arXiv subjects

Paulo Borba

Publications and source records attributed to Paulo Borba.

15 recordsLinked to original sources

arXiv2026

MergirafSemi: A Language-Agnostic Semistructured Merge Tool

Developers frequently face merge conflicts when integrating concurrent changes. Most merge tools rely on unstructured, line-based comparisons, often producing spurious conflicts and missing actual conflicts. To address these limitations, structure-aware merge tools have been proposed, which leverage syntactic representations to improve merge accuracy. However, fully structured tools may incur higher computational cost, and language-specific tools require significant development and maintenance effort. To balance these trade-offs, we propose MergirafSemi, a language-agnostic semistructured merge tool that captures structural information without requiring full structural modeling or language-specific implementations, and applies line-based merging within specific program regions, such as method bodies in Java. Our tool leverages lightweight Concrete Syntax Trees to guide merging decisions while preserving flexibility and efficiency across languages. We evaluate our tool through an empirical study on real-world merge scenarios across multiple programming languages, comparing it with unstructured, semistructured, and structured tools. Our results show that increasing structural granularity improves automatic conflict resolution but can also lead to more aggressive merge decisions, increasing the number of missed actual conflicts. In contrast, MergirafSemi achieves a more balanced trade-off, reducing spurious conflicts while maintaining competitive accuracy and better runtime performance in most common scenarios. Compared to an unstructured tool, it substantially reduces spurious conflicts, and when compared to a semistructured language-specific tool, it achieves comparable effectiveness while exhibiting more robust execution behavior and significantly lower runtime overhead.

cs.SE↗

arXiv2026

GitHub Template Repositories: Served Domains, Maintenance, and Practitioner Guidelines

Over time, GitHub has introduced different strategies for sharing reusable code artifacts. In addition to fork-based reuse, template repositories provide a distinct feature for generating new projects from scaffolding. Although this feature has been available since 2019, little is known about the domains it supports, its maintenance characteristics, or the practices that guide practitioners for effective template design. To address this gap, we conduct a large-scale empirical study of GitHub template repositories across the five most used programming languages. First, we mine and categorize templates to analyze the domains they serve, exploring the LLM-as-a-judge strategy. Next, we explore the reliability of templates by evaluating the associations between repository characteristics and activity, and quality-related issues (e.g., code smells, vulnerabilities, and security hotspots) through statistical analysis. Finally, we qualitatively analyze a representative subset of templates to derive practical guidelines and recurring pitfalls for template design and management. Our results show that Web Development is the predominant domain across ecosystems, while maintenance and quality issues vary by programming language. We further find that high-quality templates tend to adopt established software engineering practices, while providing comprehensive documentation and clear guidance for use. Overall, our findings offer empirical insights and actionable guidance to support practitioners in designing and adopting high-quality template repositories.

cs.SE↗

arXiv2026

Contrastive meta-domain adaptation for robust skin lesion classification across clinical and acquisition conditions

Deep learning models for dermatological image analysis remain sensitive to acquisition variability and domain-specific visual characteristics, leading to performance degradation when deployed in clinical settings. We investigate how visual artifacts and domain shifts affect deep learning-based skin lesion classification. We propose an adaptation strategy, grounded in the idea of visual meta-domains, that transfers visual representations from larger dermoscopic datasets into clinical image domains, thereby improving generalization robustness. Experiments across multiple dermatology datasets show consistent gains in classification performance and reduced gaps between dermoscopic and clinical images. These results emphasize the importance of domain-aware training for deployable systems.

cs.CV↗

arXiv2025

DermAI: Clinical dermatology acquisition through quality-driven image collection for AI classification in mobile

AI-based dermatology adoption remains limited by biased datasets, variable image quality, and limited validation. We introduce DermAI, a lightweight, smartphone-based application that enables real-time capture, annotation, and classification of skin lesions during routine consultations. Unlike prior dermoscopy-focused tools, DermAI performs on-device quality checks, and local model adaptation. The DermAI clinical dataset, encompasses a wide range of skin tones, ethinicity and source devices. In preliminary experiments, models trained on public datasets failed to generalize to our samples, while fine-tuning with local data improved performance. These results highlight the importance of standardized, diverse data collection aligned with healthcare needs and oriented to machine learning development.

