Automatic Analysis of Available Source Code of Top Artificial Intelligence Conference Papers

TL;DR

This paper introduces an automated method to identify AI conference papers with available source code, extract repository URLs, and analyze the characteristics and accessibility of these repositories, aiding reproducibility efforts.

Contribution

It presents a novel automated approach for detecting source code availability in AI papers and creates the largest labeled README dataset for source code documentation research.

Findings

20.5% of AI conference papers from 2010-2019 have available source code

8.1% of source code repositories are no longer accessible

Many README files lack installation instructions or usage tutorials

Abstract

Source code is essential for researchers to reproduce the methods and replicate the results of artificial intelligence (AI) papers. Some organizations and researchers manually collect AI papers with available source code to contribute to the AI community. However, manual collection is a labor-intensive and time-consuming task. To address this issue, we propose a method to automatically identify papers with available source code and extract their source code repository URLs. With this method, we find that 20.5% of regular papers of 10 top AI conferences published from 2010 to 2019 are identified as papers with available source code and that 8.1% of these source code repositories are no longer accessible. We also create the XMU NLP Lab README Dataset, the largest dataset of labeled README files for source code document research. Through this dataset, we have discovered that quite a few README files have no installation instructions or usage tutorials provided. Further, a large-scale comprehensive statistical analysis is made for a general picture of the source code of AI conference papers. The proposed solution can also go beyond AI conference papers to analyze other scientific papers from both journals and conferences to shed light on more domains.