{"total":24,"rows":[{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74,"area":null},{"id":"2502.08108","title":"Generative AI and Empirical Software Engineering: A Paradigm Shift","created":"2025-02-12","cited_by_count":9,"area":null},{"id":"2512.18925","title":"Beyond the Prompt: An Empirical Study of Cursor Rules","created":"2025-12-21","cited_by_count":7,"area":null},{"id":"2410.13098","title":"A Little Human Data Goes A Long Way","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2504.01850","title":"Code Red! On the Harmfulness of Applying Off-the-shelf Large Language Models to Programming Tasks","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2507.02858","title":"Requirements Elicitation Follow-Up Question Generation","created":"2025-07-03","cited_by_count":5,"area":null},{"id":"2505.20209","title":"Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2506.12468","title":"Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark","created":"2025-06-14","cited_by_count":4,"area":null},{"id":"2512.21757","title":"How Do Agents Perform Code Optimization? An Empirical Study","created":"2025-12-25","cited_by_count":4,"area":null},{"id":"2506.12691","title":"Get on the Train or be Left on the Station: Using LLMs for Software Engineering Research","created":"2025-06-15","cited_by_count":3,"area":null},{"id":"2505.15469","title":"A Qualitative Investigation into LLM-Generated Multilingual Code Comments and Automatic Evaluation Metrics","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.16440","title":"Evaluating the Use of LLMs for Documentation to Code Traceability","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2512.15979","title":"OLAF: Towards Robust LLM-Based Annotation Framework in Empirical Software Engineering","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2604.05100","title":"Edit, But Verify: An Empirical Audit of Instructed Code-Editing Benchmarks","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2608.29455","title":"Item-Mean Surrogates: Why Richer Persona Data Fail to Improve LLMs as Human Surrogates","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2505.09021","title":"AI-Mediated Code Comment Improvement","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2512.06227","title":"Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safety","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2512.20328","title":"Toward Explaining Large Language Models in Software Engineering Tasks","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2604.11184","title":"Taking a Pulse on How Generative AI is Reshaping the Software Engineering Research Landscape","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2607.10420","title":"Is Model Instability just Noise to be Tolerated or a Property that can be Managed?","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.07038","title":"Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.10046","title":"Detecting Soft Skills in ML Engineering Roles CVs","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.27442","title":"From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.17274","title":"After the Party: Growth, Governance, and Security Scanning in the OpenClaw Agent Skill Ecosystem","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}