{"total":16,"rows":[{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2401.06461","title":"Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers","created":"2024-01-12","cited_by_count":27,"area":null},{"id":"2406.11927","title":"On the Impacts of Contexts on Repository-Level Code Generation","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2306.00029","title":"CodeTF: One-stop Transformer Library for State-of-the-art Code LLMs","created":"2023-05-31","cited_by_count":21,"area":null},{"id":"2404.17733","title":"Building a Large Japanese Web Corpus for Large Language Models","created":"2024-04-27","cited_by_count":11,"area":null},{"id":"2507.10583","title":"$\\texttt{Droid}$: A Resource Suite for AI-Generated Code Detection","created":"2025-07-11","cited_by_count":9,"area":null},{"id":"2408.04660","title":"XMainframe: A Large Language Model for Mainframe Modernization","created":"2024-08-05","cited_by_count":6,"area":null},{"id":"2403.14592","title":"Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals","created":"2024-03-21","cited_by_count":2,"area":null},{"id":"2506.14702","title":"Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2505.11026","title":"StRuCom: A Novel Dataset of Structured Code Comments in Russian","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2505.19757","title":"CIDRe: A Reference-Free Multi-Aspect Criterion for Code Comment Quality Measurement","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2408.04663","title":"Dopamin: Transformer-based Comment Classifiers through Domain Post-Training and Multi-level Layer Aggregation","created":"2024-08-06","cited_by_count":0,"area":null},{"id":"2510.00324","title":"Which Programming Language and Model Work Best With LLM-as-a-Judge For Code Retrieval?","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2605.31520","title":"Separating Secrets from Placeholders: A Hybrid CNN-CodeBERT Framework for Three-Class Credential Leakage Detection","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.05443","title":"Scientific Code Search at Scale: A Multi-Domain Dataset and Benchmark","created":"2026-07-03","cited_by_count":0,"area":null}],"next_cursor":null}