{"total":44,"rows":[{"id":"2501.09731","title":"Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI","created":"2025-01-16","cited_by_count":34,"area":null},{"id":"2406.04291","title":"Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2506.07949","title":"Cost-Optimal Active AI Model Evaluation","created":"2025-06-09","cited_by_count":19,"area":null},{"id":"2601.20251","title":"Efficient Evaluation of LLM Performance with Statistical Guarantees","created":"2026-01-28","cited_by_count":18,"area":null},{"id":"2406.07320","title":"A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimation","created":"2024-06-11","cited_by_count":14,"area":null},{"id":"2406.10490","title":"Active, anytime-valid risk controlling prediction sets","created":"2024-06-15","cited_by_count":14,"area":null},{"id":"2506.16658","title":"Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards","created":"2025-06-20","cited_by_count":14,"area":null},{"id":"2505.18659","title":"Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees","created":"2025-05-24","cited_by_count":11,"area":null},{"id":"2412.12910","title":"Sequential Harmful Shift Detection Without Labels","created":"2024-12-17","cited_by_count":10,"area":null},{"id":"2601.21471","title":"Best Arm Identification with LLM Judges and Limited Human","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2601.20819","title":"Demystifying Prediction Powered Inference","created":"2026-01-28","cited_by_count":9,"area":null},{"id":"2505.20178","title":"No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2506.10908","title":"Probably Approximately Correct Labels","created":"2025-06-12","cited_by_count":8,"area":null},{"id":"2411.12665","title":"Regression for the Mean: Auto-Evaluation and Inference with Few Labels through Post-hoc Regression","created":"2024-11-19","cited_by_count":7,"area":null},{"id":"2411.19908","title":"Another look at statistical inference with machine learning-imputed data","created":"2024-11-29","cited_by_count":7,"area":null},{"id":"2502.02363","title":"FAB-PPI: Frequentist, Assisted by Bayes, Prediction-Powered Inference","created":"2025-02-04","cited_by_count":7,"area":null},{"id":"2505.18000","title":"Anytime-valid, Bayes-assisted, Prediction-Powered Inference","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2605.05973","title":"Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking","created":"2026-05-07","cited_by_count":7,"area":null},{"id":"2511.08991","title":"Robust Sampling for Active Statistical Inference","created":"2025-11-12","cited_by_count":6,"area":null},{"id":"2509.14218","title":"Adaptive Off-Policy Inference for M-Estimators Under Model Misspecification","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2601.21470","title":"PPI-SVRG: Unifying Prediction-Powered Inference and Variance Reduction for Semi-Supervised Optimization","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2604.18569","title":"Revisiting Active Sequential Prediction-Powered Mean Estimation","created":"2026-04-20","cited_by_count":4,"area":null},{"id":"2604.21260","title":"Calibeating Prediction-Powered Inference","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2605.05076","title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2607.17409","title":"Efficient Sequential Evaluation of Large Language Models","created":"2026-07-19","cited_by_count":4,"area":null},{"id":"2506.13593","title":"Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2510.14581","title":"Model-agnostic Selective Labeling with Provable Statistical Guarantees","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2512.05456","title":"Do We Really Even Need Data? A Modern Look at Drawing Inference with Predicted Data","created":"2025-12-05","cited_by_count":3,"area":null},{"id":"2602.02229","title":"Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.10332","title":"Generalized Prediction-Powered Inference, with Application to Binary Classifier Evaluation","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2609.17560","title":"Pay Only for Disagreement: Certified No-Regression Verdicts for Model Updates with Matching Label-Complexity Bounds","created":"2026-07-22","cited_by_count":2,"area":null},{"id":"2606.15029","title":"Metric Match: A Subset Selection Approach to Evaluating LLM Judge Reliability","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2607.08347","title":"Prediction-Powered Active Testing","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2609.05073","title":"Confounding-Valid Conformal Inference for Counterfactual KPIs in Wireless Networks","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2411.03195","title":"Online Data Collection for Efficient Semiparametric Inference","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2601.01432","title":"Personalizing black-box models for nonparametric regression with minimax optimality","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2603.27049","title":"Overcoming the Incentive Collapse Paradox","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.11638","title":"Learning U-Statistics with Active Inference","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.17581","title":"Scalable Model-Assisted Multi-Target Estimation in Large Image Collections","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.18602","title":"Teach a Molmo2Fish: Towards interactive fish tracking with natural language guidance","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.25657","title":"Targeted Review for AI-Assisted Biodiversity Surveys: Active Continuous-Score Occupancy Modeling","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.26642","title":"The Delegation Blind Spot: Auditing Product Decisions from Agent Choices","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.32267","title":"When Can Old Evaluations Certify a New Model? Label-Efficient Release Decisions under Evaluator Drift","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.10321","title":"Estimating Uncoded Crash Factors with Tabular Foundation and System One Models: Kumo Tabular and Jev","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}