cs.CV↗

arXiv2025

RefFilter: Improving Semantic Conflict Detection via Refactoring-Aware Static Analysis

Detecting semantic interference remains a challenge in collaborative software development. Recent lightweight static analysis techniques improve efficiency over SDG-based methods, but they still suffer from a high rate of false positives. A key cause of these false positives is the presence of behavior-preserving code refactorings, which current techniques cannot effectively distinguish from changes that impact behavior and can interfere with others. To handle this problem we present RefFilter, a refactoring-aware tool for semantic interference detection. It builds on existing static techniques by incorporating automated refactoring detection to improve precision. RefFilter discards behavior-preserving refactorings from reports, reducing false positives while preserving detection coverage. To evaluate effectiveness and scalability, use two datasets: a labeled dataset with 99 scenarios and ground truth, and a novel dataset of 1,087 diverse merge scenarios that we have built. Experimental results show that RefFilter reduces false positives by nearly 32% on the labeled dataset. While this reduction comes with a non significant increase in false negatives, the overall gain in precision significantly outweighs the minor trade-off in recall. These findings demonstrate that refactoring-aware interference detection is a practical and effective strategy for improving merge support in modern development workflows.

cs.SE↗

arXiv2025

The Effect of Pointer Analysis on Semantic Conflict Detection

Current merge tools don't detect semantic conflicts, which occur when changes from different developers are textually integrated but semantically interfere with each other. Although researchers have proposed static analyses for detecting semantic conflicts, these analyses suffer from significant false positive rates. To understand whether such false positives could be reduced by using pointer analysis in the implementation of semantic conflict static analyses, we conduct an empirical study. We implement the same analysis with and without pointer analysis, run them on two datasets, observe how often they differ, and compare their accuracy and computational performance. Although pointer analysis is known to improve precision in static analysis, we find that its effect on semantic conflict detection can be drastic: we observe a significant reduction in timeouts and false positives, but also a significant increase in false negatives, with prohibitive drops in recall and F1-score. These results suggest that, in the context of semantic conflict detection, we should explore hybrid analysis techniques, combining aspects of both implementations we compare in our study.

cs.SE↗

arXiv2025

LastMerge: A language-agnostic structured tool for code integration

Unstructured line-based merge tools are widely used in practice. Structured AST-based merge tools show significantly improved merge accuracy, but are rarely used in practice because they are language specific and costly, consequently not being available for many programming languages. To improve merge accuracy for a wide range of languages, we propose LastMerge, a generic structured merge tool that can be configured through a thin interface that significantly reduces the effort of supporting structured merge. To understand the impact that generic structured merge might have on merge accuracy and performance, we run an experiment with four structured merge tools: two Java specific tools, jDime and Spork, and their generic counterparts, respectively LastMerge and Mergiraf. Using each tool, we replay merge scenarios from a significant dataset, and collect data on runtime, behavioral divergences, and merge accuracy. Our results show no evidence that generic structured merge significantly impacts merge accuracy. Although we observe a difference rate of approximately 10% between the Java specific tools and their generic counterparts, most of the differences stem from implementation details and could be avoided. We find that LastMerge reports 15% fewer false positives than jDime while Mergiraf misses 42% fewer false negatives than Spork. Both generic tools exhibit comparable runtime performance to the state of the art language specific implementations. These results suggest that generic structured merge tools can effectively replace language-specific ones, paving the way for broader adoption of structured merge in industry.

cs.SE↗

arXiv2025

Choosing the Right Git Workflow: A Comparative Analysis of Trunk-based vs. Branch-based Approaches

Git has become one of the most widely used version control systems today. Among its distinguishing features, its ability to easily and quickly create branches stands out, allowing teams to customize their workflows. In this context, various formats of collaborative development workflows using Git have emerged and gained popularity among software engineers. We can categorize such workflows into two main types: branch-based workflows and trunk-based workflows. Branch-based workflows typically define a set of remote branches with well-defined objectives, such as feature branches, a branch for feature integration, and a main branch. The goal is to migrate changes from the most isolated branch to the main one shared by all as the code matures. In this category, GitFlow stands out as the most popular example. In contrast, trunk-based workflows have a single remote branch where developers integrate their changes directly. In this range of options, choosing a workflow that maximizes team productivity while promoting software quality becomes a non-trivial task. Despite discussions on forums, social networks, and blogs, few scientific articles have explored this topic. In this work, we provide evidence on how Brazilian developers work with Git workflows and what factors favor or hinder the use of each model. To this end, we conducted semi-structured interviews and a survey with software developers. Our results indicate that trunk-based development favors fast-paced projects with experienced and smaller teams, while branch-based development suits less experienced and larger teams better, despite posing management challenges.

