Newest papers

Effective Construction of Feature Database of Fingerprinting Functions for Code-Clone SCA

Zhiling Zhu, Tieming Chen, Chengwei Liu, Jiahui Wu, Qijie Song, Zhengzi Xu, Yueming Wu, Yang Liu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.24479 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

在当代有效软件开发中,对第三方库的广泛采用已经成为一种常见的做法,以避免重新发明轮子。这种趋势尤其明显在缺乏成熟包管理器的编程生态系统中,如C/C++。在这种背景下,代码克隆检测(CCD)技术已经成为识别代码重用实例的基本工具,从而减轻了安全和法律问题。尽管CCD算法取得了显著的进展,但学术工具和现实世界应用程序之间仍然存在着一个显著的差距。这种差异主要是因为学术工具依赖于由有限数量的索引库组成的实验数据集,而现实世界的应用程序需要更广泛的代码范围。为了应对这一挑战,我们提出了一种新的、系统性的方法来选择合适的开源库来构建一个更有效的CCD

Machine translation (Meta M2M100); the English original follows.

Abstract

In contemporary software development, the extensive adoption of third-party libraries has become standard practice to avoid reinventing the wheel. This trend is particularly evident in programming ecosystems that lack mature package managers, such as C/C++. Within this context, Code Clone Detection (CCD) techniques have emerged as essential tools for identifying instances of code reuse, thereby mitigating security and legal concerns. Despite significant advances in CCD algorithms, a notable gap persists between academic tools and real-world applications. This disparity primarily arises because academic tools rely on experimental datasets composed of a limited number of indexed repositories, whereas real-world applications require a much broader scope of code sources. To address this challenge, we propose a novel, systematic approach for selecting appropriate open-source repositories to construct a more effective CCD feature dataset. Our method, OSSScope, employs a greedy algorithm to analyze the diversity of fingerprinting functions across 2.55 million C repositories on GitHub, maximizing unique fingerprinting functions while minimizing the number of repositories required. OSSScope compiles an optimal feature dataset containing 61 million fingerprinting functions from 190K repositories, resulting in a 22.65% improvement in recall over SOTA tools, and covers over 95% of the features from other sources. Leveraging the selected repositories, we introduce RClassifier, a lightweight classification model that determines whether a repository should be included, streamlining construction for migration to other language ecosystems. Our evaluation of RClassifier in the Golang ecosystem validates its effectiveness, achieving recall comparable to the dataset produced by OSSScope.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Scope (computer science), Feature (linguistics), Construct (python library), Precision and recall, Code (set theory)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange