This repository is a curated list of research papers, datasets, and software projects focused on applying machine learning to source code (MLonCode). It serves as a comprehensive resource for researchers and practitioners in software engineering and machine learning interested in areas like program synthesis, code analysis, and code generation.

How It Works

The repository categorizes resources into various subfields of MLonCode, including program synthesis, source code analysis, neural network architectures, embeddings, program translation, code suggestion, repair, optimization, and more. It links to seminal papers, relevant conferences, and practical software tools, providing a broad overview of the research landscape.

Quick Start & Requirements

This is a curated list, not a software package. No installation or execution is required.

Highlighted Details

• Extensive coverage of research papers from major conferences (ICSE, ASE, FSE, ICLR, NIPS, etc.).
• Links to numerous datasets for MLonCode tasks, including large-scale code corpora like GitHub archives and StackOverflow question-code pairs.
• A wide array of software tools and frameworks for parsing, analyzing, and embedding source code, such as bblfsh, DeepCS, and code2vec.
• Categorization spans diverse MLonCode applications, from program repair and bug detection to code summarization and clone detection.

Maintenance & Community

This repository is no longer actively maintained. An alternative actively maintained resource can be found at ml4code.github.io.

Licensing & Compatibility

The repository itself does not have a specific license mentioned, but it links to various projects and papers, each with its own licensing. Users should check individual project licenses for compatibility.

Limitations & Caveats

The repository is explicitly stated as no longer actively maintained, meaning links may become outdated, and new research will not be added. Users are directed to an alternative resource for current information.