{"total":39,"rows":[{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2412.01007","title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking","created":"2024-12-01","cited_by_count":37,"area":null},{"id":"2411.12644","title":"CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval","created":"2024-11-19","cited_by_count":34,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2510.01003","title":"Improving Code Localization with Repository Memory","created":"2025-10-01","cited_by_count":20,"area":null},{"id":"2504.13128","title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2503.07358","title":"RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2504.08734","title":"Towards an Understanding of Context Utilization in Code Intelligence","created":"2025-04-11","cited_by_count":10,"area":null},{"id":"2508.16671","title":"Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verification","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2510.26130","title":"Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation","created":"2025-10-30","cited_by_count":8,"area":null},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"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":"2506.11066","title":"CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2605.25232","title":"Specification-Based Code-Text-Code Reengineering for LLM-Mediated Software Evolution","created":"2026-05-24","cited_by_count":5,"area":null},{"id":"2410.18251","title":"Context-Augmented Code Generation Using Programming Knowledge Graphs","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2505.14394","title":"Knowledge Graph Based Repository-Level Code Generation","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2508.16771","title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2505.07768","title":"Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding","created":"2025-05-12","cited_by_count":3,"area":null},{"id":"2505.24715","title":"CoRet: Improved Retriever for Code Editing","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2506.16552","title":"Revela: Dense Retriever Learning via Language Modeling","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2510.22944","title":"Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2410.21591","title":"Can Large Language Models Replace Data Scientists in Biomedical Research?","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2509.24148","title":"TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2511.05533","title":"MCP4IFC: IFC-Based Building Design Using Large Language Models","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2603.22008","title":"On the Challenges and Opportunities of Learned Sparse Retrieval for Code","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2505.20182","title":"An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2510.24749","title":"Beyond Function-Level Search: Repository-Aware Dual-Encoder Code Retrieval with Adversarial Verification","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2511.05626","title":"LLMs as Packagers of HPC Software","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2512.10393","title":"Cross-modal Retrieval Models for Stripped Binary Analysis","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2604.00167","title":"A Study on the Impact of Fault localization Granularity for Repository-Scale Code Repair Tasks","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2509.17455","title":"Understanding Benchmark Language Under Weakened Formal Semantics","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2512.11509","title":"Does Less Hallucination Mean Less Creativity? An Empirical Investigation in LLMs","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2601.20810","title":"Context-Augmented Code Generation Using Programming Knowledge Graphs","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.05780","title":"Automated Customization of LLMs for Enterprise Code Repositories Using Semantic Scopes","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2604.07755","title":"An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2608.19957","title":"Natural Language Code Retrieval for 1C:Enterprise: An Open Benchmark and Efficient Bi-Encoder","created":"2026-08-20","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}