Software Engineering (cs.SE)

Abstract: Property-based testing (PBT), while an established technique in the software testing research community, is still relatively underused in real-world software. Pain points in writing property-based tests include implementing diverse random input generators and thinking of meaningful properties to test. Developers, however, are more amenable to writing documentation; plenty of library API documentation is available and can be used as natural language specifications for property-based tests. As large language models (LLMs) have recently shown promise in a variety of coding tasks, we explore the potential of using LLMs to synthesize property-based tests. We call our approach PBT-GPT, and propose three different strategies of prompting the LLM for PBT. We characterize various failure modes of PBT-GPT and detail an evaluation methodology for automatically synthesized property-based tests. PBT-GPT achieves promising results in our preliminary studies on sample Python library APIs in $\texttt{numpy}$, $\texttt{networkx}$, and $\texttt{datetime}$.

Abstract: Explainability, i.e. the ability of a system to explain its behavior to users, has become an important quality of software-intensive systems. Recent work has focused on methods for generating explanations for various algorithmic paradigms (e.g., machine learning, self-adaptive systems). There is relatively little work on what situations and types of behavior should be explained. There is also a lack of support for eliciting explainability requirements. In this work, we explore the need for explanation expressed by users in app reviews. We manually coded a set of 1,730 app reviews from 8 apps and derived a taxonomy of Explanation Needs. We also explore several approaches to automatically identify Explanation Needs in app reviews. Our best classifier identifies Explanation Needs in 486 unseen reviews of 4 different apps with a weighted F-score of 86%. Our work contributes to a better understanding of users' Explanation Needs. Automated tools can help engineers focus on these needs and ultimately elicit valid Explanation Needs.

Abstract: Last-mile delivery of goods has gained a lot of attraction during the COVID-19 pandemic. However, current package delivery processes often lead to parking in the second lane, which in turn has negative effects on the urban environment in which the deliveries take place, i.e., traffic congestion and safety issues for other road users. To tackle these challenges, an effective autonomous delivery system is required that guarantees efficient, flexible and safe delivery of goods. The project LogiSmile, co-funded by EIT Urban Mobility, pilots an autonomous delivery vehicle dubbed the Autonomous Hub Vehicle (AHV) that works in cooperation with a small autonomous robot called the Autonomous Delivery Device (ADD). With the two cooperating robots, the project LogiSmile aims to find a possible solution to the challenges of urban goods distribution in congested areas and to demonstrate the future of urban mobility. As a member of Nieders\"achsische Forschungszentrum f\"ur Fahrzeugtechnik (NFF), the Institute for Software and Systems Engineering (ISSE) developed an integrated software safety architecture for runtime monitoring of the AHV, with (1) a dependability cage (DC) used for the on-board monitoring of the AHV, and (2) a remote command control center (CCC) which enables the remote off-board supervision of a fleet of AHVs. The DC supervises the vehicle continuously and in case of any safety violation, it switches the nominal driving mode to degraded driving mode or fail-safe mode. Additionally, the CCC also manages the communication of the AHV with the ADD and provides fail-operational solutions for the AHV when it cannot handle complex situations autonomously. The runtime monitoring concept developed for the AHV has been demonstrated in 2022 in Hamburg. We report on the obtained results and on the lessons learned.

Abstract: An Operating System (OS) combines multiple interdependent software packages, which usually have their own independently developed architectures. When a multitude of independent packages are placed together in an OS, an implicit inter-package architecture is formed. For an evolutionary effort, designers/developers of OS can greatly benefit from fully understanding the system-wide dependency focused on individual files, specifically executable files, and dynamically loadable libraries. We propose a framework, DepEx, aimed at discovering the detailed package relations at the level of individual binary files and their associated evolutionary changes. We demonstrate the utility of DepEx by systematically investigating the evolution of a large-scale Open Source OS, Ubuntu. DepEx enabled us to systematically acquire and analyze the dependencies in different versions of Ubuntu released between 2005 (5.04) to 2023 (23.04). Our analysis revealed various evolutionary trends in package management and their implications based on the analysis of the 84 consecutive versions available for download (these include beta versions). This study has enabled us to assert that DepEx can provide researchers and practitioners with a better understanding of the implicit software dependencies in order to improve the stability, performance, and functionality of their software as well as to reduce the risk of issues arising during maintenance, updating, or migration.

