arXiv subjects

Oliviero Riganelli

Publications and source records attributed to Oliviero Riganelli.

At least 19 recordsLinked to original sources

arXiv2026

"Where is My Troubleshooting Procedure?": Studying the Potential of RAG in Assisting Failure Resolution of Large Cyber-Physical System

In today's complex industrial environments, operators must often navigate through extensive technical manuals to identify troubleshooting procedures that may help react to some observed failure symptoms. These manuals, written in natural language, describe many steps in detail. Unfortunately, the number, magnitude, and articulation of these descriptions can significantly slow down and complicate the retrieval of the correct procedure during critical incidents. Interestingly, Retrieval Augmented Generation (RAG) enables the development of tools based on conversational interfaces that can assist operators in their retrieval tasks, improving their capability to respond to incidents. This paper presents the results of a set of experiments that derive from the analysis of the troubleshooting procedures available in Fincantieri, a large international company developing complex naval cyber-physical systems. Results show that RAG can assist operators in reacting promptly to failure symptoms, although specific measures have to be taken into consideration to cross-validate recommendations before actuating them.

cs.SE↗

arXiv2026

Coverage-Guided Road Selection and Prioritization for Efficient Testing in Autonomous Driving Systems

Autonomous Driving Assistance Systems (ADAS) rely on extensive testing to ensure safety and reliability, yet road scenario datasets often contain redundant cases that slow down the testing process without improving fault detection. To address this issue, we present a novel test prioritization framework that reduces redundancy while preserving geometric and behavioral diversity. Road scenarios are clustered based on geometric and dynamic features of the ADAS driving behavior, from which representative cases are selected to guarantee coverage. Roads are finally prioritized based on geometric complexity, driving difficulty, and historical failures, ensuring that the most critical and challenging tests are executed first. We evaluate our framework on the OPENCAT dataset and the Udacity self-driving car simulator using two ADAS models. On average, our approach achieves an 89% reduction in test suite size while retaining an average of 79% of failed road scenarios. The prioritization strategy improves early failure detection by up to 95x compared to random baselines.

cs.SE↗

arXiv2025

From PREVENTion to REACTion: Enhancing Failure Resolution in Naval Systems

Complex and large industrial systems often misbehave, for instance, due to wear, misuse, or faults. To cope with these incidents, it is important to timely detect their occurrences, localize the sources of the problems, and implement the appropriate countermeasures. This paper reports our experience with a state-of-the-art failure prediction method, PREVENT, and its extension with a troubleshooting module, REACT, applied to naval systems developed by Fincantieri. Our results show how to integrate anomaly detection with troubleshooting procedures. We conclude by discussing a lesson learned, which may help deploy and extend these analyses to other industrial products.

cs.SE↗

arXiv2025

MultiMind: A Plug-in for the Implementation of Development Tasks Aided by AI Assistants

The integration of AI assistants into software development workflows is rapidly evolving, shifting from automation-assisted tasks to collaborative interactions between developers and AI. Large Language Models (LLMs) have demonstrated their effectiveness in several development activities, including code completion, test case generation, and documentation production. However, embedding AI-assisted tasks within Integrated Development Environments (IDEs) presents significant challenges. It requires designing mechanisms to invoke AI assistants at the appropriate time, coordinate interactions with multiple assistants, process the generated outputs, and present feedback in a way that seamlessly integrates with the development workflow. To address these issues, we introduce MultiMind, a Visual Studio Code plug-in that streamlines the creation of AI-assisted development tasks. MultiMind provides a modular and extensible framework, enabling developers to cost-effectively implement and experiment with new AI-powered interactions without the need for complex IDE customizations. MultiMind has been tested in two use cases: one for the automatic generation of code comments and the other about the definition of AI-powered chat.

