{"total":17,"rows":[{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2402.15938","title":"Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models","created":"2024-02-24","cited_by_count":122,"area":null},{"id":"2404.00599","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-03-31","cited_by_count":72,"area":null},{"id":"2404.10952","title":"Can Language Models Solve Olympiad Programming?","created":"2024-04-16","cited_by_count":72,"area":null},{"id":"2407.09007","title":"Benchmarking Language Model Creativity: A Case Study on Code Generation","created":"2024-07-12","cited_by_count":40,"area":null},{"id":"2402.02823","title":"Evading Data Contamination Detection for Language Models is (too) Easy","created":"2024-02-05","cited_by_count":30,"area":null},{"id":"2503.07701","title":"Automated Benchmark Generation for Repository-Level Coding Tasks","created":"2025-03-10","cited_by_count":29,"area":null},{"id":"2406.19783","title":"NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations","created":"2024-06-28","cited_by_count":20,"area":null},{"id":"2402.04798","title":"Spiking-PhysFormer: Camera-Based Remote Photoplethysmography with Parallel Spike-driven Transformer","created":"2024-02-07","cited_by_count":19,"area":null},{"id":"2505.08253","title":"Evaluating LLM Metrics Through Real-World Capabilities","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2505.16667","title":"ELABORATION: A Comprehensive Benchmark on Human-LLM Competitive Programming","created":"2025-05-22","cited_by_count":16,"area":null},{"id":"2502.04355","title":"LLM-ProS: Analyzing Large Language Models' Performance in Competitive Problem Solving","created":"2025-02-04","cited_by_count":6,"area":null},{"id":"2501.05601","title":"Exploring Large Language Models for Translating Romanian Computational Problems into English","created":"2025-01-09","cited_by_count":2,"area":null},{"id":"2410.15005","title":"CAP: Data Contamination Detection via Consistency Amplification","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2402.18040","title":"Automated Discovery of Integral with Deep Learning","created":"2024-02-28","cited_by_count":0,"area":null},{"id":"2405.13352","title":"\"Turing Tests\" For An AI Scientist","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2409.09054","title":"Evaluating the Performance of Large Language Models in Competitive Programming: A Multi-Year, Multi-Grade Analysis","created":"2024-08-31","cited_by_count":0,"area":null}],"next_cursor":null}