An Artificial Assistant for Software Developers

Informations projet

DEVINTA

N° de convention de subvention: 851720

DOI

10.3030/851720

Projet clôturé

Date de signature de la CE 6 Septembre 2019

Date de début 1 Février 2020

Date de fin 31 Juillet 2025

Financé au titre de

• EXCELLENT SCIENCE - European Research Council (ERC)

Coût total

€ 1 499 093,00

Contribution de l’UE

€ 1 499 093,00

Coordonné par

UNIVERSITA DELLA SVIZZERA ITALIANA
Switzerland

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Publications

Conference proceedings (27)

On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot

Auteurs: Antonio Mastropaolo, Luca Pascarella, Emanuela Guglielmi, Matteo Ciniselli, Simone Scalabrino, Rocco Oliveto, Gabriele Bavota
Publié dans: 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), 2023
Éditeur: IEEE
DOI: 10.1109/icse48619.2023.00181

Evaluating Code Summarization Techniques: A New Metric and an Empirical Characterization

Auteurs: Antonio Mastropaolo, Matteo Ciniselli, Massimiliano Di Penta, Gabriele Bavota
Publié dans: Proceedings of the IEEE/ACM 46th International Conference on Software Engineering, 2024
Éditeur: ACM
DOI: 10.1145/3597503.3639174

SEART Data Hub: Streamlining Large-Scale Source Code Mining and Pre-Processing

Auteurs: Ozren Dabić, Rosalia Tufano, Gabriele Bavota
Publié dans: 2024 IEEE International Conference on Software Maintenance and Evolution (ICSME), 2024, Page(s) 888-892
Éditeur: IEEE
DOI: 10.1109/icsme58944.2024.00097

Source Code Recommender Systems: The Practitioners' Perspective

Auteurs: Matteo Ciniselli, Luca Pascarella, Emad Aghajani, Simone Scalabrino, Rocco Oliveto, Gabriele Bavota
Publié dans: 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), 2024
Éditeur: IEEE
DOI: 10.1109/icse48619.2023.00182

Don’t Reinvent the Wheel: Towards Automatic Replacement of Custom Implementations with APIs

Auteurs: Rosalia Tufano, Emad Aghajani, Gabriele Bavota
Publié dans: 2022 IEEE International Conference on Software Maintenance and Evolution (ICSME), 2022, Page(s) 394-398
Éditeur: IEEE
DOI: 10.1109/icsme55016.2022.00046

How the Training Procedure Impacts the Performance of Deep Learning-based Vulnerability Patching

Auteurs: Antonio Mastropaolo, Vittoria Nardone, Gabriele Bavota, Massimiliano Di Penta
Publié dans: Proceedings of the 28th International Conference on Evaluation and Assessment in Software Engineering, 2024
Éditeur: ACM
DOI: 10.1145/3661167.3661200

To What Extent do Deep Learning-based Code Recommenders Generate Predictions by Cloning Code from the Training Set?

Auteurs: Matteo Ciniselli, Luca Pascarella, Gabriele Bavota
Publié dans: 2022 IEEE/ACM 19th International Conference on Mining Software Repositories (MSR), 2022, Page(s) 167-178
Éditeur: IEEE
DOI: 10.1145/3524842.3528440

Unveiling ChatGPT's Usage in Open Source Projects: A Mining-based Study

Auteurs: Rosalia Tufano, Antonio Mastropaolo, Federica Pepe, Ozren Dabic, Massimiliano Di Penta, Gabriele Bavota
Publié dans: Proceedings of the 21st International Conference on Mining Software Repositories, Numéro 48, 2024, Page(s) 571-583
Éditeur: ACM
DOI: 10.1145/3643991.3644918

Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?

Auteurs: Antonio Mastropaolo, Massimiliano Di Penta, Gabriele Bavota
Publié dans: 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2023
Éditeur: IEEE
DOI: 10.1109/ase56229.2023.00103

Using pre-trained models to boost code review automation

Auteurs: Rosalia Tufano, Simone Masiero, Antonio Mastropaolo, Luca Pascarella, Denys Poshyvanyk, Gabriele Bavota
Publié dans: 2022 ACM/IEEE 44th International Conference on Software Engineering (ICSE), 2022, Page(s) 2291–2302
Éditeur: ACM
DOI: 10.1145/3510003.3510621