cs.SE↗

arXiv2025

Detec\c{c}\~ao de Conflitos Sem\^anticos com Testes Gerados por LLM

Semantic conflicts arise when a developer introduces changes to a codebase that unintentionally affect the behavior of changes integrated in parallel by other developers. Traditional merge tools are unable to detect such conflicts, so complementary tools like SMAT have been proposed. SMAT relies on generating and executing unit tests: if a test fails on the base version, passes on a developer's modified version, but fails again after merging with another developer's changes, a semantic conflict is indicated. While SMAT is effective at detecting conflicts, it suffers from a high rate of false negatives, partly due to the limitations of unit test generation tools such as Randoop and Evosuite. To investigate whether large language models (LLMs) can overcome these limitations, we propose and integrate a new test generation tool based on Code Llama 70B into SMAT. We explore the model's ability to generate tests using different interaction strategies, prompt contents, and parameter configurations. Our evaluation uses two samples: a benchmark with simpler systems from related work, and a more significant sample based on complex, real-world systems. We assess the effectiveness of the new SMAT extension in detecting conflicts. Results indicate that, although LLM-based test generation remains challenging and computationally expensive in complex scenarios, there is promising potential for improving semantic conflict detection.

cs.SE↗

arXiv2025

An analysis of data variation and bias in image-based dermatological datasets for machine learning classification

AI algorithms have become valuable in aiding professionals in healthcare. The increasing confidence obtained by these models is helpful in critical decision demands. In clinical dermatology, classification models can detect malignant lesions on patients' skin using only RGB images as input. However, most learning-based methods employ data acquired from dermoscopic datasets on training, which are large and validated by a gold standard. Clinical models aim to deal with classification on users' smartphone cameras that do not contain the corresponding resolution provided by dermoscopy. Also, clinical applications bring new challenges. It can contain captures from uncontrolled environments, skin tone variations, viewpoint changes, noises in data and labels, and unbalanced classes. A possible alternative would be to use transfer learning to deal with the clinical images. However, as the number of samples is low, it can cause degradations on the model's performance; the source distribution used in training differs from the test set. This work aims to evaluate the gap between dermoscopic and clinical samples and understand how the dataset variations impact training. It assesses the main differences between distributions that disturb the model's prediction. Finally, from experiments on different architectures, we argue how to combine the data from divergent distributions, decreasing the impact on the model's final accuracy.

cs.CV↗

arXiv2024

Semistructured Merge with Language-Specific Syntactic Separators

Structured merge tools exploit programming language syntactic structure to enhance merge accuracy by reducing spurious conflicts reported by unstructured tools. By creating and handling full ASTs, structured tools are language-specific and harder to implement. They can also be computationally expensive when merging large files.To reduce these drawbacks, semistructured merge tools work with partial ASTs that use strings to represent lower level syntactic structures such as method bodies, and rely on unstructured tools to merge them. This, however, results in merge accuracy loss. To improve accuracy without compromising semistructured merge benefits, we propose a tool that leverages language-specific syntactic separators to infer structure without parsing. We still resort to an unstructured tool to merge lower level structures, but only after preprocessing the code so that text in between separators such as curly braces appear in separate lines. This way we emulate the capabilities of structured merge tools while avoiding their drawbacks. By comparing our tool with a robust implementation of semistructured merge, we find that our tool substantially reduces the number of spurious conflicts. We also observe significant but less substantial reductions on the overall number of reported conflicts, and of files with conflicts. However, similar to structured tools, our tool lets more merge conflicts go undetected. Our tool shows significant improvements over unstructured tools widely used in practice. Finally we observe that exploiting language-specific syntactic separators introduces unique textual alignment challenges.

cs.SE↗

arXiv2024

Using Information Flow to estimate interference between developers same method contributions