Abstract: The ease of using a Large Language Model (LLM) to answer a wide variety of queries and their high availability has resulted in LLMs getting integrated into various applications. LLM-based recommenders are now routinely used by students as well as professional software programmers for code generation and testing. Though LLM-based technology has proven useful, its unethical and unattributed use by students and professionals is a growing cause of concern. As such, there is a need for tools and technologies which may assist teachers and other evaluators in identifying whether any portion of a source code is LLM generated. In this paper, we propose a neural network-based tool that instructors can use to determine the original effort (and LLM's contribution) put by students in writing source codes. Our tool is motivated by minimum description length measures like Kolmogorov complexity. Our initial experiments with moderate sized (up to 500 lines of code) have shown promising results that we report in this paper.

Abstract: Methods: This work introduces a method supporting the collaborative definition of machine learning tasks by leveraging model-based engineering in the formalization of the systems modeling language SysML. The method supports the identification and integration of various data sources, the required definition of semantic connections between data attributes, and the definition of data processing steps within the machine learning support. Results: By consolidating the knowledge of domain and machine learning experts, a powerful tool to describe machine learning tasks by formalizing knowledge using the systems modeling language SysML is introduced. The method is evaluated based on two use cases, i.e., a smart weather system that allows to predict weather forecasts based on sensor data, and a waste prevention case for 3D printer filament that cancels the printing if the intended result cannot be achieved (image processing). Further, a user study is conducted to gather insights of potential users regarding perceived workload and usability of the elaborated method. Conclusion: Integrating machine learning-specific properties in systems engineering techniques allows non-data scientists to understand formalized knowledge and define specific aspects of a machine learning problem, document knowledge on the data, and to further support data scientists to use the formalized knowledge as input for an implementation using (semi-) automatic code generation. In this respect, this work contributes by consolidating knowledge from various domains and therefore, fosters the integration of machine learning in industry by involving several stakeholders.

Abstract: Objective: This study aims to investigate the existing body of knowledge in the field of Model-Driven Engineering MDE in support of AI (MDE4AI) to sharpen future research further and define the current state of the art. Method: We conducted a Systemic Literature Review (SLR), collecting papers from five major databases resulting in 703 candidate studies, eventually retaining 15 primary studies. Each primary study will be evaluated and discussed with respect to the adoption of (1) MDE principles and practices and (2) the phases of AI development support aligned with the stages of the CRISP-DM methodology. Results: The study's findings show that the pillar concepts of MDE (metamodel, concrete syntax and model transformation), are leveraged to define domain-specific languages (DSL) explicitly addressing AI concerns. Different MDE technologies are used, leveraging different language workbenches. The most prominent AI-related concerns are training and modeling of the AI algorithm, while minor emphasis is given to the time-consuming preparation of the data sets. Early project phases that support interdisciplinary communication of requirements, such as the CRISP-DM \textit{Business Understanding} phase, are rarely reflected. Conclusion: The study found that the use of MDE for AI is still in its early stages, and there is no single tool or method that is widely used. Additionally, current approaches tend to focus on specific stages of development rather than providing support for the entire development process. As a result, the study suggests several research directions to further improve the use of MDE for AI and to guide future research in this area.

Abstract: Learning effective representations of source code is critical for any Machine Learning for Software Engineering (ML4SE) system. Inspired by natural language processing, large language models (LLMs) like Codex and CodeGen treat code as generic sequences of text and are trained on huge corpora of code data, achieving state of the art performance on several software engineering (SE) tasks. However, valid source code, unlike natural language, follows a strict structure and pattern governed by the underlying grammar of the programming language. Current LLMs do not exploit this property of the source code as they treat code like a sequence of tokens and overlook key structural and semantic properties of code that can be extracted from code-views like the Control Flow Graph (CFG), Data Flow Graph (DFG), Abstract Syntax Tree (AST), etc. Unfortunately, the process of generating and integrating code-views for every programming language is cumbersome and time consuming. To overcome this barrier, we propose our tool COMEX - a framework that allows researchers and developers to create and combine multiple code-views which can be used by machine learning (ML) models for various SE tasks. Some salient features of our tool are: (i) it works directly on source code (which need not be compilable), (ii) it currently supports Java and C#, (iii) it can analyze both method-level snippets and program-level snippets by using both intra-procedural and inter-procedural analysis, and (iv) it is easily extendable to other languages as it is built on tree-sitter - a widely used incremental parser that supports over 40 languages. We believe this easy-to-use code-view generation and customization tool will give impetus to research in source code representation learning methods and ML4SE. Tool: https://pypi.org/project/comex - GitHub: https://github.com/IBM/tree-sitter-codeviews - Demo: https://youtu.be/GER6U87FVbU