DEVINTA

DEVINTA

DEVINTA (An Artificial Assistant for Software Developers) is a five-year project funded by the European Research Council - Starting Grant (ERC-StG). The project started in February 2020, and has the goal to set the foundations for a new generation of developers' recommender systems envisioned as artificial assistants able to provide various forms of support in different phases of the software lifecycle. Three main research challenges will be tackled:

1. Support developers in program comprehension activities by translating a given code into a natural language text explaining what the provided code does and guiding the developer step-by-step in its comprehension.


2. Predict the feature that the developer is implementing and suggest how to automatically complete the feature.


3. Provide support for online code review, meaning the ability to review in real time the code written by the developer, looking for possible bugs/suboptimal implementation choices. Solutions to remove the identified issues should be timely synthesized.

Team

Gabriele Bavota Principal Investigator

Luca Pascarella Postdoc

Emad Aghajani Postdoc

Rosalia Tufano PhD Student

Matteo Ciniselli PhD Student

Antonio Mastropaolo PhD Student

Publications

• Deep Learning-based Code Reviews: A Paradigm Shift or a Double-Edged Sword?
  R. Tufano, A. Martin-Lopez, A. Tayeb, O. Dabic, S. Haiduc, G. Bavota.
  International Conference on Software Engineering (ICSE 2025).


• Code Review Automation: Strengths and Weaknesses of the State of the Art.
  R. Tufano, O. Dabic, A. Mastropaolo, M. Ciniselli, G. Bavota.
  Transactions on Software Engineering (TSE 2024).


• Evaluating Code Summarization Techniques: A New Metric and an Empirical Characterization.
  A. Mastropaolo, M. Ciniselli, M. Di Penta, G. Bavota.
  International Conference on Software Engineering (ICSE 2024).


• Toward Automatically Completing GitHub Workflows.
  A. Mastropaolo, F. Zampetti, G. Bavota, M. Di Penta.
  International Conference on Software Engineering (ICSE 2024).


• Unveiling ChatGPT's Usage in Open Source Projects: A Mining-based Study.
  R. Tufano, A. Mastropaolo, F. Pepe, O. Dabic, M. Di Penta, G. Bavota.
  International Conference on Mining Software Repositories (MSR 2024).


• On the Generalizability of Transformer Models to Code Completions of Different Lengths.
  N. Cooper, R. Tufano, G. Bavota, D. Poshyvanyk.
  International Conference on Software Maintenance and Evolution (ICSME 2024).


• Deep Learning-based Code Completion: On the Impact on Performance of Contextual Information.
  M. Ciniselli, L. Pascarella, G. Bavota.
  International Conference on Software Maintenance and Evolution (ICSME 2024).


• SEART Data Hub: Streamlining Large-Scale Source Code Mining and Pre-Processing.
  O. Dabic, R. Tufano, G. Bavota.
  International Conference on Software Maintenance and Evolution - Tool (ICSME 2024).


• On the Generalizability of Deep Learning-based Code Completion Across Programming Language Versions.
  M. Ciniselli, A. Martin-Lopez, G. Bavota.
  International Conference on Program Comprehension (ICPC 2024).


• Towards Summarizing Code Snippets Using Pre-Trained Transformers.
  A. Mastropaolo, M. Ciniselli, L. Pascarella, R. Tufano, E. Aghajani, G. Bavota.
  International Conference on Program Comprehension (ICPC 2024).


• How do Hugging Face Models Document Datasets, Bias, and Licenses? An Empirical Study.
  F. Pepe, V. Nardone, A. Mastropaolo, G. Bavota, G. Canfora, M. Di Penta.
  International Conference on Program Comprehension (ICPC 2024).


• Automated Variable Renaming: Are We There Yet?
  A. Mastropaolo, E. Aghajani, L. Pascarella, G. Bavota.
  Journal of Empirical Software Engineering (EMSE 2023).


• Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?.
  A. Mastropaolo, M. Di Penta, G. Bavota.
  International Conference on Automated Software Engineering (ASE 2023).


• Automating Code-Related Tasks Through Transformers: The Impact of Pre-training.
  R. Tufano, L. Pascarella, G. Bavota.
  International Conference on Software Engineering (ICSE 2023).