cs.SE↗

arXiv2025

OpenCat: Improving Interoperability of ADS Testing

Testing Advanced Driving Assistance Systems (ADAS), such as lane-keeping functions, requires creating road topologies or using predefined benchmarks. However, the test cases in existing ADAS benchmarks are often designed in specific formats (e.g., OpenDRIVE) and tailored to specific ADAS models. This limits their reusability and interoperability with other simulators and models, making it challenging to assess ADAS functionalities independently of the platform-specific details used to create the test cases. This paper evaluates the interoperability of SensoDat, a benchmark developed for ADAS regression testing. We introduce OpenCat, a converter that transforms OpenDRIVE test cases into the Catmull-Rom spline format, which is widely supported by many current test generators. By applying OpenCat to the SensoDat dataset, we achieved high accuracy in converting test cases into reusable road scenarios. To validate the converted scenarios, we used them to evaluate a lane-keeping ADAS model using the Udacity simulator. Both the simulator and the ADAS model operate independently of the technologies underlying SensoDat, ensuring an unbiased evaluation of the original test cases. Our findings reveal that benchmarks built with specific ADAS models hinder their effective usage for regression testing. We conclude by offering insights and recommendations to enhance the reusability and transferability of ADAS benchmarks for more extensive applications.

cs.SE↗

arXiv2025

On the Possibility of Breaking Copyleft Licenses When Reusing Code Generated by ChatGPT

AI assistants can help developers by recommending code to be included in their implementations (e.g., suggesting the implementation of a method from its signature). Although useful, these recommendations may mirror copyleft code available in public repositories, exposing developers to the risk of reusing code that they are allowed to reuse only under certain constraints (e.g., a specific license for the derivative software). This paper presents a large-scale study about the frequency and magnitude of this phenomenon in ChatGPT. In particular, we generate more than 70,000 method implementations using a range of configurations and prompts, revealing that a larger context increases the likelihood of reproducing copyleft code, but higher temperature settings can mitigate this issue.

cs.SE↗

arXiv2025

Studying How Configurations Impact Code Generation in LLMs: the Case of ChatGPT

Leveraging LLMs for code generation is becoming increasingly common, as tools like ChatGPT can suggest method implementations with minimal input, such as a method signature and brief description. Empirical studies further highlight the effectiveness of LLMs in handling such tasks, demonstrating notable performance in code generation scenarios. However, LLMs are inherently non-deterministic, with their output influenced by parameters such as temperature, which regulates the model's level of creativity, and top-p, which controls the choice of the tokens that shall appear in the output. Despite their significance, the role of these parameters is often overlooked. This paper systematically studies the impact of these parameters, as well as the number of prompt repetitions required to account for non-determinism, in the context of 548 Java methods. We observe significantly different performances across different configurations of ChatGPT, with temperature having a marginal impact compared to the more prominent influence of the top-p parameter. Additionally, we show how creativity can enhance code generation tasks. Finally, we provide concrete recommendations for addressing the non-determinism of the model.

cs.SE↗

arXiv2024

Testing in the Evolving World of DL Systems:Insights from Python GitHub Projects

In the ever-evolving field of Deep Learning (DL), ensuring project quality and reliability remains a crucial challenge. This research investigates testing practices within DL projects in GitHub. It quantifies the adoption of testing methodologies, focusing on aspects like test automation, the types of tests (e.g., unit, integration, and system), test suite growth rate, and evolution of testing practices across different project versions. We analyze a subset of 300 carefully selected repositories based on quantitative and qualitative criteria. This study reports insights on the prevalence of testing practices in DL projects within the open-source community.

cs.SE↗

arXiv2024

ReProbe: An Architecture for Reconfigurable and Adaptive Probes

Modern distributed systems are highly dynamic and scalable, requiring monitoring solutions that can adapt to rapid changes. Monitoring systems that rely on external probes can only achieve adaptation through expensive operations such as deployment, undeployment, and reconfiguration. This poster paper introduces ReProbes, a class of adaptive monitoring probes that can handle rapid changes in data collection strategies. ReProbe offers controllable and configurable self-adaptive capabilities for data transmission, collection, and analysis methods. The resulting architecture can effectively enhance probe adaptability when qualitatively compared to state-of-the-art monitoring solutions.

