{"id":13,"date":"2024-06-16T15:11:45","date_gmt":"2024-06-16T15:11:45","guid":{"rendered":"https:\/\/collab.di.uniba.it\/qualaiproject\/?page_id=13"},"modified":"2026-03-27T10:01:48","modified_gmt":"2026-03-27T10:01:48","slug":"publications","status":"publish","type":"page","link":"https:\/\/collab.di.uniba.it\/qualaiproject\/publications\/","title":{"rendered":"Publications"},"content":{"rendered":"<p><strong>2026<\/strong><\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">G. Colavito, F. Lanubile, N. Novielli, C. Arreza, Y. Shi. &#8220;<a href=\"https:\/\/collab.di.uniba.it\/nicole\/wp-content\/uploads\/sites\/6\/2026\/03\/Issue-Classification-with-LLMs-NASA.pdf\">Issue classification with LLMs: An empirical study of the NASA flight software systems<\/a>&#8220;. Journal of Systems and Software, Vol. 237, July 2026, https:\/\/doi.org\/10.1016\/j.jss.2026.112851\u00a0<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Vitale, A., Guglielmi, E., Scalabrino, S., Oliveto, R. (2026). <a href=\"https:\/\/arxiv.org\/abs\/2601.23059\">On the Impact of Code Comments for Automated Bug-Fixing: An Empirical Study<\/a>. In <\/span><i><span style=\"font-weight: 400;\">Proceedings of the International Conference on Program Comprehension (<\/span><\/i><span style=\"font-weight: 400;\">to appear)<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">V. De Martino, S. Lambiase, F. Pecorelli, W.J. van den Heuvel, F. Ferrucci, F. Palomba, <a href=\"https:\/\/arxiv.org\/abs\/2511.00901\">\u201cSustainability of Machine Learning-Enabled Systems: The Machine Learning Practitioner\u2019s Perspective<\/a>\u201d, (2026), in press.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">G. Festa, G. Giordano, V. Pontillo, M. Di Penta, D. Tamburri, F. Palomba, <a href=\"https:\/\/www.researchgate.net\/publication\/394897922_Pythonic_vs_Refactorable_Pythonic_On_the_Relationship_between_Pythonic_Idioms_and_Code_Quality_in_Machine_Learning_Projects\">\u201cPythonic vs Refactorable Pythocnic: On the Relationship between Pythonic Idioms and Code Quality in Machine Learning Projects\u201d<\/a>, (2026) in press<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><strong>2025<\/strong><\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">D. Grassi, F. Lanubile, N. Novielli, L. Quaranta, A. Serebrenik <a href=\"https:\/\/research.tue.nl\/en\/publications\/self-monitoring-of-developers-emotions-the-case-of-agile-retrospe\/\">\u201cSelf-monitoring of Developers\u2019 Emotions: the Case of Agile Retrospective Meetings\u201c<\/a>. ACM Transactions on Software Engineering and Methodology (Accepted: Sept. 2025), https:\/\/doi.org\/10.1145\/3766064<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">G. Colavito, F. Lanubile, N. Novielli. \u201c<a href=\"https:\/\/collab.di.uniba.it\/nicole\/wp-content\/uploads\/sites\/6\/2025\/05\/Extended_Benchmark_LLM_4_Issue_Report_Classification__IST_Accepted.pdf\">Benchmarking large language models for automated labeling: The case of issue report classification<\/a>\u201c. Information and Software Technology, 184 (2025). <\/span><a href=\"https:\/\/doi.org\/10.1007\/s10664-024-10611-z\"><span style=\"font-weight: 400;\">https:\/\/doi.org\/10.1007\/s10664-024-10611-z<\/span><\/a><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Daniela Grassi, Filippo Lanubile, Alberta Mocta-Schnabel, Nicole Novielli. <a href=\"https:\/\/hdl.handle.net\/11586\/530740\">\u201cA Cluster-based Approach for Emotion Recognition in Software Development<\/a>\u201c. In Proceedings of the 18th International Conference on Cooperative and Human Aspects of Software Engineering (CHASE 2025), doi: 10.1109\/CHASE66643.2025.00034.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Vitale, A., Oliveto, R., &amp; Scalabrino, S. (2025). <a href=\"https:\/\/iris.polito.it\/handle\/11583\/2999907\">A catalog of data smells for coding tasks<\/a>. <\/span><i><span style=\"font-weight: 400;\">ACM Transactions on Software Engineering and Methodology<\/span><\/i><span style=\"font-weight: 400;\">, <\/span><i><span style=\"font-weight: 400;\">34<\/span><\/i><span style=\"font-weight: 400;\">(4), 1-32.