• On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot.
  A. Mastropaolo, L. Pascarella, E. Guglielmi, M. Ciniselli, S. Scalabrino, R. Oliveto, G. Bavota.
  International Conference on Software Engineering (ICSE 2023).


• Source Code Recommender Systems: The Practitioners' Perspective.
  M. Ciniselli, L. Pascarella, E. Aghajani, S. Scalabrino, R. Oliveto, G. Bavota.
  International Conference on Software Engineering (ICSE 2023).


• Don't Reinvent the Wheel: Towards Automatic Replacement of Custom Implementations with APIs.
  R. Tufano, E. Aghajani, G. Bavota.
  International Conference on Software Maintenance and Evolution - NIER (ICSME 2022).


• Using Transfer Learning for Code-Related Tasks.
  A. Mastropaolo, N. Cooper, D. Palacio, S. Scalabrino, D. Poshyvanyk, R. Oliveto, G. Bavota.
  Transactions on Software Engineering (TSE 2023).


• Using Pre-Trained Models to Boost Code Review Automation.
  R. Tufano, S. Masiero, A. Mastropaolo, L. Pascarella, D. Poshyvanyk, G. Bavota.
  International Conference on Software Engineering (ICSE 2022).


• Using Reinforcement Learning for Load Testing of Video Games.
  R. Tufano, S. Scalabrino, L. Pascarella, E. Aghajani, R. Oliveto, G. Bavota.
  International Conference on Software Engineering (ICSE 2022).


• Using Deep Learning to Generate Complete Log Statements.
  A. Mastropaolo, L. Pascarella, G. Bavota.
  International Conference on Software Engineering (ICSE 2022).


• An Empirical Study on the Usage of Transformer Models for Code Completion.
  M. Ciniselli, N. Cooper, L. Pascarella, A. Mastropaolo, E. Aghajani, D. Poshyvanyk, M. Di Penta, G. Bavota.
  Transactions on Software Engineering (TSE 2022).


• Towards Automating Code Review Activities.
  R. Tufano, L. Pascarella, M. Tufano, D. Poshyvanyk, G. Bavota.
  International Conference on Software Engineering (ICSE 2021).


• Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks.
  A. Mastropaolo, S. Scalabrino, N. Cooper, D. Palacio, D. Poshyvanyk, R. Oliveto, G. Bavota.
  International Conference on Software Engineering (ICSE 2021).


• Evaluating SZZ Implementations Through a Developer-informed Oracle.
  G. Rosa, L. Pascarella, S. Scalabrino, R. Tufano, G. Bavota, M. Lanza, R. Oliveto.
  International Conference on Software Engineering (ICSE 2021).


• FeaRS: Recommending Complete Android Method Implementations.
  F. Wen, V. Ferrari, E. Aghajani, C. Nagy, M. Lanza, G. Bavota.
  International Conference on Software Maintenance and Evolution (ICSME 2021).


• An Empirical Study on the Usage of BERT Models for Code Completion.
  M. Ciniselli, N. Cooper, L. Pascarella, D. Poshyvanyk, M. Di Penta, G. Bavota.
  International Conference on Mining Software Repositories (MSR 2021).


• Sampling Projects in GitHub for MSR Studies.
  O. Dabic, E. Aghajani, G. Bavota.
  International Conference on Mining Software Repositories (MSR 2021).


• An Empirical Study on Code Comment Completion.
  A. Mastropaolo, E. Aghajani, L. Pascarella, G. Bavota.
  International Conference on Software Maintenance and Evolution (ICSME 2021).


• Why Developers Refactor Source Code: A Mining-based Study.
  J. Pantiuchina, F. Zampetti, S. Scalabrino, V. Piantadosi, R. Oliveto, G. Bavota, M. Di Penta.
  Transactions on Software Engineering and Methodology (TOSEM 2021).


• On the Relationship between Refactoring Actions and Bugs: A Differentiated Replication.
  M. Di Penta, G. Bavota, F. Zampetti.
  ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2020).

Open Positions

There are currently no open positions.

Contacts

Gabriele Bavota

Address: Università della Svizzera italiana (USI), Via G. Buffi 13, 6900 Lugano
Email: gabriele.bavota [at] usi [dot] ch
Website: https://www.inf.usi.ch/faculty/bavota/