检索结果-内蒙古大学图书馆

E-PRedictor: an approach for early prediction of pull request acceptance

Science China(Information Sciences) 2025年第5期68卷 380-395页

作者： Kexing CHEN Lingfeng BAO Xing HU Xin XIA Xiaohu YANG State Key Laboratory of Blockchain and Data Security Zhejiang University Software Engineering Application Technology Lab

A pull request(PR) is an event in Git where a contributor asks project maintainers to review code he/she wants to merge into a project. The PR mechanism greatly improves the efficiency of distributed software development in the opensource community. Nevertheless, the massive number of PRs in an open-source software(OSS) project increases the workload of developers. To reduce the burden on developers, many previous studies have investigated factors that affect the chance of PRs getting accepted and built prediction models based on these factors. However, most prediction models are built on the data after PRs are submitted for a while(e.g., comments on PRs), making them not useful in practice. Because integrators still need to spend a large amount of effort on inspecting PRs. In this study, we propose an approach named E-PRedictor(earlier PR predictor) to predict whether a PR will be merged when it is created. E-PRedictor combines three dimensions of manual statistic features(i.e., contributor profile, specific pull request, and project profile) and deep semantic features generated by BERT models based on the description and code changes of PRs. To evaluate the performance of E-PRedictor, we collect475192 PRs from 49 popular open-source projects on GitHub. The experiment results show that our proposed approach can effectively predict whether a PR will be merged or not. E-PRedictor outperforms the baseline models(e.g., Random Forest and VDCNN) built on manual features significantly. In terms of F1@Merge, F1@Reject, and AUC(area under the receiver operating characteristic curve), the performance of E-PRedictor is 90.1%, 60.5%, and 85.4%, respectively.

关键词： pull request prediction model GitHub

来源：评论

学校读者我要写书评

暂无评论

A Helmet Detection Algorithm Based on Transformers with Deformable Attention Module

引用

Chinese Journal of Electronics 2025年第1期34卷 229-241页

作者： Songle Chen Hongbo Sun Yuxin Wu Lei Shang Xiukai Ruan Engineering Research Center of Post Big Data Technology and Application of Jiangsu Province Nanjing University of Posts and Telecommunications State Key Lab for Novel Software Technology Nanjing University Institute of Intelligent Locks Wenzhou University

Wearing a helmet is one of the effective measures to protect workers' safety. To address the challenges of severe occlusion, multi-scale, and small target issues in helmet detection, this paper proposes a helmet detection algorithm based on deformable attention transformers. The main contributions of this paper are as follows. A compact end-to-end network architecture for safety helmet detection based on transformers is proposed. It cancels the computationally intensive transformer encoder module in the existing detection transformer(DETR) and uses the transformer decoder module directly on the output of feature extraction for query decoding, which effectively improves the efficiency of helmet detection. A novel feature extraction network named Swin transformer with deformable attention module(DSwin transformer) is proposed. By sparse cross-window attention, it enhances the contextual awareness of multi-scale features extracted by Swin transformer, and keeps high computational efficiency simultaneously. The proposed method generates the query reference points and query embeddings based on the joint prediction probabilities, and selects an appropriate number of decoding feature maps and sparse sampling points for query decoding, which further enhance the inference capability and processing speed. On the benchmark safety-helmet-wearing-dataset(SHWD), the proposed method achieves the average detection accuracy mAP@0.5 of 95.4% with 133.35G floating-point operations per second(FLOPs) and 20 frames per second(FPS), the state-of-the-art method for safety helmet detection.

关键词： Head Accuracy Network architecture Benchmark testing Transformers Feature extraction Safety Decoding Computational efficiency Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep Assessment of Code Review Generation Approaches: Beyond Lexical Similarity

arXiv

引用

arXiv 2025年

作者： Jiang, Yanjie Liu, Hui Chen, Tianyi Fan, Fu Dong, Chunhao Liu, Kui Zhang, Lu Peking University China Beijing Institute of Technology China Huawei Software Engineering Application Technology Lab China

