An Artificial Assistant for Software Developers

Informacje na temat projektu

DEVINTA

Identyfikator umowy o grant: 851720

DOI 10.3030/851720

Data podpisania przez KE 6 Września 2019

Data rozpoczęcia 1 Lutego 2020

Data zakończenia 31 Lipca 2025

Finansowanie w ramach

• EXCELLENT SCIENCE - European Research Council (ERC)

Koszt całkowity € 1 499 093,00

Wkład UE € 1 499 093,00

Koordynowany przez

UNIVERSITA DELLA SVIZZERA ITALIANA
Szwajcaria

CORDIS oferuje możliwość skorzystania z odnośników do publicznie dostępnych publikacji i rezultatów projektów realizowanych w ramach programów ramowych HORYZONT.

Odnośniki do rezultatów i publikacji związanych z poszczególnymi projektami 7PR, a także odnośniki do niektórych konkretnych kategorii wyników, takich jak zbiory danych i oprogramowanie, są dynamicznie pobierane z systemu OpenAIRE .

Publikacje

Materiały z konferencji (22)

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

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

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

Autorzy: Antonio Mastropaolo, Matteo Ciniselli, Massimiliano Di Penta, Gabriele Bavota
Opublikowane w: Proceedings of the IEEE/ACM 46th International Conference on Software Engineering, 2024
Wydawca: ACM
DOI: 10.1145/3597503.3639174

Source Code Recommender Systems: The Practitioners' Perspective

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

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

Autorzy: Rosalia Tufano, Emad Aghajani, Gabriele Bavota
Opublikowane w: 2022 IEEE International Conference on Software Maintenance and Evolution (ICSME), 2022, Strona(/y) 394-398
Wydawca: IEEE
DOI: 10.1109/icsme55016.2022.00046

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

Autorzy: Antonio Mastropaolo, Vittoria Nardone, Gabriele Bavota, Massimiliano Di Penta
Opublikowane w: Proceedings of the 28th International Conference on Evaluation and Assessment in Software Engineering, 2024
Wydawca: ACM
DOI: 10.1145/3661167.3661200

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

Autorzy: Matteo Ciniselli, Luca Pascarella, Gabriele Bavota
Opublikowane w: 2022 IEEE/ACM 19th International Conference on Mining Software Repositories (MSR), 2022, Strona(/y) 167-178
Wydawca: IEEE
DOI: 10.1145/3524842.3528440

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

Autorzy: Rosalia Tufano, Antonio Mastropaolo, Federica Pepe, Ozren Dabic, Massimiliano Di Penta, Gabriele Bavota
Opublikowane w: Proceedings of the 21st International Conference on Mining Software Repositories, Numer 48, 2024, Strona(/y) 571-583
Wydawca: ACM
DOI: 10.1145/3643991.3644918

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

Autorzy: Antonio Mastropaolo, Massimiliano Di Penta, Gabriele Bavota
Opublikowane w: 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2023
Wydawca: IEEE
DOI: 10.1109/ase56229.2023.00103

Using pre-trained models to boost code review automation

Autorzy: Rosalia Tufano, Simone Masiero, Antonio Mastropaolo, Luca Pascarella, Denys Poshyvanyk, Gabriele Bavota
Opublikowane w: 2022 ACM/IEEE 44th International Conference on Software Engineering (ICSE), 2022, Strona(/y) 2291–2302
Wydawca: ACM
DOI: 10.1145/3510003.3510621

Using deep learning to generate complete log statements

Autorzy: Antonio Mastropaolo, Luca Pascarella, Gabriele Bavota
Opublikowane w: 2022 ACM/IEEE 44th International Conference on Software Engineering (ICSE), 2022, Strona(/y) 2279–2290
Wydawca: ACM
DOI: 10.1145/3510003.3511561

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

Autorzy: Massimiliano Di Penta, Gabriele Bavota, Fiorella Zampetti
Opublikowane w: Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020, Strona(/y) 556-567, ISBN 9781450370431
Wydawca: ACM
DOI: 10.1145/3368089.3409695

Using reinforcement learning for load testing of video games

Autorzy: Rosalia Tufano, Simone Scalabrino, Luca Pascarella, Emad Aghajani, Rocco Oliveto, Gabriele Bavota
Opublikowane w: 2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE), 2022, Strona(/y) 2303–2314
Wydawca: ACM
DOI: 10.1145/3510003.3510625

An Empirical Study on Code Comment Completion

Autorzy: Antonio Mastropaolo, Emad Aghajani, Luca Pascarella, Gabriele Bavota
Opublikowane w: 2021 IEEE International Conference on Software Maintenance and Evolution (ICSME), 2021, Strona(/y) 159-170, ISBN 978-1-6654-2882-8
Wydawca: IEEE
DOI: 10.1109/icsme52107.2021.00021

