Table of Contents

• On the Impact of Code Comments for Automated Bug-Fixing: An Empirical StudyAntonio Vitale, Emanuela Guglielmi, Simone Scalabrino, Rocco Oliveto. 1-13 [doi]
• Pretraining on Call Graphs: When Binary Analysis Tasks Profit From ContextSamuel Valenzuela, Johannes Kinder. 14-25 [doi]
• AutoLogger: A Multi-Agent Framework for the End-to-End Automated LoggingRenyi Zhong, Yintong Huo, Wenwei Gu, Yichen Li 0003, Michael R. Lyu. 26-37 [doi]
• PALM: Path-aware LLM-based Test Generation with ComprehensionYaoxuan Wu, Xiaojie Zhou, Ahmad Humayun, Muhammad Ali Gulzar, Miryung Kim. 38-48 [doi]
• Self-Improving Code Generation via Semantic Entropy and Behavioral ConsensusHuan Zhang 0019, Wei Cheng 0010, Wei Hu 0007. 49-60 [doi]
• EyeLayer: Integrating Human Attention Patterns into LLM-Based Code SummarizationJiahao Zhang, Yifan Zhang 0013, Kevin Leach, Yu Huang 0015. 61-72 [doi]
• Do Developers Read Type Information? An Eye-Tracking Study on TypeScriptSamuel W. Flint, Robert Dyer 0001, Bonita Sharif. 73-84 [doi]
• Eye-Tracking Insights into the Effects of Type Annotations and Identifier NamingNils Alznauer, Norman Peitek, Youssef Abdelsalam, Annabelle Bergum, Marvin Wyrich, Sven Apel. 85-96 [doi]
• LuaReSym: Recovering Variable Liveness Ranges in Stripped Lua Bytecode via Multi-Stage Static AnalysisWeilong Li, Ruizhi Xiao, Yabo Wang, Jiakun Sun, Yuqing Shao, Shuyuan Jin. 97-109 [doi]
• SQL-Commenter: Aligning Large Language Models for SQL Comment Generation with Direct Preference OptimizationLei Yu, Peng Wang, Jingyuan Zhang, Xin Wang, Jia Xu, Li Yang, Changzhi Deng, Jiajia Ma, Fengjun Zhang. 110-122 [doi]
• Grasping AI Reliance in Program Comprehension and Coding through the AIRELI Persona TaxonomyTarek Alakmeh, Norman Anderson, Victoria Jackson, Guilherme Vaz Pereira, Umit Akirmak, Anthony Estey, Rafael Prikladnicki, André van der Hoek, Margaret-Anne D. Storey, Thomas Fritz 0001. 123-134 [doi]
• Modubin: A Binary Modularization Approach Based on the Locality of Homologous FunctionsWenyan Yu, Lei Cui 0003, Jiayuan Li 0002, Yubo Li, Hong Li 0004, Kai Cheng, Hongsong Zhu. 135-145 [doi]
• Put The "Code" Back in "Code Comprehension Study"Kyle D. Chin, Reid Holmes. 146-158 [doi]
• RlDecompiler: Enhancing LLM-based Decompilation via Reinforcement Learning with a Multi-Faceted Reward FunctionYuChi Su, Weina Niu, Jiacheng Gong, Ran Yan, Song Li 0006, Xin Liu 0050, Xiaosong Zhang 0001. 159-170 [doi]
• SCOPE: Tree-based Self-Correcting Online Log Parsing via Syntactic-Semantic CollaborationDongyi Fan, Suqiong Zhang, Lili He 0006, Ming Liu, Yifan Huo. 171-182 [doi]
• Studying Quality Improvements Recommended via Manual and Automated Code ReviewGiuseppe Crupi, Rosalia Tufano, Gabriele Bavota. 183-194 [doi]
• Evaluating the Impact of Post-Training Quantization on Large Language Models for Code GenerationAlessandro Giagnorio, Antonio Mastropaolo, Saima Afrin, Massimiliano Di Penta, Gabriele Bavota. 195-206 [doi]
• Towards Universal Segmentation for Log ParsingVan-Hoang Le, Domenico Bianculli, Huy-Trung Nguyen. 207-219 [doi]
• The Way of Types: A Report on Developer Experience with Type-Driven DevelopmentSára Juhosová, Andy Zaidman, Jesper Cockx. 220-231 [doi]
• An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language ModelsChengli Xing, Zhengran Zeng, Gexiang Fang, Rui Xie 0003, Wei Ye 0004, Shikun Zhang. 232-244 [doi]
• A Comparative Study of Dual-Monitor and Augmented-Reality Interfaces for Digital-Twin-Based DebuggingLucas Kreber, Nico Feld, Stephan Diehl, Benjamin Weyers. 245-256 [doi]
• CodeGlance: Understanding Code Reasoning Challenges in LLMs through Multi-Dimensional Feature AnalysisYunkun Wang, Xuanhe Zhang, Junxiao Han, Chen Zhi, ShuiGuang Deng. 257-269 [doi]
• Leveraging Change Types and Contexts to Guide LLMs for Automated Test Code UpdatingTaicheng Huang, Xiangping Chen, Yuan Huang, Changlin Yang. 270-281 [doi]
• A Multi-Agent Framework for Automated Exploit Generation with Constraint-Guided Comprehension and ReflectionSiyi Chen, Tianhan Luo, Shijian Wu, Xiangyu Liu, Yilin Zhou, Qi Li, Wenyuan Xu. 282-294 [doi]
