Rohith Pudari

I am a PhD candidate in the FORCOLAB research group at the University of Toronto, where I am advised by Prof. Shurui Zhou. My research lies at the intersection of machine learning and software engineering, with a particular interest in understanding how AI can support developers throughout the software development lifecycle.

My work focuses on leveraging machine learning techniques to make software development more efficient, effective, and accessible. In particular, I study open-source software ecosystems and developer communities, exploring how large-scale data from code repositories, documentation, and developer interactions can be used to improve software engineering practices and tooling.

Prior to joining the University of Toronto, I completed my M.Sc. in Computer Science at the University of Victoria under the supervision of Prof. Neil Ernst, where I investigated the role of AI-assisted tools in software development and their impact on developer productivity and workflows.

Master's Thesis

AI Supported Software Development: Moving beyond Code Completion
Committee: Prof. Neil Ernst, Prof. Jens Weber
Slides

Education

PhD Candidate in Software Engineering
University of Toronto (2022 - 2026).
Advisor: Prof. Shurui Zhou

MSc in Computer Science
University of Victoria (2020 - 2022).
Advisor: Prof. Neil Ernst

B.Tech in Information Technology, 2019
Sreenidhi Institute of Science and Technology (2015 - 2019).

news

Jun 08, 2026	Our paper “When Tools Overlook Domain Knowledge: An Empirical Study of Refactoring in Scientific Software” co-authored with Ahmed Musa Awon, Prof. Neil Ernst and Prof Shurui Zhou has been accepted to ACM Transactions on Software Engineering and Methodology (TOSEM). Preprint will be available soon.
Oct 05, 2023	Our paper “Aligning Documentation and Q&A Forum through Constrained Decoding with Weak Supervision” co-authored with Shiyuan Zhou, Prof. Iftekhar Ahmed, Dr. Zhuyun Dai and Prof Shurui Zhou has been accepted to the ICSME 2023 New Ideas and Emerging Results Track!. This paper is available in my publications page.

selected publications

TOSEM

When Tools Overlook Domain Knowledge: An Empirical Study of Refactoring in Scientific Software

Rohith Pudari, Neil A. Ernst, and Shurui Zhou

ACM Transactions on Software Engineering and Methodology (TOSEM), Jun 2026

Just Accepted

Abs

Refactoring is a critical process for improving code quality, but anecdotal evidence has shown that refactoring in scientific software (Sci-SW ) is not always feasible. The inherently exploratory nature of Sci-SW development, characterized by evolving requirements andlimited adoption of traditional software engineering practices, could present significant challenges to refactoring. However, there is nosystematic study exploring refactoring practices in Sci-OSS. To bridge this gap, we explore the effectiveness of three state-of-the-art refactoring detection tools: RefDiff (C), RefactoringMiner (Java), and PyRef (Python) to detect refactorings in scientific open-source software (Sci-OSS). Our findings reveal that these tools have significant limitations, detecting fewer refactorings in Sci-OSS than non-scientific OSS (Non-Sci-OSS). Through a mixed-method approach, we identified that 67.54% of undetected refactorings in Sci-OSS require domain knowledge. To complement our analysis of the refactoring changes, we conducted surveys with 47 practitioners experienced in refactoring Sci-OSS and 14 follow-up interviews to gain deeper insights into the associated challenges. Our results revealed seven novel challenges for Sci-OSS-refactoring, including a domain knowledge gap. These findings emphasize the necessity for specialized tools and strategies to support refactoring in Sci-OSS effectively.
ICSME
Aligning Documentation and Q&A Forum through Constrained Decoding with Weak Supervision

Rohith Pudari, Shiyuan Zhou, Iftekhar Ahmed, Zhuyun Dai, and Shurui Zhou

In 2023 IEEE International Conference on Software Maintenance and Evolution (ICSME), Oct 2023

Abs DOI Bib PDF Blog Slides

Stack Overflow (SO) is a widely used question-and-answer (Q&A) forum dedicated to software development. It plays a supplementary role to official documentation (DOC for short) by offering practical examples and resolving uncertainties. However, the process of simultaneously consulting both the documentation and SO posts can be challenging and time-consuming due to their disconnected nature. In this study, we propose DOSA, a novel approach to automatically align SO and DOC, which inject domain-specific knowledge about the DOC structure into large language models (LLMs) through weak supervision and constrained decoding, thereby enhancing knowledge retrieval and streamlining task completion during the software development procedure. Our preliminary experiments find that DOSA outperforms various widely-used baselines, showing the promise of using generative retrieval models to perform low-resource software engineering tasks.
@inproceedings{pudari2023dosa, author = {Pudari, Rohith and Zhou, Shiyuan and Ahmed, Iftekhar and Dai, Zhuyun and Zhou, Shurui}, booktitle = {2023 IEEE International Conference on Software Maintenance and Evolution (ICSME)}, title = {Aligning Documentation and Q&A Forum through Constrained Decoding with Weak Supervision}, year = {2023}, volume = {}, number = {}, pages = {346-351}, keywords = {}, doi = {10.1109/ICSME58846.2023.00043}, issn = {2576-3148}, month = oct, }