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Spina, A., Russodivito, M., Scalabrino, S., &amp; Oliveto, R. (2025). <a href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S016412122500398X\">Peeking Inside the Black Box: Training Data Exposure in Code Language Models<\/a>. <\/span><i><span style=\"font-weight: 400;\">Journal of Systems and Software<\/span><\/i><span style=\"font-weight: 400;\">, 112729.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">A. Parziale, G. Voria, G. Giordano, G. Catolino, G. Robles, F. Palomba. <a href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0950584925001971\">&#8220;Fairness on a budget, across the board: A cost-effective evaluation of fairness-aware practices across contexts, tasks, and sensitive attributes.&#8221;<\/a> Information and Software Technology (2025): 107858.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">A. Parziale, G. Voria, G. Giordano, G. Catolino, G. Robles, F. Palomba. <a href=\"https:\/\/arxiv.org\/abs\/2503.15622\">&#8220;Contextual fairness-aware practices in ML: A cost-effective empirical evaluation.&#8221;<\/a> In 2025 IEEE International Conference on Software Analysis, Evolution and Reengineering-Companion (SANER-C), pp. 1-8. IEEE, 2025.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">G. Voria, B. Scala, L. Todisco, C. Venditto, G. Giordano, G. Catolino, F. Palomba.<a href=\"https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=5246323\"> &#8220;Fair and square? Evaluating fairness of LLM-generated synthetic datasets.&#8221;<\/a> Information and Software Technology (2025): 107980.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">G. Recupito, G. Giordano, F. Ferrucci, D. Di Nucci, F. Palomba, <a href=\"https:\/\/arxiv.org\/abs\/2403.08311\">\u201cWhen Code Smells Meet ML: On the Lifecycle of ML-specific Code Smells in ML-enabled Systems\u201d<\/a>, (2025) Vol. 30, article number 139.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">V. De Martino, G. Recupito, G. Giordano, F. Ferrucci, D. Di Nucci, F. Palomba, <a href=\"https:\/\/hdl.handle.net\/11386\/4913997\">\u201cInto the ML-Universe: An Improved Classification and Characterization of Machine-Learning Projects\u201d<\/a>, (<\/span><span style=\"font-weight: 400;\">2025<\/span><span style=\"font-weight: 400;\">) Vol. 230,<\/span><span style=\"font-weight: 400;\"> 112471.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">S. Lambiase, G. Catolino, F. Palomba, F. Ferrucci, D. Russo, \u201c<\/span><span style=\"font-weight: 400;\">Investigating the Role of Cultural Values in Adopting Large Language Models for Software Engineering\u201d, <\/span><i><span style=\"font-weight: 400;\">ACM Transactions on Software Engineering and Methodology<\/span><\/i><span style=\"font-weight: 400;\">, <\/span><i><span style=\"font-weight: 400;\">35<\/span><\/i><span style=\"font-weight: 400;\">(1), 1-43.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">V. De Martino, F. Palomba, \u201c<a href=\"https:\/\/fpalomba.github.io\/pdf\/Journals\/J73.pdf\">Classification and Challenges of Non-Functional Requirements in ML-Enabled Systems: A Systematic Literature Review<\/a>, <\/span><i><span style=\"font-weight: 400;\">Information and Software Technology<\/span><\/i><span style=\"font-weight: 400;\">, <\/span><i><span style=\"font-weight: 400;\">181<\/span><\/i><span style=\"font-weight: 400;\">, 107678.