{"total":19,"rows":[{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344,"area":null},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2509.14635","title":"SWE-QA: Can Language Models Answer Repository-level Code Questions?","created":"2025-09-18","cited_by_count":38,"area":null},{"id":"2401.15963","title":"NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctness","created":"2024-01-29","cited_by_count":26,"area":null},{"id":"2401.00288","title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","created":"2023-12-30","cited_by_count":22,"area":null},{"id":"2406.16441","title":"UniCoder: Scaling Code Large Language Model via Universal Code","created":"2024-06-24","cited_by_count":18,"area":null},{"id":"2403.16702","title":"ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search","created":"2024-03-25","cited_by_count":12,"area":null},{"id":"2209.08372","title":"CodeQueries: A Dataset of Semantic Queries over Code","created":"2022-09-17","cited_by_count":11,"area":null},{"id":"2210.14494","title":"CS1QA: A Dataset for Assisting Code-based Question Answering in an Introductory Programming Course","created":"2022-10-26","cited_by_count":11,"area":null},{"id":"2412.14764","title":"CodeRepoQA: A Large-scale Benchmark for Software Engineering Question Answering","created":"2024-12-19","cited_by_count":11,"area":null},{"id":"2411.03012","title":"Leveraging Large Language Models in Code Question Answering: Baselines and Issues","created":"2024-11-05","cited_by_count":6,"area":null},{"id":"2601.13240","title":"KOCO-BENCH: Can Large Language Models Leverage Domain Knowledge in Software Development?","created":"2026-01-19","cited_by_count":5,"area":null},{"id":"2504.09249","title":"NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding","created":"2025-04-12","cited_by_count":3,"area":null},{"id":"2209.01566","title":"Towards Top-Down Automated Development in Limited Scopes: A Neuro-Symbolic Framework from Expressibles to Executables","created":"2022-09-04","cited_by_count":2,"area":null},{"id":"2209.05130","title":"Semantic-Preserving Adversarial Code Comprehension","created":"2022-09-12","cited_by_count":2,"area":null},{"id":"2604.24814","title":"SWE-QA: A Dataset and Benchmark for Complex Code Understanding","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2307.02443","title":"An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code","created":"2023-07-05","cited_by_count":1,"area":null},{"id":"2601.15339","title":"Lost in Transcription: How Speech-to-Text Errors Derail Code Understanding","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2604.16021","title":"Neurosymbolic Repo-level Code Localization","created":"2026-04-17","cited_by_count":1,"area":null}],"next_cursor":null}