ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “Repository analysis”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.SEcs.AIcs.IREmpiricalRecentJul 9, 2026

ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation

QiHong Chen, Aaron Imani, Iftekhar Ahmed

Proposed ProjAgent, a repository-level code generation system using procedural similarity for retrieval and conservative static-analysis feedback.

View →
cs.HCcs.AIEmpiricalRecentAug 10, 2026

Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations

Weijie Liang, Yuanfeng Song, Xing Chen, Caleb Chen Cao +2 more

This paper evaluates the use of rendered code as operational context for agentic coding, showing consistent reduction in prompt-token cost but limited increase in linear savings and end-to-end repair…

View →
cs.SEcs.AIcs.CLRecentJun 4, 2026

Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution

Liliana Hotsko, Yinxi Li, Yuntian Deng, Pengyu Nie

Code2LoRA introduces a hypernetwork framework to efficiently inject repository-specific knowledge into code language models using LoRA adapters, supporting both static and evolving codebases.

View →
cs.CREmpiricalRecentJul 1, 2026

Antaeus: Hunting Repository-Level Logic Vulnerabilities via Context-Grounded LLM Reasoning

Michele Armillotta, Nicolò Romandini, Rebecca Montanari, Lorenzo Cavallaro

Antaeus is a framework that uses repository-level code context to detect logic vulnerabilities using LLM reasoning, reducing calls, cost, and triage effort.

View →
cs.CRcs.SEMay 7, 2026

Heimdallr: Characterizing and Detecting LLM-Induced Security Risks in GitHub CI Workflows

Bonan Ruan, Yeqi Fu, Chuqi Zhang, Jiahao Liu +2 more

This paper introduces Heimdallr, a novel framework that characterizes and detects LLM-induced security risks by analyzing the full execution chain of LLM integrations within GitHub CI workflows.

View →
cs.CRcs.LGEmpiricalRecentJun 17, 2026

OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing

Nahum Korda, Gadi Evron

This paper presents OpenAnt, a system for automated vulnerability discovery in large codebases using a multi-stage pipeline combining static analysis and large language models.

View →
cs.CRcs.SEEmpiricalRecentJul 16, 2026

The Distributed Open-Source Vulnerability Ecosystem

Peter Mandl, Paul Mandl

This paper explores the causes of inconsistent vulnerability scanner findings in the open-source ecosystem.

View →
cs.SEcs.CREmpiricalRecentJun 21, 2026

On Good Authority: Release-Authority Measurement for Registry-Mediated Package Ecosystems

Igor Santos-Grueiro

The paper introduces a predecessor-aware release-authority record to compare package releases with their immediate predecessors.

View →
cs.CRApr 22, 2026

Hidden Secrets in the arXiv: Discovering, Analyzing, and Preventing Unintentional Information Disclosure in Source Files of Scientific Preprints

Jan Pennekamp, Johannes Lohmöller, David Schütte, Joscha Loos +1 more

This paper systematically analyzes 2.7 million arXiv submissions to demonstrate that nearly every preprint unintentionally discloses sensitive or unnecessary information through its source files, prop…

View →
cs.SEcs.CRMar 25, 2026

Software Supply Chain Smells: Lightweight Analysis for Secure Dependency Management

Larissa Schmid, Diogo Gaspar, Raphina Liu, Sofia Bobadilla +2 more

The paper introduces 'software supply chain smells,' structural indicators of security risks in third-party dependencies, and presents Dirty-Waters, a tool that detects these smells, finding that diff…

View →
cs.SEcs.AIRecentMay 28, 2026

Code-QA-Bench: Separating Code Reasoning from Documentation Memorization in Repository-Level QA

Jun Zhang, JianYing Qu, Hanwen Du, Zhongkai Sun +2 more

The paper introduces Code-QA-Bench, a novel framework that rigorously separates genuine code reasoning from mere documentation memorization in repository-level code understanding benchmarks.

View →
cs.SEEmpiricalRecentJun 17, 2026

Toward Semantically-Seeded, Graph-Propagated Impact Analysis Across Software Artifacts: A Vision

Momil Seedat

This paper proposes a change-impact-analysis tool that fuses semantic and structural signals to identify impacted artifacts.

View →
cs.CREmpiricalRecentOct 16, 2026

Trojan Horse: Automated Repository Poisoning against Coding Agents

Xiao Yang, Jinchang Hou, Jiawei Chen, Zhonghou Lv +2 more

The paper presents TrojanForge, an automated framework for repository poisoning that achieves a stable poisoning success rate of over 60%.

View →
cs.CRMay 11, 2026

Towards LLM-Based Analysis of Virtualization-Obfuscated Code through Automated Data Generation

Sangjun An, Hyeyeon Park, Yejin Son, Seoksu Lee +1 more

The paper proposes a novel framework to analyze large, obfuscated binaries by decomposing them into structurally coherent units, enabling large-scale dataset generation for LLM-based analysis.

View →
cs.SEcs.AIEmpiricalRecentJul 22, 2026

Don't Trust the Label: License Laundering in AI Supply Chains

James Jewitt, Hao Li, Gopi Krishnan Rajbahadur, Bram Adams +1 more

This paper investigates the survival of licenses in the supply chain of AI artifacts, finding that a large percentage of artifacts lack declared licenses and that obligation-bearing licenses have low…

View →
cs.CRcs.SEApr 23, 2026

CrossCommitVuln-Bench: A Dataset of Multi-Commit Python Vulnerabilities Invisible to Per-Commit Static Analysis

Arunabh Majumdar

The paper introduces CrossCommitVuln-Bench, a benchmark dataset demonstrating that many real-world Python vulnerabilities are introduced across multiple commits, making them invisible to standard per-…

View →