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">G. Annunziata, S. Lambiase, D. Tamburri,, W.J. Van Den Heuvel, F. Palomba,G. Catolino, F. Ferrucci, A. De Lucia (2025). <a href=\"https:\/\/www.researchgate.net\/publication\/388114635_Uncovering_Community_Smells_in_Machine_Learning-Enabled_Systems_Causes_Effects_and_Mitigation_Strategies\">Uncovering community smells in machine learning-enabled systems: Causes, effects, and mitigation strategie<\/a>s. <\/span><i><span style=\"font-weight: 400;\">ACM Transactions on Software Engineering and Methodology<\/span><\/i><span style=\"font-weight: 400;\">, <\/span><i><span style=\"font-weight: 400;\">34<\/span><\/i><span style=\"font-weight: 400;\">(6), 1-48.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">A. Della Porta, S. Lambiase, F. Palomba (2025). <a href=\"https:\/\/arxiv.org\/abs\/2504.13656\">Do prompt patterns affect code quality? a first empirical assessment of chatgpt-generated code.<\/a> In <\/span><i><span style=\"font-weight: 400;\">Proceedings of the 29th International Conference on Evaluation and Assessment in Software Engineering<\/span><\/i><span style=\"font-weight: 400;\"> (pp. 181-192).<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">G. Annunziata, S. Lambiase, F. Palomba, G. Catolino, F. Ferrucci (2025). <a href=\"https:\/\/arxiv.org\/abs\/2504.17419\">How do communities of ML-enabled systems smell? a cross-sectional study on the prevalence of community smells.<\/a> In <\/span><i><span style=\"font-weight: 400;\">Proceedings of the 29th International Conference on Evaluation and Assessment in Software Engineering<\/span><\/i><span style=\"font-weight: 400;\"> (pp. 272-282).<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">V. De Martino, J. Castano, F. Palomba, X. Franch, S. Mart\u00ednez-Fern\u00e1ndez (2025). <a href=\"https:\/\/arxiv.org\/abs\/2411.09974\">A framework for using llms for repository mining studies in empirical software engineering<\/a>. In <\/span><i><span style=\"font-weight: 400;\">2025 IEEE\/ACM International Workshop on Methodological Issues with Empirical Studies in Software Engineering (WSESE)<\/span><\/i><span style=\"font-weight: 400;\">(pp. 6-11). IEEE.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">V. De Martino, S. Mart\u00ednez-Fern\u00e1ndez, F. Palomba (2025). <a href=\"https:\/\/arxiv.org\/abs\/2410.06708\">Do developers adopt green architectural tactics for ml-enabled systems? a mining software repository study<\/a>. In <\/span><i><span style=\"font-weight: 400;\">2025 IEEE\/ACM 47th International Conference on Software Engineering: Software Engineering in Society (ICSE-SEIS)<\/span><\/i><span style=\"font-weight: 400;\"> (pp. 135-139). IEEE.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">G. Recupito, G. Giordano, D. Di Nucci, F. Palomba, <a href=\"https:\/\/ceur-ws.org\/Vol-4109\/paper4.pdf\">\u201cDetecting Semantic Data Smells with BERT: A Transformer-Based Approach to Data Quality\u201d<\/a>, (2025), ECAI Workshop on MLOps, 2025.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">A. Della Porta, G. Recupito, S. Lambiase, D. Di Nucci, F. Palomba,<a href=\"https:\/\/hdl.handle.net\/11386\/4935735\"> \u201cUnlocking Code Simplicity: The Role of Prompt Patterns in Managing LLM Code Complexity\u201d<\/a>, 2025 IEEE International Conference on Software Analysis, Evolution and Reengineering \u2013 Companion (SANER-C), (2025).<\/span><\/li>\n<li aria-level=\"1\"><span style=\"font-weight: 400;\">G. Recupito, V. De Martino, D. Di Nucci, F. Palomba, <a href=\"https:\/\/arxiv.org\/abs\/2510.03802\">\u201cA First Look at the Lifecycle of DL-Specific Self-Admitted Technical Debt\u201d<\/a>, 2025 IEEE International Conference on Software Analysis, Evolution and Reengineering \u2013 Companion (SANER-C), (2025) pp. 150\u2013157.