochastic Sampling is Epistemically Shallow: The Dimensionality Gap Between Temperature Variation and Model Diversity in LLMs","created":"2026-05-18","cited_by_count":1,"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":"2606.09878","title":"FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.01152","title":"AGC-Bench: Measuring Artificial General Creativity","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.05052","title":"Beyond Independent Labels: Schwartz-Geometry Decoding for Human Value Detection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.27023","title":"BayesAME: Bayesian Active Model Evaluation","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.31184","title":"Accounting for Bias Enables Sustainable LLM Evaluation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.01627","title":"What Makes Something Hard(er)? Explaining Question Difficulty in Natural Language","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.20099","title":"EvalBuilder: Can LLMs Build Efficient Benchmarks?","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}