Empirical software engineering research often depends on datasets of code repository artifacts, where sampling strategies are employed to enable large-scale analyses. The design and evaluation of these strategies are critical, as they directly influence the generalizability of research findings. However, sampling remains an underestimated aspect in software engineering research: we identify two main challenges related to (1) the design and representativeness of sampling approaches, and (2) the ability to reason about the implications of sampling decisions on generalizability. To address these challenges, we propose a Domain-Specific Language (DSL) to explicitly describe complex sampling strategies through composable sampling operators. This formalism supports both the specification and the reasoning about the generalizability of results based on the applied sampling strategies. We implement the DSL as a Python-based fluent API, and demonstrate how it facilitates representativeness reasoning using statistical indicators extracted from sampling workflows. We validate our approach through a case study of MSR papers involving code repository sampling. Our results show that the DSL can model the sampling strategies reported in recent literature.

International audience

Coding practices are increasingly used by software companies. Their use promotes consistency, readability, and maintainability, which contribute to software quality. Coding practices were initially enforced by general-purpose linters, but companies now tend to design and adopt their own company-specific practices. However, these company-specific practices are often not automated, making it challenging to ensure they are shared and used by developers. Converting these practices into linter rules is a complex task that requires extensive static analysis and language engineering expertise.In this paper, we seek to answer the following question: can coding practices be learned automatically from examples manually tagged by developers? We conduct a feasibility study using CodeBERT, a state-of-the-art machine learning approach, to learn linter rules. Our results show that, although the resulting classifiers reach high precision and recall scores when evaluated on balanced synthetic datasets, their application on real-world, unbalanced codebases, while maintaining excellent recall, suffers from a severe drop in precision that hinders their usability.

International audience

Digital twins, along with Internet of Things and Artificial Intelligence, have been identified as one of the key technologies for Industry 4.0. However, the definition of Digital Twin (DT) is still abstract and context-dependent. In this paper, we present a metamodel that supports concrete and operational descriptions of digital twin deployment. This metamodel encompasses the different aspects of deployment, including the definition of hardware and software components that compose the layered cyber-physical architectures of the digital twin, along with the installation and instantiation tasks that compose deployment processes. Multiple configurations can also be defined to support the deployment of a digital twin in different execution contexts. The relevance of this metamodel was evaluated by two case studies. The first consists in deploying the digital twin of a cobot in a simulation environment. The second applies the approach in a home automation environment. In both cases, our metamodel provides complete and precise descriptions of the deployment process and thus constitutes a viable first step towards a model-driven approach for digital twin deployment.

International audience

Nowadays, development teams often rely on tools such as Jira or Bugzilla to manage backlogs of issues to be solved to develop or maintain software. Although they relate to many different concerns (e.g., bug fixing, new feature development, architecture refactoring), few means are proposed to identify and classify these different kinds of issues, except for non mandatory labels that can be manually associated to them. This may lead to a lack of issue classification or to issue misclassification that may impact automatic issue management (planning, assignment) or issue-derived metrics. Automatic issue classification thus is a relevant topic for assisting backlog management. This paper proposes a binary classification solution for discriminating bug from non bug issues. This solution combines natural language processing (TF-IDF) and classification (multi-layer perceptron) techniques, selected after comparing commonly used solutions to classify issues. Moreover, hyper-parameters of the neural network are optimized using a genetic algorithm. The obtained results, as compared to existing works on a commonly used benchmark, show significant improvements on the F1 measure for all datasets.

Software architecture modeling plays a key role in software development and, beyond, in software quality.The Spring framework is widely used in industry to deploy software.This paper evaluates whether Spring fosters good practices for architecture definition.It describes the results of an empirical study, based on a corpus of open-source Spring projects.Analysis shows that a strong (70%) majority of projects mixes all Spring architecture definition features.This can be considered as a pragmatic use of a very flexible tool.However, few good practice documentation and tool assistance exist to prevent hazardous architecture constructions.The paper highlights these situations and concludes on recommendations to assist developers.