cs.SE↗

arXiv2024

Assessing AI-Based Code Assistants in Method Generation Tasks

AI-based code assistants are increasingly popular as a means to enhance productivity and improve code quality. This study compares four AI-based code assistants, GitHub Copilot, Tabnine, ChatGPT, and Google Bard, in method generation tasks, assessing their ability to produce accurate, correct, and efficient code. Results show that code assistants are useful, with complementary capabilities, although they rarely generate ready-to-use correct code.

cs.SE↗

arXiv2024

Generating Java Methods: An Empirical Assessment of Four AI-Based Code Assistants

AI-based code assistants are promising tools that can facilitate and speed up code development. They exploit machine learning algorithms and natural language processing to interact with developers, suggesting code snippets (e.g., method implementations) that can be incorporated into projects. Recent studies empirically investigated the effectiveness of code assistants using simple exemplary problems (e.g., the re-implementation of well-known algorithms), which fail to capture the spectrum and nature of the tasks actually faced by developers. In this paper, we expand the knowledge in the area by comparatively assessing four popular AI-based code assistants, namely GitHub Copilot, Tabnine, ChatGPT, and Google Bard, with a dataset of 100 methods that we constructed from real-life open-source Java projects, considering a variety of cases for complexity and dependency from contextual elements. Results show that Copilot is often more accurate than other techniques, yet none of the assistants is completely subsumed by the rest of the approaches. Interestingly, the effectiveness of these solutions dramatically decreases when dealing with dependencies outside the boundaries of single classes.

cs.SE↗

arXiv2024

Analyzing Prompt Influence on Automated Method Generation: An Empirical Study with Copilot

Generative AI is changing the way developers interact with software systems, providing services that can produce and deliver new content, crafted to satisfy the actual needs of developers. For instance, developers can ask for new code directly from within their IDEs by writing natural language prompts, and integrated services based on generative AI, such as Copilot, immediately respond to prompts by providing ready-to-use code snippets. Formulating the prompt appropriately, and incorporating the useful information while avoiding any information overload, can be an important factor in obtaining the right piece of code. The task of designing good prompts is known as prompt engineering. In this paper, we systematically investigate the influence of eight prompt features on the style and the content of prompts, on the level of correctness, complexity, size, and similarity to the developers' code of the generated code. We specifically consider the task of using Copilot with 124,800 prompts obtained by systematically combining the eight considered prompt features to generate the implementation of 200 Java methods. Results show how some prompt features, such as the presence of examples and the summary of the purpose of the method, can significantly influence the quality of the result.

cs.SE↗

arXiv2023

Automated Probe Life-Cycle Management for Monitoring-as-a-Service

Cloud services must be continuously monitored to guarantee that misbehaviors can be timely revealed, compensated, and fixed. While simple applications can be easily monitored and controlled, monitoring non-trivial cloud systems with dynamic behavior requires the operators to be able to rapidly adapt the set of collected indicators. Although the currently available monitoring frameworks are equipped with a rich set of probes to virtually collect any indicator, they do not provide the automation capabilities required to quickly and easily change (i.e., deploy and undeploy) the probes used to monitor a target system. Indeed, changing the collected indicators beyond standard platform-level indicators can be an error-prone and expensive process, which often requires manual intervention. This paper presents a Monitoring-as-a-Service framework that provides the capability to automatically deploy and undeploy arbitrary probes based on a user-provided set of indicators to be collected. The life-cycle of the probes is fully governed by the framework, including the detection and resolution of the erroneous states at deployment time. The framework can be used jointly with existing monitoring technologies, without requiring the adoption of a specific probing technology. We experimented our framework with cloud systems based on containers and virtual machines, obtaining evidence of the efficiency and effectiveness of the proposed solution.

