{"total":15,"rows":[{"id":"2103.05331","title":"Active Testing: Sample-Efficient Model Evaluation","created":"2021-03-09","cited_by_count":82,"area":null},{"id":"2101.11665","title":"On Statistical Bias In Active Learning: How and When To Fix It","created":"2021-01-27","cited_by_count":75,"area":null},{"id":"2107.00643","title":"Mandoline: Model Evaluation under Distribution Shift","created":"2021-07-01","cited_by_count":55,"area":null},{"id":"2508.09093","title":"Scaling Up Active Testing to Large Language Models","created":"2025-08-12","cited_by_count":13,"area":null},{"id":"2507.23771","title":"Consensus-Driven Active Model Selection","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2109.05720","title":"Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories","created":"2021-09-13","cited_by_count":7,"area":null},{"id":"2306.03151","title":"DISCount: Counting in Large Image Collections with Detector-Based Importance Sampling","created":"2023-06-05","cited_by_count":7,"area":null},{"id":"2507.01372","title":"Active Measurement: Efficient Estimation at Scale","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2109.12043","title":"Sample Efficient Model Evaluation","created":"2021-09-24","cited_by_count":4,"area":null},{"id":"2603.21840","title":"Select, Label, Evaluate: Active Testing in NLP","created":"2026-03-23","cited_by_count":3,"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":"2512.20854","title":"How important is Recall for Measuring Retrieval Quality?","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2602.07226","title":"Fault-Tolerant Evaluation for Sample-Efficient Model Performance Estimators","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2609.08399","title":"MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.38096","title":"Tail-Influence Sampling for CVaR Policy Evaluation","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}