<\/span><\/li>\n<li aria-level=\"1\"><span style=\"font-weight: 400;\">Daniela Grassi, Fabio Calefato, Darja Smite, Nicole Novielli, Filippo Lanubile. <a href=\"https:\/\/collab.di.uniba.it\/nicole\/wp-content\/uploads\/sites\/6\/2025\/08\/ESEM___Exploring_Engagement_and_Emotions_in_Hybrid_Meetings.pdf\">\u201cExploring Engagement in Hybrid Meetings\u201c<\/a>. In Proceedings of the 19th ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM 2025), <strong>\u00a0<\/strong><a href=\"https:\/\/doi.org\/10.1109\/ESEM64174.2025.00032\" target=\"_blank\" rel=\"noopener\">10.1109\/ESEM64174.2025.00032<\/a><\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><strong>2024<\/strong><\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Russodivito, M., Spina, A., Scalabrino, S., &amp; Oliveto, R. (2024). <a href=\"https:\/\/hdl.handle.net\/11695\/150233\">Black-Box Reconstruction Attacks on LLMs: A Preliminary Study in Code Summarization.<\/a> In <i>Proceedings of the International Conference on the Quality of Information and Communications Technology<\/i> (pp. 391-398). Cham: Springer Nature Switzerland.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Rosa, G., Scalabrino, S., Robles, G., &amp; Oliveto, R. (2024). <a href=\"https:\/\/sscalabrino.github.io\/files\/2024\/MSR2024NotAllDockerfile.pdf\">Not all dockerfile smells are the same: An empirical evaluation of hadolint writing practices by experts<\/a>. In <\/span><i><span style=\"font-weight: 400;\">Proceedings of the 21st International Conference on Mining Software Repositories<\/span><\/i><span style=\"font-weight: 400;\"> (pp. 231-241).<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Rosa, G., Zappone, F., Scalabrino, S., &amp; Oliveto, R. (2024).<a href=\"https:\/\/arxiv.org\/abs\/2208.09097\"> Fixing Dockerfile smells: an empirical study<\/a>. <i>Empirical Software Engineering<\/i>, <i>29<\/i>(5), 108.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Vitale, A., Mastropaolo, A., Oliveto, R., Di Penta, M., &amp; Scalabrino, S. (2025). <a href=\"https:\/\/arxiv.org\/abs\/2502.07611\">Optimizing datasets for code summarization: Is code-comment coherence enough?<\/a>. In <\/span><i><span style=\"font-weight: 400;\">Proceedings of the International Conference on Program Comprehension <\/span><\/i><span style=\"font-weight: 400;\">(pp. 237-249).<\/span><\/li>\n<li>Nicole Novielli, Rocco Oliveto, Fabio Palomba, Fabio Calefato, Giuseppe Colavito, Vincenzo De Martino, Antonio Della Porta, Giammaria Giordano, Emanuela Guglielmi, Filippo Lanubile, Luigi Quaranta, Gilberto Recupito, Simone Scalabrino, Angelica Spina and Antonio Vitale, &#8220;<a href=\"https:\/\/ceur-ws.org\/Vol-3674\/RP-paper3.pdf\">QualAI: Continuous Quality Improvement of AI-based Systems<\/a>&#8220;, in\u00a0<em>Proceedings of\u00a018th International Conference on Research Challenges in Information Science (RCIS 2024), Research Project Track<\/em><\/li>\n<li>Giuseppe Colavito, Filippo Lanubile, Nicole Novielli, Luigi Quaranta, &#8220;<a href=\"https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S0164121223002339\">Impact of Data Quality for Automatic Issue Classification Using Pre-trained Language Models<\/a>&#8220;, <em> Journal of Systems and Software<\/em>, 2024, DOI: 10.1016\/j.jss.2023.111838<\/li>\n<li>Giuseppe Colavito, Filippo Lanubile, Nicole Novielli, Luigi Quaranta. &#8220;<a href=\"https:\/\/collab.di.uniba.it\/nicole\/wp-content\/uploads\/sites\/6\/2024\/01\/ColavitoEtAl_GPT_and_issue_labeling__MSR_2024.pdf\">Leveraging GPT-like LLMs to Automate Issue Labeling<\/a>&#8220;. In\u00a0<em>Proceedings of the 21st International Conference on Mining Software Repositories (MSR 2024)<\/em>, to appear<\/li>\n<li>Carmine Ferrara, Francesco Casillo, Carmine Gravino, Andrea De Lucia, Fabio Palomba, &#8220;<a href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639185\">ReFAIR: Toward a Context-Aware Recommender for Fairness Requirements Engineering<\/a>&#8220;.