Code review is a standard practice for ensuring the quality of software projects, and recent research has focused extensively on automated code review. While significant advancements have been made in generating code reviews, the automated assessment of these reviews remains less explored, with existing approaches and metrics often proving inaccurate. Current metrics, such as BLEU, primarily rely on lexical similarity between generated and reference reviews. However, such metrics tend to underestimate reviews that articulate the expected issues in ways different from the references. In this paper, we explore how semantic similarity between generated and reference reviews can enhance the automated assessment of code reviews. We first present a benchmark called GradedReviews, which is constructed by collecting real-world code reviews from open-source projects, generating reviews using state-of-the-art approaches, and manually assessing their quality. We then evaluate existing metrics for code review assessment using this benchmark, revealing their limitations. To address these limitations, we propose two novel semantic-based approaches for assessing code reviews. The first approach involves converting both the generated review and its reference into digital vectors using a deep learning model and then measuring their semantic similarity through Cosine similarity. The second approach generates a prompt based on the generated review and its reference, submits this prompt to ChatGPT, and requests ChatGPT to rate the generated review according to explicitly defined criteria. Our evaluation on the GradedReviews benchmark indicates that the proposed semantic-based approaches significantly outperform existing state-of-the-art metrics in assessing generated code review, improving the correlation coefficient between the resulting scores and human scores from 0.22 to 0.47. © 2025, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Code Change Intention, Development Artifact and History Vulnerability: Putting Them Together for Vulnerability Fix Detection by LLM

arXiv

引用

arXiv 2025年

作者： Yang, Xu Zhu, Wenhan Pacheco, Michael Zhou, Jiayuan Wang, Shaowei Hu, Xing Liu, Kui University of Manitoba WinnipegMB Canada Huawei Canada Canada Zhejiang University Hangzhou China Huawei Software Engineering Application Technology Lab Hangzhou China

Detecting vulnerability fix commits in open-source software is crucial for maintaining software security. To help OSS identify vulnerability fix commits, several automated approaches are developed. However, existing approaches like VulFixMiner and CoLeFunDa, focus solely on code changes, neglecting essential context from development artifacts. Tools like Vulcurator, which integrates issue reports, fail to leverage semantic associations between different development artifacts (e.g., pull requests and history vulnerability fixes). Moreover, they miss vulnerability fixes in tangled commits and lack explanations, limiting practical use. Hence to address those limitations, we propose LLM4VFD, a novel framework that leverages Large Language Models (LLMs) enhanced with Chain-of-Thought reasoning and In-Context Learning to improve the accuracy of vulnerability fix detection. LLM4VFD comprises three components: (1) Code Change Intention, which analyzes commit summaries, purposes, and implications using Chain-of-Thought reasoning;(2) Development Artifact, which incorporates context from related issue reports and pull requests;(3) Historical Vulnerability, which retrieves similar past vulnerability fixes to enrich context. More importantly, on top of the prediction, LLM4VFD also provides a detailed analysis and explanation to help security experts understand the rationale behind the decision. We evaluated LLM4VFD against state-of-the-art techniques, including Pre-trained Language Model-based approaches and vanilla LLMs, using a newly collected dataset, BigVulFixes. Experimental results demonstrate that LLM4VFD significantly outperforms the best-performed existing approach by 68.1%–145.4%. Furthermore, We conducted a user study with security experts, showing that the analysis generated by LLM4VFD improves the efficiency of vulnerability fix identification. © 2025, CC BY.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Distinguishing LLM-Generated from Human-Written Code by Contrastive Learning

引用

ACM Transactions on software engineering and Methodology 2025年第4期34卷

作者： Xu, Xiaodan Ni, Chao Guo, Xinrong Liu, Shaoxuan Wang, Xiaoya Liu, Kui Yang, Xiaohu State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Software Engineering Application Technology Lab Hangzhou Huawei China Institute of Blockchain and Data Security China

Large language models (LLMs), such as ChatGPT released by OpenAI, have attracted significant attention from both industry and academia due to their demonstrated ability to generate high-quality content for various tasks. Despite the impressive capabilities of LLMs, there are growing concerns regarding their potential risks in various fields, such as news, education, and software engineering. Recently, several commercial and open source LLM-generated content detectors have been proposed, which, however, are primarily designed for detecting natural language content without considering the specific characteristics of program code. This article aims to fill this gap by proposing a novel ChatGPT-generated code detector, CodeGPTSensor, based on a contrastive learning framework and a semantic encoder built with UniXcoder. To assess the effectiveness of CodeGPTSensor on differentiating ChatGPT-generated code from human-written code, we first curate a large-scale Human and Machine comparison Corpus (HMCorp), which includes 550k pairs of human-written and ChatGPT-generated code (i.e., 288k Python code pairs and 222k Java code pairs). Based on the HMCorp dataset, our qualitative and quantitative analysis of the characteristics of ChatGPT-generated code reveals the challenge and opportunity of distinguishing ChatGPT-generated code from human-written code with their representative features. Our experimental results indicate that CodeGPTSensor can effectively identify ChatGPT-generated code, outperforming all selected baselines. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Multi-view Transformer-Based Network for Prerequisite Learning in Concept Graphs 23rd

Multi-view Transformer-Based Network for Prerequisite Learn...