cs.DC↗

arXiv2022

Non-Functional Testing of Runtime Enforcers in Android

Runtime enforcers can be used to ensure that running applications satisfy desired correctness properties. Although runtime enforcers that are correct-by-construction with respect to abstract behavioral models are relatively easy to specify, the concrete software enforcers generated from these specifications may easily introduce issues in the target application. Indeed developers can generate test suites to verify the functional behavior of the enforcers, for instance exploiting the same models used to specify them. However, it remains challenging and tedious to verify the behavior of enforcers in terms of non-functional performance characteristics. This paper describes a practical approach to reveal runtime enforcers that may introduce inefficiencies in the target application. The approach relies on a combination of automatic test generation and runtime monitoring of multiple key performance indicators. We designed our approach to reveal issues in four indicators for mobile systems: responsiveness, launch time, memory, and energy consumption. Experimental results show that our approach can detect performance issues that might be introduced by automatically generated enforcers.

cs.SE↗

arXiv2022

Proactive Libraries: Enforcing Correct Behaviors in Android Apps

The Android framework provides a rich set of APIs that can be exploited by developers to build their apps. However, the rapid evolution of these APIs jointly with the specific characteristics of the lifecycle of the Android components challenge developers, who may release apps that use APIs incorrectly. In this demo, we present Proactive Libraries, a tool that can be used to decorate regular libraries with the capability of proactively detecting and healing API misuses at runtime. Proactive Libraries blend libraries with multiple proactive modules that collect data, check the compliance of API usages with correctness policies, and heal executions as soon as the possible violation of a policy is detected. The results of our evaluation with 27 possible API misuses show the effectiveness of Proactive Libraries in correcting API misuses with negligible runtime overhead.

cs.SE↗

arXiv2022

Exception-Driven Fault Localization for Automated Program Repair

Automated Program Repair (APR) techniques typically exploit spectrum-based fault localization (SBFL) to identify the program locations that should be patched, making the effectiveness of APR techniques dependent on the effectiveness of fault localization. Indeed, results show that SBFL often does not localize faults accurately, hindering the effectiveness of APR. In this paper, we propose EXCEPT, a technique that addresses the localization problem by focusing on the semantics of failures rather than on the correlation between the executed statements and the failed tests, as SBFL does. We focus on failures due to exceptions and we exploit their type and source to localize and guess the faults. Experiments with 43 exception-raising faults from the Defects4J benchmark show that EXCEPT can perform better than Ochiai and ssFix.

cs.SE↗

arXiv2021

Cloud Failure Prediction with Hierarchical Temporal Memory: An Empirical Assessment

Hierarchical Temporal Memory (HTM) is an unsupervised learning algorithm inspired by the features of the neocortex that can be used to continuously process stream data and detect anomalies, without requiring a large amount of data for training nor requiring labeled data. HTM is also able to continuously learn from samples, providing a model that is always up-to-date with respect to observations. These characteristics make HTM particularly suitable for supporting online failure prediction in cloud systems, which are systems with a dynamically changing behavior that must be monitored to anticipate problems. This paper presents the first systematic study that assesses HTM in the context of failure prediction. The results that we obtained considering 72 configurations of HTM applied to 12 different types of faults introduced in the Clearwater cloud system show that HTM can help to predict failures with sufficient effectiveness (F-measure = 0.76), representing an interesting practical alternative to (semi-)supervised algorithms.

cs.NE↗

arXiv2021

Declarative Dashboard Generation

Systems of systems are highly dynamic software systems that require flexible monitoring solutions to be observed and controlled. Indeed, operators have to frequently adapt the set of collected indicators according to changing circumstances, to visualize the behavior of the monitored systems and timely take actions, if needed. Unfortunately, dashboard systems are still quite cumbersome to configure and adapt to a changing set of indicators that must be visualized. This paper reports our initial effort towards the definition of an automatic dashboard generation process that exploits metamodel layouts to create a full dashboard from a set of indicators selected by operators.

cs.SE↗