{"total":19,"rows":[{"id":"2503.17181","title":"A Study of LLMs' Preferences for Libraries and Programming Languages","created":"2025-03-21","cited_by_count":20,"area":null},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2503.00691","title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","created":"2025-03-02","cited_by_count":11,"area":null},{"id":"2409.18952","title":"RepairBench: Leaderboard of Frontier Models for Program Repair","created":"2024-09-27","cited_by_count":9,"area":null},{"id":"2502.18473","title":"Disproving Program Equivalence with LLMs","created":"2025-02-05","cited_by_count":5,"area":null},{"id":"2505.03019","title":"Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2509.07054","title":"Statistical Methods in Generative AI","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2506.04142","title":"Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2411.10842","title":"CODECLEANER: Elevating Standards with A Robust Data Contamination Mitigation Toolkit","created":"2024-11-16","cited_by_count":2,"area":null},{"id":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2604.24703","title":"Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis","created":"2026-04-27","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":"2606.16999","title":"Selection Without Signal, Recovery Through Expression: A Measurement Study of Post-Hoc Falsification Operators for Frozen Small Code Models","created":"2026-06-15","cited_by_count":2,"area":null},{"id":"2505.13511","title":"Can AI Freelancers Compete? Benchmarking Earnings, Reliability, and Task Success at Scale","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2509.20837","title":"Verification Limits Code LLM Training","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2511.05501","title":"Towards Real-World Validity in Generative AI Benchmarks: Understanding and Designing Domain-Centered Evaluations for Journalism Practitioners","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2606.29815","title":"SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.12771","title":"Memorization Diagnostics for Code LLMs Should be Scale-Aware","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2610.02438","title":"Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}