Background . Code coverage and mutation score serve as pivotal test effectiveness metrics used to assess a test suite’s ability to uncover actual defects. However, prior research has produced inconsistent or even conflicting findings regarding their correlation with defect detection capability, particularly concerning the impact of test suite size. Problem. The extent of the potentially confounding effect of test suite size in test effectiveness evaluation context is not clear, nor is the method to remove the potentially confounding effect, or the influence of this removal on the performance of test suite optimization. Objective . Our goal is to deeply understand how test suite size affects the true relationship between test effectiveness metrics and a test suite’s ability to detect actual defects. Method. We first employ statistical methods to examine the extent of the potentially confounding effect of test suite size in the context of test effectiveness evaluation. After that, we propose a linear regression-based method to remove the potentially confounding effect of test suite size. Finally, we empirically explore the impact of this removal method on test suite optimization. Result. Our experimental results, based on the Defects4J defect dataset, uncovers that: (1) the confounding effect of test suite size on the associations between test effectiveness metrics and defect detection capability in general exists; (2) the proposed linear regression-based method can effectively remove the confounding effect; and (3) after removing the confounding effect, mutation score demonstrates superior effectiveness in predicting test suite effectiveness, while statement coverage is the least effective metric. Furthermore, both coverage-based and mutation-based test suite reduction exhibit enhanced cost-effectiveness in defect detection, and there is a marginal improvement in the speed of defect detection for coverage-based test case prioritization. Conclusion . When using test effectiveness metrics to assess test suite effectiveness, it is crucial to eliminate the influence of test suite size.

Machine Learning (ML) software employs statistical algorithms to perform high-stake tasks in our daily lives, whose results are usually discriminatory due to protected features (e.g., gender), i.e., one part (called privileged, e.g., male) may be more likely to obtain beneficial decisions than the other part (called unprivileged, e.g., female). In alleviating the unfairness, developers have obtained widely held beliefs about the tradeoff between performance and fairness for ML software. Surprisingly, recent research on feature engineering suggests that enlarging the feature set is the perfect way to kill two birds with one stone, i.e., achieving both higher performance and fairness. However, the experiments used in the prior study did not remove the effect of protected features, which have been suggested to be excluded in both industrial applications and academic studies. As a result, the study did not fully explore the tradeoff between performance and fairness. In this article, we first conduct an empirical study to replicate this prior study after excluding the protected features and observe that there is still a tradeoff between performance and fairness with enlarging the features, i.e., more features are not perfect, which would lead to higher performance and lower fairness. Due to more features causing more collection and pre-processing budgets, we aim to search for an effective alternative. Inspired by the “less is more” principle, we propose a novel feature ranking method, Hybrid-importance and Early-validation based Feature Ranking (HEFR) , to find an efficient subset to replace the full feature set with comparable performance and fairness. Our method, HEFR, employs hybrid feature importances to combine performance and fairness and conducts early validation to check the effectiveness of hybrid importances. We conduct experiments on seven datasets and three classifiers to evaluate our method with five baselines. The results have shown that (a) HEFR is efficient for ML software feature engineering: applying HEFR to choose about 10% of features would construct ML software with better or comparable performance and fairness, and (b) HEFR is actionable with small dataset sizes: applying HEFR with only 10% data size would still help choose the proper feature subset.

Code-line-Ievel defect prediction (CLDP) is an effective technique to incorporate comprehensive measures for buggy line identification to optimize efforts in Software Quality Assurance activities. Most CLDP methods either consider the textual information of the code or rely merely on file-level label information, which have not fully leveraged the essential information in the CLDP context, with historical code-line-level labels being incredibly overlooked in their application. Due to the vast number of code lines and the sparsity of the tokens they contain, leveraging historical code-line-level label information remains a significant challenge. To address this issue, we propose a novel CLDP method, Spectrum infOrmation and caUsality aNalysis based coDe-line-level defect prediction (SOUND). SOUND incorporates two key ideas: (a) it introduces a spectrum information perspective, utilizing labels from historical defective lines to quantify the contribution of tokens to line-level defects, and (b) it applies causal analysis to obtain a more systematic and comprehensive understanding of the causal relationships between tokens and defects. After conducting a comprehensive study involving 142 releases across 19 software projects, the experimental results demonstrate that our method significantly outperforms existing state-of-the-art (SOTA) CLDP baseline methods in terms of its ability to rank defective lines under three indicators, IFA, Recall@Top20%LOC, and Effort@Top20%Recall. Notably, in terms of IFA, our method achieves a score of 0 in most cases, indicating that the first line in the ranking list generated by our method is actually defective, significantly enhancing its practicality.