Using deep learning to generate complete log statements

Auteurs: Antonio Mastropaolo, Luca Pascarella, Gabriele Bavota
Publié dans: 2022 ACM/IEEE 44th International Conference on Software Engineering (ICSE), 2022, Page(s) 2279–2290
Éditeur: ACM
DOI: 10.1145/3510003.3511561

On the relationship between refactoring actions and bugs: a differentiated replication

Auteurs: Massimiliano Di Penta, Gabriele Bavota, Fiorella Zampetti
Publié dans: Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020, Page(s) 556-567, ISBN 9781450370431
Éditeur: ACM
DOI: 10.1145/3368089.3409695

Using reinforcement learning for load testing of video games

Auteurs: Rosalia Tufano, Simone Scalabrino, Luca Pascarella, Emad Aghajani, Rocco Oliveto, Gabriele Bavota
Publié dans: 2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE), 2022, Page(s) 2303–2314
Éditeur: ACM
DOI: 10.1145/3510003.3510625

An Empirical Study on Code Comment Completion

Auteurs: Antonio Mastropaolo, Emad Aghajani, Luca Pascarella, Gabriele Bavota
Publié dans: 2021 IEEE International Conference on Software Maintenance and Evolution (ICSME), 2021, Page(s) 159-170, ISBN 978-1-6654-2882-8
Éditeur: IEEE
DOI: 10.1109/icsme52107.2021.00021

Sampling Projects in GitHub for MSR Studies

Auteurs: Ozren Dabic, Emad Aghajani, Gabriele Bavota
Publié dans: 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR), 2021, Page(s) 560-564, ISBN 978-1-7281-8710-5
Éditeur: IEEE
DOI: 10.1109/msr52588.2021.00074

On the Generalizability of Deep Learning-based Code Completion Across Programming Language Versions

Auteurs: Matteo Ciniselli, Alberto Martin-Lopez, Gabriele Bavota
Publié dans: Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension, 2024
Éditeur: ACM
DOI: 10.1145/3643916.3644411

Towards Automating Code Review Activities

Auteurs: Rosalia Tufano, Luca Pascarella, Michele Tufano, Denys Poshyvanyk, Gabriele Bavota
Publié dans: 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), 2021, Page(s) 163-174, ISBN 978-1-6654-0296-5
Éditeur: IEEE
DOI: 10.1109/icse43902.2021.00027

Toward Automatically Completing GitHub Workflows

Auteurs: Antonio Mastropaolo, Fiorella Zampetti, Gabriele Bavota, Massimiliano Di Penta
Publié dans: Proceedings of the IEEE/ACM 46th International Conference on Software Engineering, 2024
Éditeur: ACM
DOI: 10.1145/3597503.3623351

Automating Code-Related Tasks Through Transformers: The Impact of Pre-training

Auteurs: Rosalia Tufano, Luca Pascarella, Gabriele Bavota
Publié dans: 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), 2024
Éditeur: IEEE
DOI: 10.1109/icse48619.2023.00203

On the Generalizability of Transformer Models to Code Completions of Different Lengths

Auteurs: Nathan Cooper, Rosalia Tufano, Gabriele Bavota, Denys Poshyvanyk
Publié dans: 2024 IEEE International Conference on Software Maintenance and Evolution (ICSME), 2024, Page(s) 375-387
Éditeur: IEEE
DOI: 10.1109/icsme58944.2024.00042

Deep Learning-based Code Reviews: A Paradigm Shift or a Double-Edged Sword?

Auteurs: Rosalia Tufano, Alberto Martin-Lopez, Ahmad Tayeb, Ozren Dabić, Sonia Haiduc, Gabriele Bavota
Publié dans: 2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE), 2025, Page(s) 1640-1652
Éditeur: IEEE
DOI: 10.1109/icse55347.2025.00060

Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks

Auteurs: Antonio Mastropaolo, Simone Scalabrino, Nathan Cooper, David Nader Palacio, Denys Poshyvanyk, Rocco Oliveto, Gabriele Bavota
Publié dans: 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), 2021, Page(s) 336-347, ISBN 978-1-6654-0296-5
Éditeur: IEEE
DOI: 10.1109/icse43902.2021.00041

Quality In, Quality Out: Investigating Training Data's Role in AI Code Generation

Auteurs: Cristina Improta, Rosalia Tufano, Pietro Liguori, Domenico Cotroneo, Gabriele Bavota
Publié dans: 2025 IEEE/ACM 33rd International Conference on Program Comprehension (ICPC), 2025, Page(s) 454-465
Éditeur: IEEE
DOI: 10.1109/icpc66645.2025.00056

