works on

From the 1 of 14 linked papers with an AI index.

collaborators

14 papers

cs.SE2026

Detecting Behavioral Changes in Python Refactoring Implementations with Foundation Models

Jonhnanthan Oliveira, Rohit Gheyi, Márcio Ribeiro +1

Python is a widely adopted programming language, valued for its simplicity and flexibility. However, automated refactoring for Python remains challenging, even though refactoring i…

cs.SE2026

Comprehending Python Repetition Structures: An Eye-Tracking Study with Novice Developers

José Júnior Silva da Costa, Rohit Gheyi, José Aldo Silva da Costa +1

Code comprehension is central to software maintenance and evolution, yet different Python repetition structures may impose distinct cognitive demands. We conducted a controlled eye…

cs.SE2026

AI-Conducted Interviews in Empirical Software Engineering: An Experience Report

Rohit Gheyi, Danyllo Albuquerque, Márcio Ribeiro +1

The paper reports on using a customized AI system (MyGPT) to conduct short, self‑administered, voice‑based interviews in empirical software engineering studies, evaluating particip…

cs.SE2026

Foundation Models as Oracles for Refactoring Correctness Detection

Rohit Gheyi, Rian Melo, Jonhnanthan Oliveira +2

Refactoring tools in popular Integrated Development Environments (IDEs) can introduce unintended behavioral changes or compilation errors, a persistent challenge that undermines de…

cs.SE2026

An Empirical Study of Gemini 3 for Detecting Natural Language Test Smells in Manual Test Cases

Keila Lucas, Rohit Gheyi, Márcio Ribeiro +4

Manual testing, in which testers follow natural language instructions to validate system behavior, remains essential for uncovering issues that are difficult to capture with automa…

cs.SE2026

Vulnerability Detection with Interprocedural Context in Multiple Languages: Assessing Effectiveness and Cost of Modern LLMs

Kevin Lira, Baldoino Fonseca, Davy Baía +2

Large Language Models (LLMs) have been a promising way for automated vulnerability detection. However, most prior studies have explored the use of LLMs to detect vulnerabilities on…