{"total":32,"rows":[{"id":"2410.08948","title":"Emergent social conventions and collective bias in LLM populations","created":"2024-10-11","cited_by_count":123,"area":null},{"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":"2506.07949","title":"Cost-Optimal Active AI Model Evaluation","created":"2025-06-09","cited_by_count":19,"area":null},{"id":"2502.04262","title":"Efficient Randomized Experiments Using Foundation Models","created":"2025-02-06","cited_by_count":10,"area":null},{"id":"2505.23785","title":"Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale","created":"2025-05-23","cited_by_count":10,"area":null},{"id":"2604.11581","title":"Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking","created":"2026-04-13","cited_by_count":10,"area":null},{"id":"2506.10908","title":"Probably Approximately Correct Labels","created":"2025-06-12","cited_by_count":8,"area":null},{"id":"2509.22957","title":"Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas","created":"2025-09-26","cited_by_count":8,"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":"2508.15162","title":"A Unified Framework for Inference with General Missingness Patterns and Machine Learning Imputation","created":"2025-08-21","cited_by_count":7,"area":null},{"id":"2601.05420","title":"Efficient Inference for Noisy LLM-as-a-Judge Evaluation","created":"2026-01-08","cited_by_count":7,"area":null},{"id":"2603.19160","title":"PPI is the Difference Estimator: Recognizing the Survey Sampling Roots of Prediction-Powered Inference","created":"2026-03-19","cited_by_count":7,"area":null},{"id":"2604.18569","title":"Revisiting Active Sequential Prediction-Powered Mean Estimation","created":"2026-04-20","cited_by_count":4,"area":null},{"id":"2605.29249","title":"Prediction-Powered Inference Across Many Tasks for AI Evaluation & Social Science Research","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2508.01341","title":"Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: \"One Map, Many Trials\" in Satellite-Driven Poverty Analysis","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2606.27687","title":"Mitigating LLM-based p-Hacking by Preregistering for the Next LLM","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2505.04643","title":"Prediction-powered estimators for finite population statistics in highly imbalanced textual data: Public hate crime estimation","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2601.11920","title":"Enhancing LLM-Based Data Annotation with Error Decomposition","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2604.19645","title":"The signal is the ceiling: Measurement limits of LLM-predicted experience ratings from open-ended survey text","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.09834","title":"Supercharging Bayesian Inference with Reliable AI-Informed Priors","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2607.15455","title":"Design-Based Supervised Learning with Noisy Human Labels","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2609.25447","title":"Conduct Under Pressure: What Sixty Language Models Do When a User Pushes","created":"2026-09-21","cited_by_count":1,"area":null},{"id":"2312.05990","title":"Constructing Vec-tionaries to Extract Message Features from Texts: A Case Study of Moral Appeals","created":"2023-12-10","cited_by_count":0,"area":null},{"id":"2503.01672","title":"Automated Annotation of Evolving Corpora for Augmenting Longitudinal Network Data: A Framework Integrating Large Language Models and Expert Knowledge","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2601.02400","title":"Detecting and Mitigating Treatment Leakage in Text-Based Causal Inference: Distillation and Sensitivity Analysis","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2602.03791","title":"Should I use Synthetic Data for That? An Analysis of the Suitability of Synthetic Data for Data Sharing and Augmentation","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2606.24244","title":"When Surveys Become Conversations: Adaptive Matrix Validation for AI-Assisted Interviews","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.07915","title":"Validating LLMs in social science: Epistemic threats and emerging norms","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.02909","title":"When Predictions Become Regressors: A Split-Sample Correction for Biases in Downstream Inference","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.22582","title":"Hybrid Panels: Toward Human-AI Collaboration in Survey Research","created":"2026-08-23","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},{"id":"2610.16757","title":"Is the Platform Part of the Measurement? A Protocol and Simulation Study for Cross-Platform Equivalence of Machine-Labelled Policy Sentiment","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}