Sampling Projects in GitHub for MSR Studies

Autorzy: Ozren Dabic, Emad Aghajani, Gabriele Bavota
Opublikowane w: 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR), 2021, Strona(/y) 560-564, ISBN 978-1-7281-8710-5
Wydawca: IEEE
DOI: 10.1109/msr52588.2021.00074

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

Autorzy: Matteo Ciniselli, Alberto Martin-Lopez, Gabriele Bavota
Opublikowane w: Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension, 2024
Wydawca: ACM
DOI: 10.1145/3643916.3644411

Towards Automating Code Review Activities

Autorzy: Rosalia Tufano, Luca Pascarella, Michele Tufano, Denys Poshyvanyk, Gabriele Bavota
Opublikowane w: 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), 2021, Strona(/y) 163-174, ISBN 978-1-6654-0296-5
Wydawca: IEEE
DOI: 10.1109/icse43902.2021.00027

Toward Automatically Completing GitHub Workflows

Autorzy: Antonio Mastropaolo, Fiorella Zampetti, Gabriele Bavota, Massimiliano Di Penta
Opublikowane w: Proceedings of the IEEE/ACM 46th International Conference on Software Engineering, 2024
Wydawca: ACM
DOI: 10.1145/3597503.3623351

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

Autorzy: Rosalia Tufano, Luca Pascarella, Gabriele Bavota
Opublikowane w: 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), 2024
Wydawca: IEEE
DOI: 10.1109/icse48619.2023.00203

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

Autorzy: Antonio Mastropaolo, Simone Scalabrino, Nathan Cooper, David Nader Palacio, Denys Poshyvanyk, Rocco Oliveto, Gabriele Bavota
Opublikowane w: 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), 2021, Strona(/y) 336-347, ISBN 978-1-6654-0296-5
Wydawca: IEEE
DOI: 10.1109/icse43902.2021.00041

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

Autorzy: Matteo Ciniselli, Nathan Cooper, Luca Pascarella, Denys Poshyvanyk, Massimiliano Di Penta, Gabriele Bavota
Opublikowane w: 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR), 2021, Strona(/y) 108-119, ISBN 978-1-7281-8710-5
Wydawca: IEEE
DOI: 10.1109/msr52588.2021.00024

Evaluating SZZ Implementations Through a Developer-Informed Oracle

Autorzy: Giovanni Rosa, Luca Pascarella, Simone Scalabrino, Rosalia Tufano, Gabriele Bavota, Michele Lanza, Rocco Oliveto
Opublikowane w: 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), 2021, Strona(/y) 436-447, ISBN 978-1-6654-0296-5
Wydawca: IEEE
DOI: 10.1109/icse43902.2021.00049

Towards Summarizing Code Snippets Using Pre-Trained Transformers

Autorzy: Antonio Mastropaolo, Matteo Ciniselli, Luca Pascarella, Rosalia Tufano, Emad Aghajani, Gabriele Bavota
Opublikowane w: Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension, 2024
Wydawca: ACM
DOI: 10.1145/3643916.3644400

Artykuły recenzowane (7)

Automated variable renaming: are we there yet?

Autorzy: Antonio Mastropaolo, Emad Aghajani, Luca Pascarella, Gabriele Bavota
Opublikowane w: Empirical Software Engineering, Numer 28, 2023, ISSN 1382-3256
Wydawca: Kluwer Academic Publishers
DOI: 10.1007/s10664-022-10274-8

Why Developers Refactor Source Code

Autorzy: Jevgenija Pantiuchina, Fiorella Zampetti, Simone Scalabrino, Valentina Piantadosi, Rocco Oliveto, Gabriele Bavota, Massimiliano Di Penta
Opublikowane w: ACM Transactions on Software Engineering and Methodology, Numer 29/4, 2020, Strona(/y) 1-30, ISSN 1049-331X
Wydawca: Association for Computing Machinary, Inc.
DOI: 10.1145/3408302

Using Transfer Learning for Code-Related Tasks

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

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

Autorzy: Rosalia Tufano, Ozren Dabić, Antonio Mastropaolo, Matteo Ciniselli, Gabriele Bavota
Opublikowane w: IEEE Transactions on Software Engineering, Numer 50, 2024, Strona(/y) 338-353, ISSN 0098-5589
Wydawca: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tse.2023.3348172

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

Autorzy: Giovanni Rosa, Luca Pascarella, Simone Scalabrino, Rosalia Tufano, Gabriele Bavota, Michele Lanza, Rocco Oliveto
Opublikowane w: Journal of Systems and Software, Numer 202, 2024, Strona(/y) 111729, ISSN 0164-1212
Wydawca: Elsevier BV
DOI: 10.1016/j.jss.2023.111729

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

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

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

Autorzy: Antonio Mastropaolo, Valentina Ferrari, Luca Pascarella, Gabriele Bavota
Opublikowane w: Journal of Systems and Software, Numer 210, 2024, Strona(/y) 111947, ISSN 0164-1212
Wydawca: Elsevier BV
DOI: 10.1016/j.jss.2023.111947