Smart contracts are gaining popularity as a means to support transparent, traceable, and self-executing decentralized applications, which enable the exchange of value in a trustless environment. Developers of smart contracts rely on various libraries, such as OpenZeppelin for Solidity contracts, to improve application quality and reduce development costs. The API documentations of these libraries are important sources of information for developers who are unfamiliar with the APIs. Yet, maintaining high-quality documentations is non-trivial, and errors in documentations may place barriers for developers to learn the correct usages of APIs. In this paper, we propose a technique, DocCon, to detect inconsistencies between documentations and the corresponding code for Solidity smart contract libraries. Our fact-based approach allows inconsistencies of different severity levels to be queried, from a database containing precomputed facts about the API code and documentations. DocCon successfully detected high-priority API documentation errors in popular smart contract libraries, including mismatching parameters, missing requirements, outdated descriptions, etc. Our experiment result shows that DocCon achieves good precision and is applicable to different libraries: 29 and 22 out of our reported 40 errors have been confirmed and fixed by library developers so far.
Thu 13 OctDisplayed time zone: Eastern Time (US & Canada) change
10:00 - 12:00 | Technical Session 22 - Code Summarization and RecommendationResearch Papers / NIER Track / Journal-first Papers / Industry Showcase at Banquet A Chair(s): Houari Sahraoui Université de Montréal | ||
10:00 20mResearch paper | Identifying Solidity Smart Contract API Documentation Errors Research Papers Chenguang Zhu The University of Texas at Austin, Ye Liu Nanyang Technological University, Xiuheng Wu Nanyang Technological University, Singapore, Yi Li Nanyang Technological University Pre-print | ||
10:20 10mVision and Emerging Results | Few-shot training LLMs for project-specific code-summarization NIER Track Toufique Ahmed University of California at Davis, Prem Devanbu Department of Computer Science, University of California, Davis DOI Pre-print | ||
10:30 20mResearch paper | Answer Summarization for Technical Queries: Benchmark and New Approach Research Papers Chengran Yang Singapore Management University, Bowen Xu School of Information Systems, Singapore Management University, Ferdian Thung Singapore Management University, Yucen Shi Singapore Management University, Ting Zhang Singapore Management University, Zhou Yang Singapore Management University, Xin Zhou , Jieke Shi Singapore Management University, Junda He Singapore Management University, DongGyun Han Royal Holloway, University of London, David Lo Singapore Management University | ||
10:50 20mPaper | Code Structure Guided Transformer for Source Code SummarizationVirtual Journal-first Papers Shuzheng Gao Harbin Institute of Technology, Cuiyun Gao Harbin Institute of Technology, Yulan He University of Warwick, Jichuan Zeng The Chinese University of Hong Kong, Lun Yiu Nie Tsinghua University, Xin Xia Huawei Software Engineering Application Technology Lab, Michael Lyu The Chinese University of Hong Kong | ||
11:10 10mVision and Emerging Results | Taming Multi-Output Recommenders for Software EngineeringVirtual NIER Track Christoph Treude University of Melbourne | ||
11:20 20mIndustry talk | MV-HAN: A Hybrid Attentive Networks based Multi-View Learning Model for Large-scale Contents RecommendationVirtual Industry Showcase Ge Fan Tencent Inc., Chaoyun Zhang Tencent Inc., Kai Wang Tencent Inc., Junyang Chen Shenzhen University DOI Pre-print | ||
11:40 20mResearch paper | Which Exception Shall We Throw?Virtual Research Papers Hao Zhong Shanghai Jiao Tong University | ||