\u00a0 In <em>Proceedings of the 2024 IEEE\/ACM 46th International Conference on Software Engineering<\/em> (ICSE \u201924), April 14\u201320, 2024, Lisbon, Portugal. ACM, New York, NY, USA, 13 pages. https:\/\/doi.org\/ 10.1145\/3597503.3639185<\/li>\n<li>Gilberto Recupito, Raimondo Rapacciuolo, Dario Di Nucci, Fabio Palomba, &#8220;<a href=\"https:\/\/fpalomba.github.io\/pdf\/Conferencs\/C82.pdf\">Unmasking Data Secrets: An Empirical Investigation into Data Smells and Their Impact on Data Quality<\/a>&#8220;. In\u00a0<em>Proceedings of 3rd International Conference on AI Engineering <\/em> (CAIN 2024), to appear<\/li>\n<li><span style=\"font-weight: 400;\">G. Recupito, F. Pecorelli, G. Catolino, V. Lenarduzzi, D. Taibi, D. Di Nucci, F. Palomba\u00a0 (2024). <a href=\"https:\/\/www.unipegaso.iris.cineca.it\/handle\/20.500.12607\/27782\">Technical debt in ai-enabled systems: On the prevalence, severity, impact, and management strategies for code and architecture. <\/a><\/span><i><span style=\"font-weight: 400;\">Journal of Systems and Software<\/span><\/i><span style=\"font-weight: 400;\">, <\/span><i><span style=\"font-weight: 400;\">216<\/span><\/i><span style=\"font-weight: 400;\">, 112151.<\/span><\/li>\n<li><span style=\"font-weight: 400;\">G. Recupito, R. Rapacciuolo, D. Di Nucci, F. Palomba (2024). <a href=\"https:\/\/fpalomba.github.io\/pdf\/Conferencs\/C82.pdf\">Unmasking data secrets: An empirical investigation into data smells and their impact on data quality.<\/a> In <\/span><i><span style=\"font-weight: 400;\">Proceedings of the IEEE\/ACM 3rd International Conference on AI Engineering-Software Engineering for AI<\/span><\/i><span style=\"font-weight: 400;\"> (pp. 53-63).<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">A. Della Porta, V. De Martino, G. Recupito, C. Iemmino, G. Catolino, D. Di Nucci, F. Palomba, <a href=\"https:\/\/ceur-ws.org\/Vol-3762\/523.pdf\">\u201cUsing Large Language Models to Support Software Engineering Documentation in Waterfall Life Cycles: Are We There Yet?\u201d<\/a>, Ital-IA, (2024) pp. 42\u201347.<\/span><\/li>\n<\/ul>\n<p><strong>2023<\/strong><\/p>\n<ul>\n<li>Gianmaria Giordano, Giusy Annunziata, Andrea De Lucia and Fabio Palomba, &#8220;<a href=\"https:\/\/ceur-ws.org\/Vol-3543\/paper18.pdf\">Understanding Developer Practices and Code Smells Diffusion in AI-Enabled Software: A Preliminary Study<\/a>&#8220;. IWSM\/MENSURA 23, September 14\u201315, 2023, Rome, Italy<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>2026 G. Colavito, F. Lanubile, N. Novielli, C. Arreza, Y. Shi. &#8220;Issue classification with LLMs: An empirical study of the NASA flight software systems&#8220;. Journal of Systems and Software, Vol. 237, July 2026, https:\/\/doi.org\/10.1016\/j.jss.2026.112851\u00a0 Vitale, A., Guglielmi, E., Scalabrino, S.,<\/p>\n","protected":false},"author":5,"featured_media":0,"parent":0,"menu_order":3,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-13","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.3 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Publications - QualAI - Continuous Quality Improvement of AI-based Systems<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/collab.di.uniba.it\/qualaiproject\/publications\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Publications - QualAI - Continuous Quality Improvement of AI-based Systems\" \/>\n<meta property=\"og:description\" content=\"2026 G. Colavito, F. Lanubile, N. Novielli, C. Arreza, Y. Shi. &#8220;Issue classification with LLMs: An empirical study of the NASA flight software systems&#8220;. Journal of Systems and Software, Vol. 237, July 2026, https:\/\/doi.org\/10.1016\/j.jss.2026.112851\u00a0 Vitale, A., Guglielmi, E., Scalabrino, S.,\" \/>\n<meta property=\"og:url\" content=\"https:\/\/collab.di.uniba.it\/qualaiproject\/publications\/\" \/>\n<meta property=\"og:site_name\" content=\"QualAI - Continuous Quality Improvement of AI-based Systems\" \/>\n<meta property=\"article:modified_time\" content=\"2026-03-27T10:01:48+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/collab.di.uniba.it\\\/qualaiproject\\\/publications\\\/\",\"url\":\"https:\\\/\\\/collab.di.uniba.it\\\/qualaiproject\\\/publications\\\/\",\"name\":\"Publications - QualAI - Continuous Quality Improvement of AI-based