{"total":16,"rows":[{"id":"2602.20557","title":"GENSR: Symbolic Regression Based in Equation Generative Space","created":"2026-02-24","cited_by_count":9,"area":null},{"id":"2606.15474","title":"Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines","created":"2026-06-13","cited_by_count":8,"area":null},{"id":"2608.24419","title":"A Judge Should Know What Changed:Construct Validity for LLM-as-a-Judge Evaluation","created":"2026-08-25","cited_by_count":4,"area":null},{"id":"2603.15656","title":"Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2602.22595","title":"Don't let the information slip away","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2606.01034","title":"A Finite-Calibration Regime Map for LLM Judge Panels","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2602.19945","title":"DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.12997","title":"Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosis","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2605.31381","title":"LLM Judges Inconsistently Disagree Across Safety Criteria and Harm Categories","created":"2026-05-29","cited_by_count":1,"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":"2608.26638","title":"Which Metrics Save the Most Human Annotation? Prediction-Powered Evaluation and Meta-Evaluation","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2608.27463","title":"Rating the Raters: Rasch Measurement Theory for LLM Evaluation","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2609.18366","title":"Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts","created":"2026-09-16","cited_by_count":1,"area":null},{"id":"2603.20012","title":"Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features","created":"2026-03-20","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":"2610.18248","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}