• Improved Bug Localization with AI Agents Leveraging Hypothesis and Dynamic CognitionAsif Mohammed Samir, Mohammad Masudur Rahman 0001. 295-306 [doi]
• A Code Ranking Framework with Human-Inspired Agent-Based Tests GenerationLiuwen Cao, Jiaxi Liang, Jiexin Wang 0002, Yi Cai 0001. 307-318 [doi]
• Guidelines to Prompt Large Language Models for Code Generation: An Empirical CharacterizationAlessandro Midolo, Alessandro Giagnorio, Fiorella Zampetti, Rosalia Tufano, Gabriele Bavota, Massimiliano Di Penta. 319-330 [doi]
• From Generation to Reasoning: Chain-of-Thought Guided Merge Conflict ResolutionChunyou Peng, Zhengnan Zhang, Shmuel S. Tyszberowicz, Zhiming Liu 0001, Bo Liu 0033. 331-342 [doi]
• Understanding Codebase like a Professional! Human-AI Collaboration for Code ComprehensionJie Gao, Yue Xue, Xiaofei Xie, Junming Cao, SoeMin Thant, Erika Lee, Bowen Xu. 343-354 [doi]
• RepoMind: Enhancing Repository-Level Code Generation via LLM Reasoning over Structured Repository DocumentationSongwen Gong, Mengzhen Wang, Jiexin Wang 0002, Yi Cai 0001. 355-366 [doi]
• SkelDPO: A Skeleton-Guided Direct Preference Optimization Framework for Efficient Code GenerationYu Yu, Chen Lyu. 367-378 [doi]
• Typify: A Lightweight Usage-driven Static Analyzer for Precise Python Type InferenceAli Aman, Muhammad Asaduzzaman, Shaowei Wang 0002. 379-389 [doi]
• Algorithm-Based Pipeline for Reliable and Intent-Preserving Code Translation with LLMsShahriar Rumi Dipto, Saikat Mondal, Chanchal K. Roy. 390-401 [doi]
• To GOTO or Not to GOTO: Measuring Structural Complexity of (Decompiled) CodeSteffen Enders, Eva-Maria C. Behner, Elmar Padilla. 402-414 [doi]
• Automated Test Suite Enhancement Using Large Language Models with Few-shot PromptingAlex Chudic, Gül Çalikli. 415-427 [doi]
• Understanding CI/CD Workflow Runs Through Interactive and Animated VisualizationsPablo Valenzuela-Toledo, Timo Kehrer, Sebastiano Panichella. 428-432 [doi]
• Attention to Innovation: Linking Developer Gaze and Coding ApproachesYahya Lafhal, Zohreh Sharafi, Mahta Amini. 433-437 [doi]
• Test Behaviors, Not Methods! Detecting Tests Obsessed by MethodsAndre Hora 0001, Andy Zaidman. 438-442 [doi]
• Understanding Type Hints in Python Libraries and Frameworks: Early InsightsThiago Roberto Magalhães, João Eduardo Montandon. 443-447 [doi]
• Precise LLM-based Semantic Slicing for Deadlock Detection in Concurrent Java ProgramsTaythir G. Martin, Rodion Podorozhny, Shibbir Ahmed. 448-452 [doi]
• CMind: An AI Agent for Localizing C Memory BugsChia-Yi Su, Collin McMillan. 453-457 [doi]
• CrossLink: A Tool for Cross-Language (Java-C/C++) Code ComprehensionAjinkya Sawarkar, Anirudh Arrepu, Sridhar Chimalakonda. 458-462 [doi]
• BF-CBOM: Uncovering Cryptographic Assets Through Comparative CBOM Analysis at ScaleRoman Bögli, Jonas Spieler, Timo Kehrer. 463-467 [doi]
• COBMaker - An Interactive Block-Based Programming Environment for COBOLSatish Pati, Raghavendra Pappu, Rahul Krishna Gaddam, Sridhar Chimalakonda. 468-472 [doi]
• CPPJoules: An Energy Measurement Tool for C++Shivadharshan S, Akilesh P, Rajrupa Chattaraj, Sridhar Chimalakonda. 473-477 [doi]
• Hyalinos: From Type Inference to Community KnowledgeLarisa Safina. 478-482 [doi]
• Can We Spot Energy Regressions Using Developers' Tests? An Industrial ReplicationLouay Khrouf, Anas Shatnawi, Romain Rouvoy. 483-491 [doi]
• Evaluating the use of Augmented Reality for Dependency Graph Analysis: A Controlled ExperimentJuan Pablo Sandoval Alcocer, Dussan Freire-Pozo, Tiara Rojas-Stambuk, Alison Fernandez Blanco, Leonel Merino. 492-503 [doi]
• LLMs for Qualitative Data Analysis Fail on Security-specific Comments in Human ExperimentsMaria Camporese, Fabio Massacci, Yuanjun Gong. 515-526 [doi]
• Industrial Replication of COLOR: Locator Repair in Continuous Integration and Failure Patterns under UI/DOM EvolutionHilal Taha, Mike Papadakis, Joel Muller. 527-536 [doi]
• Reducing Token Usage of State-in-Context Agents using MinificationNicolas Hrubec, Jürgen Cito. 537-546 [doi]
• Agile Story-Point Estimation: Is RAG a Better Way to Go?Lamyea Maha, Tajmilur Rahman, Chanchal Roy. 547-557 [doi]