Systems\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/collab.di.uniba.it\\\/qualaiproject\\\/#website\"},\"datePublished\":\"2024-06-16T15:11:45+00:00\",\"dateModified\":\"2026-03-27T10:01:48+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/collab.di.uniba.it\\\/qualaiproject\\\/publications\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/collab.di.uniba.it\\\/qualaiproject\\\/publications\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/collab.di.uniba.it\\\/qualaiproject\\\/publications\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/collab.di.uniba.it\\\/qualaiproject\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Publications\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/collab.di.uniba.it\\\/qualaiproject\\\/#website\",\"url\":\"https:\\\/\\\/collab.di.uniba.it\\\/qualaiproject\\\/\",\"name\":\"QualAI - Continuous Quality Improvement of AI-based Systems\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/collab.di.uniba.it\\\/qualaiproject\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Publications - QualAI - Continuous Quality Improvement of AI-based Systems","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/collab.di.uniba.it\/qualaiproject\/publications\/","og_locale":"en_US","og_type":"article","og_title":"Publications - QualAI - Continuous Quality Improvement of AI-based Systems","og_description":"2026 G. Colavito, F. Lanubile, N. Novielli, C. Arreza, Y. Shi. &#8220;Issue classification with LLMs: An empirical study of the NASA flight software systems&#8220;. Journal of Systems and Software, Vol. 237, July 2026, https:\/\/doi.org\/10.1016\/j.jss.2026.112851\u00a0 Vitale, A., Guglielmi, E., Scalabrino, S.,","og_url":"https:\/\/collab.di.uniba.it\/qualaiproject\/publications\/","og_site_name":"QualAI - Continuous Quality Improvement of AI-based Systems","article_modified_time":"2026-03-27T10:01:48+00:00","twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/collab.di.uniba.it\/qualaiproject\/publications\/","url":"https:\/\/collab.di.uniba.it\/qualaiproject\/publications\/","name":"Publications - QualAI - Continuous Quality Improvement of AI-based Systems","isPartOf":{"@id":"https:\/\/collab.di.uniba.it\/qualaiproject\/#website"},"datePublished":"2024-06-16T15:11:45+00:00","dateModified":"2026-03-27T10:01:48+00:00","breadcrumb":{"@id":"https:\/\/collab.di.uniba.it\/qualaiproject\/publications\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/collab.di.uniba.it\/qualaiproject\/publications\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/collab.di.uniba.it\/qualaiproject\/publications\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/collab.di.uniba.it\/qualaiproject\/"},{"@type":"ListItem","position":2,"name":"Publications"}]},{"@type":"WebSite","@id":"https:\/\/collab.di.uniba.it\/qualaiproject\/#website","url":"https:\/\/collab.di.uniba.it\/qualaiproject\/","name":"QualAI - Continuous Quality Improvement of AI-based Systems","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/collab.di.uniba.it\/qualaiproject\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/collab.di.uniba.it\/qualaiproject\/wp-json\/wp\/v2\/pages\/13","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/collab.di.uniba.it\/qualaiproject\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/collab.di.uniba.it\/qualaiproject\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/collab.di.uniba.it\/qualaiproject\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/collab.di.uniba.it\/qualaiproject\/wp-json\/wp\/v2\/comments?post=13"}],"version-history":[{"count":29,"href":"https:\/\/collab.di.uniba.it\/qualaiproject\/wp-json\/wp\/v2\/pages\/13\/revisions"}],"predecessor-version":[{"id":74,"href":"https:\/\/collab.di.uniba.it\/qualaiproject\/wp-json\/wp\/v2\/pages\/13\/revisions\/74"}],"wp:attachment":[{"href":"https:\/\/collab.di.uniba.it\/qualaiproject\/wp-json\/wp\/v2\/media?parent=13"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}