This work's main goal is to understand if Information Flow Control (IFC), a security technique used for discovering leaks in software, could be used to indicate the presence of dynamic semantic conflicts between developers contributions in merge scenarios. However, as defining if a dynamic semantic conflict exists involves understanding the expected behaviour of a system, and as such behavioural specifications are often hard to capture, formalize and reason about, we instead try to detect a code level adaptation of the notion of interference from Goguen and Meseguer. We limit our scope to interference caused by developers contributions on the same method. Therefore, we conduct an evaluation to understand if information flow may be used to estimate interference. In particular, we use Java Object-sensitive Analysis (JOANA) to do the IFC for Java programs. JOANA does the IFC of Java programs by using a System Dependence Graph (SDG), a directed graph representing the information flow through a program. Additionally, we bring evidence that information flow between developers same-method contributions occurred for around 64% of the scenarios we evaluated. Finally, we conducted a manual analysis, on 35 scenarios with information flow between developers same-method contributions, to understand the limitations of using information flow to estimate interference between same-method contributions. From the 35 analysed scenarios, for only 15 we considered that an interference in fact existed. We found three different major reasons for detecting information flow and no interference: cases related to the nature of changes, to excessive annotation from our strategy and to the conservativeness of the flows identified by JOANA. We conclude that information flow may be used to estimate interference, but, ideally, the number of false positives should be reduced.

cs.SE↗

arXiv2023

Detecting Semantic Conflicts using Static Analysis

Version control system tools empower developers to independently work on their development tasks. These tools also facilitate the integration of changes through merging operations, and report textual conflicts. However, when developers integrate their changes, they might encounter other types of conflicts that are not detected by current merge tools. In this paper, we focus on dynamic semantic conflicts, which occur when merging reports no textual conflicts but results in undesired interference - causing unexpected program behavior at runtime. To address this issue, we propose a technique that explores the use of static analysis to detect interference when merging contributions from two developers. We evaluate our technique using a dataset of 99 experimental units extracted from merge scenarios. The results provide evidence that our technique presents significant interference detection capability. It outperforms, in terms of F1 score and recall, previous methods that rely on dynamic analysis for detecting semantic conflicts, but these show better precision. Our technique precision is comparable to the ones observed in other studies that also leverage static analysis or use theorem proving techniques to detect semantic conflicts, albeit with significantly improved overall performance.

cs.SE↗

arXiv2023

Detecting Semantic Conflicts with Unit Tests

Branching and merging are common practices in collaborative software development, increasing developer's productivity. Despite such benefits, developers need to merge software and resolve merge conflicts. While modern merge techniques can resolve textual conflicts automatically, they fail when the conflict arises at the semantic level. Although semantic merge tools have been proposed, they are usually based on heavyweight static analyses or need explicit specifications of program behavior. In this work, we take a different route and propose SAM (SemAntic Merge), a semantic merge tool based on the automated generation of unit tests that are used as partial specifications. To evaluate SAM's feasibility for detecting conflicts, we perform an empirical study analyzing more than 80 pairs of changes integrated into common class elements from 51 merge scenarios. Furthermore, we also assess how the four unit-test generation tools used by SAM contribute to conflict identification. We propose and assess the adoption of Testability Transformations and Serialization. Our results show that SAM best performs when combining only the tests generated by Differential EvoSuite and EvoSuite and using the proposed Testability Transformations (nine detected conflicts out of 28). These results reinforce previous findings about the potential of using test-case generation to detect test conflicts.

cs.SE↗

arXiv2020

Programming the Universe: The First Commandment of Software Engineering for all Varieties of Information Systems

Since the early days of computers and programs, the process and outcomes of software development has been a minefield plagued with problems and failures, as much as the complexity and complication of software and its development has increased by a thousandfold in half a century. Over the years, a number of theories, laws, best practices, manifestos and methodologies have emerged, with varied degrees of (un)success. Our experience as software engineers of complex and large-scale systems shows that those guidelines are bound to previously defined and often narrow scopes. Enough is enough. Nowadays, nearly every company is in the software and services business and everything is - or is managed by - software. It is about time, then, that the laws that govern our universe ought to be redefined. In this context, we discuss and present a set of universal laws that leads us to propose the first commandment of software engineering for all varieties of information systems.

cs.SE↗