引用

23rd International Semantic Web Conference, ISWC 2024

作者： Wang, Zhichun Shao, Yifeng Peng, Boci Li, Bangui Li, Yun Wang, Qianren Li, Nijun School of Artificial Intelligence Beijing Normal University Beijing China Engineering Research Center of Intelligent Technology and Educational Application Ministry of Education Beijing China School of Intelligence Science and Technology Peking University Beijing China School of Computer Science and Engineering Beihang University Beijing China Advanced Cognitive AI Lab Shanghai Huawei Technologies Shanghai China

ISBN: (纸本)9783031778438

Prerequisite learning is the task of identifying prerequisite relations among concepts, which is important for many AI-based educational applications. Previous approaches explore different kinds of learning resources to obtain useful features for predicting prerequisites. Early approaches use handcrafted features while recent approaches use neural networks to encode information of concepts. To further improve the results of prerequisite learning, we build concept graphs to include comprehensive information about concepts from open data and learning resources, and propose a Multi-view Transformer-based Network (MTN) to encode multi-view features of concepts in the graph. Multi-view features are fused to make accurate predictions of concept prerequisites. We evaluate our approach on four public datasets and compare it with recently published approaches. The results show that our approach can achieve state-of-the-art results in the task of prerequisite learning. The source code and data are available at https://***/kg-bnu/MTN. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based open API recommendation for Mashup development

引用

Science China(Information Sciences) 2023年第7期66卷 94-111页

作者： Ye WANG Junwu CHEN Qiao HUANG Xin XIA Bo JIANG School of Computer and Information Engineering Zhejiang Gongshang University Software Engineering Application Technology Lab

Mashup developers often need to find open application programming interfaces(APIs) for their composition application development. Although most enterprises and service organizations have encapsulated their businesses or resources online as open APIs, finding the right high-quality open APIs is not an easy task from a library with several open APIs. To solve this problem, this paper proposes a deep learning-based open API recommendation(DLOAR) approach. First, the hierarchical density-based spatial clustering of applications with a noise topic model is constructed to build topic models for Mashup clusters. Second,developers' requirement keywords are extracted by the Text Rank algorithm, and the language model is built. Third, a neural network-based three-level similarity calculation is performed to find the most relevant open APIs. Finally, we complement the relevant information of open APIs in the recommended list to help developers make better choices. We evaluate the DLOAR approach on a real dataset and compare it with commonly used open API recommendation approaches: term frequency-inverse document frequency, latent dirichlet allocation, Word2Vec, and Sentence-BERT. The results show that the DLOAR approach has better performance than the other approaches in terms of precision, recall, F1-measure, mean average precision,and mean reciprocal rank.

关键词： Mashup development open API recommendation deep learning neural network service discovery

来源：评论

学校读者我要写书评

暂无评论

Satellite Federated Fine-Tuning for Foundation Models in Space Computing Power Networks

arXiv

引用

arXiv 2025年

作者： Zhu, Yan Zhu, Jingyang Wang, Ting Shi, Yuanming Jiang, Chunxiao Letaief, Khaled Ben MoE Engineering Research-Center of Software/Hardware Co-design Technology and Application The Shanghai Key Lab. of Trustworthy Computing East China Normal University Shanghai200062 China School of Information Science and Technology ShanghaiTech University Shanghai201210 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Advancements in artificial intelligence (AI) and low-earth orbit (LEO) satellites have promoted the application of large remote sensing foundation models for various downstream tasks. However, direct downloading of these models for fine-tuning on the ground is impeded by privacy concerns and limited bandwidth. Satellite federated learning (FL) offers a solution by enabling model fine-tuning directly on-board satellites and aggregating model updates without data downloading. Nevertheless, for large foundation models, the computational capacity of satellites is insufficient to support effective on-board fine-tuning in traditional satellite FL frameworks. To address these challenges, we propose a satellite-ground collaborative federated fine-tuning framework. The key of the framework lies in how to reasonably decompose and allocate model components to alleviate insufficient on-board computation capabilities. During fine-tuning, satellites exchange intermediate results with ground stations or other satellites for forward propagation and back propagation, which brings communication challenges due to the special communication topology of space transmission networks, such as intermittent satellite-ground communication, short duration of satellite-ground communication windows, and unstable inter-orbit inter-satellite links (ISLs). To reduce transmission delays, we further introduce tailored communication strategies that integrate both communication and computing resources. Specifically, we propose a parallel intra-orbit communication strategy, a topology-aware satellite-ground communication strategy, and a latency-minimalization inter-orbit communication strategy to reduce space communication costs. Simulation results demonstrate significant reductions in training time with improvements of approximately 33%. Copyright © 2025, The Authors. All rights reserved.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Dual Prompt-Based Few-Shot Learning for Automated Vulnerability Patch Localization 31

