{"total":75,"rows":[{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361,"area":null},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333,"area":null},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2309.16298","title":"At Which Training Stage Does Code Data Help LLMs Reasoning?","created":"2023-09-28","cited_by_count":82,"area":"lr"},{"id":"2407.02883","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","created":"2024-07-03","cited_by_count":60,"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":"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":"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":"2402.01935","title":"Code Representation Learning At Scale","created":"2024-02-02","cited_by_count":26,"area":null},{"id":"2204.03293","title":"CoCoSoDa: Effective Contrastive Learning for Code Search","created":"2022-04-07","cited_by_count":22,"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":"2201.10866","title":"CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search","created":"2022-01-26","cited_by_count":21,"area":null},{"id":"2506.09003","title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner","created":"2025-06-10","cited_by_count":20,"area":null},{"id":"2210.01185","title":"ContraCLM: Contrastive Learning For Causal Language Model","created":"2022-10-03","cited_by_count":18,"area":null},{"id":"2401.04514","title":"Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search","created":"2024-01-09","cited_by_count":17,"area":null},{"id":"2205.02029","title":"CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training","created":"2022-05-04","cited_by_count":15,"area":null},{"id":"2502.07555","title":"O1 Embedder: Let Retrievers Think Before Action","created":"2025-02-11","cited_by_count":15,"area":"lr"},{"id":"2502.20868","title":"ProBench: Benchmarking Large Language Models in Competitive Programming","created":"2025-02-28","cited_by_count":15,"area":"lr"},{"id":"2310.08069","title":"Rethinking Negative Pairs in Code Search","created":"2023-10-12","cited_by_count":14,"area":null},{"id":"2305.16837","title":"ChatGPT: A Study on its Utility for Ubiquitous Software Engineering Tasks","created":"2023-05-26","cited_by_count":12,"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":"2603.19223","title":"F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World","created":"2026-03-19","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":"2406.11589","title":"CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents","created":"2024-06-17","cited_by_count":11,"area":"agents"},{"id":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2406.01359","title":"R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models","created":"2024-06-03","cited_by_count":9,"area":null},{"id":"2603.16124","title":"SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding","created":"2026-03-17","cited_by_count":9,"area":"agents"},{"id":"2210.12285","title":"Exploring Representation-Level Augmentation for Code Search","created":"2022-10-21","cited_by_count":8,"area":null},{"id":"2309.09980","title":"Code Representation Pre-training with Complements from Program Executions","created":"2023-09-04","cited_by_count":8,"area":null},{"id":"2312.07200","title":"Code Membership Inference for Detecting Unauthorized Data Use in Code Pre-trained Language Models","created":"2023-12-12","cited_by_count":8,"area":"safety"},{"id":"2210.09597","title":"Soft-Labeled Contrastive Pre-training for Function-level Code Representation","created":"2022-10-18","cited_by_count":7,"area":null},{"id":"2606.11864","title":"CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding","created":"2026-06-10","cited_by_count":7,"area":"agents"},{"id":"2311.09707","title":"GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding","created":"2023-11-16","cited_by_count":6,"area":null},{"id":"2407.10722","title":"Mitigating Data Imbalance for Software Vulnerability Assessment: Does Data Augmentation Help?","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2505.15585","title":"MIRB: Mathematical Information Retrieval Benchmark","created":"2025-05-21","cited_by_count":6,"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":"2110.07811","title":"Cascaded Fast and Slow Models for Efficient Semantic Code Search","created":"2021-10-15","cited_by_count":4,"area":null},{"id":"2205.01293","title":"A Survey of Deep Learning Models for Structural Code Understanding","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2311.14901","title":"Code Search Debiasing:Improve Search Results beyond Overall Ranking Performance","created":"2023-11-25","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":"2508.19558","title":"Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking","created":"2025-08-27","cited_by_count":4,"area":"synth"},{"id":"2202.04847","title":"A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2205.10674","title":"NS3: Neuro-Symbolic Semantic Code Search","created":"2022-05-21","cited_by_count":3,"area":null},{"id":"2208.05596","title":"Finding Reusable Machine Learning Components to Build Programming Language Processing Pipelines","created":"2022-08-11","cited_by_count":3,"area":null},{"id":"2406.12326","title":"Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning","created":"2024-06-18","cited_by_count":3,"area":null},{"id":"2409.13551","title":"Contextualized Data-Wrangling Code Generation in Computational Notebooks","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2412.08291","title":"Code LLMs: A Taxonomy-based Survey","created":"2024-12-11","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":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2512.21332","title":"C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling","created":"2025-12-24","cited_by_count":3,"area":null},{"id":"2309.00584","title":"Laminar: A New Serverless Stream-based Framework with Semantic Code Search and Code Completion","created":"2023-09-01","cited_by_count":2,"area":null},{"id":"2402.17583","title":"FaultProfIT: Hierarchical Fault Profiling of Incident Tickets in Large-scale Cloud Systems","created":"2024-02-27","cited_by_count":2,"area":null},{"id":"2503.08161","title":"OASIS: Order-Augmented Strategy for Improved Code Search","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2504.07740","title":"Zero-Shot Cross-Domain Code Search without Fine-Tuning","created":"2025-04-10","cited_by_count":2,"area":null},{"id":"2505.14976","title":"SDLog: A Deep Learning Framework for Detecting Sensitive Information in Software Logs","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2508.15423","title":"An Empirical Study of Knowledge Distillation for Code Understanding Tasks","created":"2025-08-21","cited_by_count":2,"area":"distill"},{"id":"2201.07984","title":"AstBERT: Enabling Language Model for Financial Code Understanding with Abstract Syntax Trees","created":"2022-01-20","cited_by_count":1,"area":null},{"id":"2305.00875","title":"Redundancy and Concept Analysis for Code-trained Language Models","created":"2023-05-01","cited_by_count":1,"area":null},{"id":"2306.15604","title":"Constructing Multilingual Code Search Dataset Using Neural Machine Translation","created":"2023-06-27","cited_by_count":1,"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":"2312.14279","title":"Characterizing and Classifying Developer Forum Posts with their Intentions","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2507.03958","title":"A Comparative Study of Specialized LLMs as Dense Retrievers","created":"2025-07-05","cited_by_count":1,"area":"mllm"},{"id":"2509.16442","title":"Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2512.23065","title":"TabiBERT: A Large-Scale ModernBERT Foundation Model and A Unified Benchmark for Turkish","created":"2025-12-28","cited_by_count":1,"area":null},{"id":"2605.04615","title":"Beyond Retrieval: A Multitask Benchmark and Model for Code Search","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2401.14975","title":"Embedding-based search in JetBrains IDEs","created":"2024-01-26","cited_by_count":0,"area":null},{"id":"2502.07494","title":"URECA: The Chain of Two Minimum Set Cover Problems exists behind Adaptation to Shifts in Semantic Code Search","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2503.05315","title":"LoRACode: LoRA Adapters for Code Embeddings","created":"2025-03-07","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":"2604.15663","title":"CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval","created":"2026-04-17","cited_by_count":0,"area":"rag"},{"id":"2605.15081","title":"ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World","created":"2026-05-14","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},{"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":"2608.24221","title":"DeepRepoQA: Code Repository Question Answering with Deep Agent Exploration","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2609.01865","title":"ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval","created":"2026-09-01","cited_by_count":0,"area":"rag"}],"next_cursor":null}