Deep Learning-Based Code Completion: On the Impact on Performance of Contextual Information

Auteurs: Matteo Ciniselli, Luca Pascarella, Gabriele Bavota
Publié dans: 2024 IEEE International Conference on Software Maintenance and Evolution (ICSME), 2024, Page(s) 211-223
Éditeur: IEEE
DOI: 10.1109/icsme58944.2024.00029

An Empirical Study on the Usage of BERT Models for Code Completion

Auteurs: Matteo Ciniselli, Nathan Cooper, Luca Pascarella, Denys Poshyvanyk, Massimiliano Di Penta, Gabriele Bavota
Publié dans: 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR), 2021, Page(s) 108-119, ISBN 978-1-7281-8710-5
Éditeur: IEEE
DOI: 10.1109/msr52588.2021.00024

Evaluating SZZ Implementations Through a Developer-Informed Oracle

Auteurs: Giovanni Rosa, Luca Pascarella, Simone Scalabrino, Rosalia Tufano, Gabriele Bavota, Michele Lanza, Rocco Oliveto
Publié dans: 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), 2021, Page(s) 436-447, ISBN 978-1-6654-0296-5
Éditeur: IEEE
DOI: 10.1109/icse43902.2021.00049

Towards Summarizing Code Snippets Using Pre-Trained Transformers

Auteurs: Antonio Mastropaolo, Matteo Ciniselli, Luca Pascarella, Rosalia Tufano, Emad Aghajani, Gabriele Bavota
Publié dans: Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension, 2024
Éditeur: ACM
DOI: 10.1145/3643916.3644400

Peer reviewed articles (7)

Automated variable renaming: are we there yet?

Auteurs: Antonio Mastropaolo, Emad Aghajani, Luca Pascarella, Gabriele Bavota
Publié dans: Empirical Software Engineering, Numéro 28, 2023, ISSN 1382-3256
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s10664-022-10274-8

Why Developers Refactor Source Code

Auteurs: Jevgenija Pantiuchina, Fiorella Zampetti, Simone Scalabrino, Valentina Piantadosi, Rocco Oliveto, Gabriele Bavota, Massimiliano Di Penta
Publié dans: ACM Transactions on Software Engineering and Methodology, Numéro 29/4, 2020, Page(s) 1-30, ISSN 1049-331X
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3408302

Using Transfer Learning for Code-Related Tasks

Auteurs: Antonio Mastropaolo, Nathan Cooper, David Nader-Palacio, Simone Scalabrino, Denys Poshyvanyk, Rocco Oliveto, Gabriele Bavota
Publié dans: IEEE Transactions on Software Engineering, 2022, ISSN 0098-5589
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tse.2022.3183297

Code Review Automation: Strengths and Weaknesses of the State of the Art

Auteurs: Rosalia Tufano, Ozren Dabić, Antonio Mastropaolo, Matteo Ciniselli, Gabriele Bavota
Publié dans: IEEE Transactions on Software Engineering, Numéro 50, 2024, Page(s) 338-353, ISSN 0098-5589
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tse.2023.3348172

A comprehensive evaluation of SZZ Variants through a developer-informed oracle

Auteurs: Giovanni Rosa, Luca Pascarella, Simone Scalabrino, Rosalia Tufano, Gabriele Bavota, Michele Lanza, Rocco Oliveto
Publié dans: Journal of Systems and Software, Numéro 202, 2024, Page(s) 111729, ISSN 0164-1212
Éditeur: Elsevier BV
DOI: 10.1016/j.jss.2023.111729

An Empirical Study on the Usage of Transformer Models for Code Completion

Auteurs: Matteo Ciniselli, Nathan Cooper, Luca Pascarella, Antonio Mastropaolo, Emad Aghajani, Denys Poshyvanyk, Massimiliano Di Penta, Gabriele Bavota
Publié dans: IEEE Transactions on Software Engineering, 2021, ISSN 0098-5589
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tse.2021.3128234

Log statements generation via deep learning: Widening the support provided to developers

Auteurs: Antonio Mastropaolo, Valentina Ferrari, Luca Pascarella, Gabriele Bavota
Publié dans: Journal of Systems and Software, Numéro 210, 2024, Page(s) 111947, ISSN 0164-1212
Éditeur: Elsevier BV
DOI: 10.1016/j.jss.2023.111947