Dual Prompt-Based Few-Shot Learning for Automated Vulnerabil...

引用

31st IEEE International Conference on software Analysis, Evolution and Reengineering, SANER 2024

作者： Zhang, Junwei Hu, Xing Bao, Lingfeng Xia, Xin Li, Shanping Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China Software Engineering Application Technology Lab Huawei China

ISBN: (纸本)9798350330663

Vulnerabilities are disclosed with corresponding patches so that users can remediate them in time. However, there are instances where patches are not released with the disclosed vulnerabilities, causing hidden dangers, especially if dependent software remains uninformed about the affected code repository. Hence, it is crucial to automatically locate security patches for disclosed vulnerabilities among a multitude of commits. Despite the promising performance of existing learning-based localization approaches, they still suffer from the following limitations: (1) They cannot perform well in data scarcity scenarios. Most neural models require extensive datasets to capture the semantic correlations between the vulnerability description and code commits, while the number of disclosed vulnerabilities with patches is limited. (2) They struggle to capture the deep semantic correlations between the vulnerability description and code commits due to inherent differences in semantics and characters between code changes and commit messages. It is difficult to use one model to capture the semantic correlations between vulnerability descriptions and code commits. To mitigate these two limitations, in this paper, we propose a novel security patch localization approach named Prom VPat, which utilizes the dual prompt tuning channel to capture the semantic correlation between vulnerability descriptions and commits, especially in data scarcity (i.e., few-shot) scenarios. We first input the commit message and code changes with the vulnerability description into the prompt generator to generate two new inputs with prompt templates. Then, we adopt a pre-trained language model (i.e., PLM) as the encoder, utilize the prompt tuning method to fine-tune the encoder, and generate two correlation probabilities as the semantic features. In addition, we extract 26 handcrafted features from the vulnerability descriptions and the code commits. Finally, we utilize the attention mechanism to fuse the

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Ratchet: Retrieval Augmented Transformer for Program Repair 35

Ratchet: Retrieval Augmented Transformer for Program Repair

引用

35th IEEE International Symposium on software Reliability engineering, ISSRE 2024

作者： Wang, Jian Liu, Shangqing Xie, Xiaofei Siow, Jingkai Liu, Kui Li, Yi Singapore Management University Singapore Nanyang Technological University Singapore Software Engineering Application Technology Laboratory Huawei China

ISBN: (纸本)9798350353884

Automated Program Repair (APR) presents the promising momentum of releasing developers from the burden of manual debugging tasks by automatically fixing bugs in various ways. Recent advances in deep learning inspire many works in employing deep learning techniques to fixing buggy programs. However, several challenges remain unaddressed: (1) state-of-the-art fault localization techniques often require additional artifacts, such as bug-triggering test cases or bug reports. These artifacts are not always available in the early development phases;(2) Sequence-to-Sequence model-based APR often requires additional contexts with high quality to generate patches. Yet, it is challenging to identify high-quality contexts that are not common in *** this paper, with the redundancy assumption in program repair, we propose a dual deep learning-based APR tool, RATCHET, for localizing (RATCHET-FL) and repairing (Ratchet-PG) buggy programs. Ratchet-FL localizes buggy statements based on the feature learned by a simple BiLSTM model from the code, without any bug-triggering test cases or bug reports. Ratchet-PG relies on our proposed retrieval augmented transformer to learn the historical patches and generate patches for fixing bugs. We evaluate the effectiveness of Ratchet with in-the-lab DrRepair dataset and in-the-wild dataset Ratchet-DS (curated in this work). Our experimental results show that Ratchet outperforms state-of-the-art deep learning approaches on fault localization with 39.8-96.4% accuracy and patch generation with 18.4-46.4% repair accuracy. © 2024 IEEE.

关键词： Program debugging

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：