The study examined 265,363 Kaggle notebooks to explore how code quality relates to machine learning performance. Using Pylint and SonarQube, it found that general Python code quality shows negligible correlation with performance, while ML‑specific violations have a small negative association with performance. Popularity and author expertise do not predict code quality or performance, though competition expertise correlates with better performance and fewer ML‑specific violations.
arXiv:2609.12708v2 Announce Type: replace-cross Abstract: AI coding assistants are becoming co-authors of production software, yet their evaluation centers on functional correctness, leaving open whe...
arXiv:2508. 16131v3 Announce Type: replace-cross Abstract: Code completion entails the task of providing missing tokens given a surrounding context.
arXiv:2506. 02791v4 Announce Type: replace-cross Abstract: In recent years, code intelligence has gained increasing importance in the field of automated software engineering.
arXiv:2606. 12620v1 Announce Type: cross Abstract: Thanks to the rapid adoption of AI code assistants powered by large language models (LLMs), industry codebases are, increasingly, a hybrid of AI- and human-authored code.
arXiv:2506. 11066v3 Announce Type: replace-cross Abstract: Code retrieval is essential in modern software development, as it boosts code reuse and accelerates debugging.
arXiv:2606. 12864v1 Announce Type: cross Abstract: Despite strong performance in competitive programming, the role of Large Language Models (LLMs) in supporting human learning in the same setting remains largely unexplored.
arXiv:2512. 22827v2 Announce Type: replace-cross Abstract: Code often suffers from performance bugs.
arXiv:2609.22097v1 Announce Type: cross Abstract: The evaluation of large language models (LLMs) on coding tasks has primarily focused on performance metrics such as pass@k. As LLMs continue to advan...
arXiv:2606. 20517v1 Announce Type: new Abstract: LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on code-generation tasks.
The paper introduces a dataset comprising the complete development history of a 21,000-line Python tool created solely by Claude AI, without any human-authored code or tests. It also presents two code‑provenance tracing tools, three taxonomies for instruction intent, commit provenance, and response reliability, and applies these to analyze the dataset. Findings include that CLI instructions differ from IDE‑chat instructions, development is largely proactive, 14.3% of AI code‑generation events contain errors later caught by the AI‑authored test suite, and about 1 in 4–5 interactive responses contain factual errors.
arXiv:2511. 06090v3 Announce Type: replace-cross Abstract: Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness.
arXiv:2607. 29516v1 Announce Type: cross Abstract: AI coding agents are generating code at volumes that exceed the capacity of traditional peer review.