ABSTRACT The relationship between test code and production code, that is, test‐to‐code traceability, plays an essential role in the verification, reliability, and certification of software systems. Prior work on test‐to‐code traceability focuses mainly on Java. However, as Python allows more flexible testing styles, it is still unknown whether existing traceability approaches work well on Python projects. In order to address this gap in knowledge, this paper evaluates whether existing traceability approaches can accurately identify test‐to‐code links in Python projects. We collected seven popular Python projects and carried out an exploratory study at both the method and module levels (involving a total of 3198 test cases). On these projects, we evaluated 15 individual traceability techniques along with cross‐level information propagation and four combining resolution strategies. The results reveal that the performance of test‐to‐code traceability approaches on Python has many differences with Java: (1) most of the existing techniques have poor effectiveness for Python; (2) after augmenting with cross‐level information, the recall surprisingly drops; and (3) machine learning based combination approach achieves the best recall but the worst precision. These findings shed light on the best traceability approaches for Python projects, and also provide guidelines for researchers and the Python community.

Deep learning (DL) models have proven to be highly successful and are now essential to our everyday routines. However, DL models, like traditional software, inevitably contain bugs that affect their performance in real-world scenarios. Effective software engineering techniques are necessary to ensure their dependability. In recent years, fault localization methods for DL models have gained significant attention as a valuable tool for improving the reliability of DL models. Owing to the data-driven programming paradigm, traditional fault localization techniques are challenging to apply directly to DL programs. Previous studies have shown that neuron errors within models can lead to abnormal behavior, and they fix the DL model errors from the perspective of neurons. Nonetheless, there remains a significant gap between the DL program statement and model errors. To tackle this problem, this paper proposes a novel fault localization method for DL models, named wei G hted s U sp I ciousness an D balanc E d agg R egation ( \(\mathsf{GUIDER}\) ) that revisits the idea and challenge of spectrum-based fault localization in the context of DL models. For pre-trained DL models, \(\mathsf{GUIDER}\) utilizes neuron coverage information and test case confidence to compute weighted neuron suspiciousness values and employs balanced aggregation methods to elevate these values from the neuron level to the layer level, which establishes a bridge between the DL model and the DL program, facilitating the developers’ debugging process. We evaluate \(\mathsf{GUIDER}\) using 161 real model bugs collected from StackOverflow and five state-of-the-art fault localization methods for DL models as baselines. The results indicate that (a) our method successfully localizes 67% of the model bugs by ranking the buggy layer to the first place (i.e., top- \(1\) ), significantly outperforming all five baselines, and (b) our method maintains an acceptable time overhead compared with all baseline methods.

The co-evolution of production and test code (PT co-evolution) has received increasing attention in recent years. However, we found that existing work did not comprehensively study various PT co-evolution scenarios, such as the qualification and persistence of their effects on software. Inspired by technical debt (TD), we refer to TD generated during the co-evolution between production and test code as PT co-evolution technical debt (PTCoTD). To better understand PT co-evolution, we first conducted an exploratory study on its characteristics on 15 open-source projects, finding unbalanced PT co-evolution prevalent and summarizing five potential PT flaws. Then we proposed an approach to identify and quantify PTCoTDs of these flaw patterns, considering evolutionary and structural relationships. We also built prediction models to describe cost trajectories and rank all PTCoTDs to prioritize expensive ones. The evaluation on the 15 projects shows that our approach can identify PTCoTDs that deserve attention. The identified PTCoTDs account for about half of the project's total maintenance costs, and the cost proportion of the expensive Top-5 is 1.8x more than the file proportion they contain. Almost all covered maintenance costs persist as PTCoTD in the future, with an average increase of 6.8% between the last two releases. Our approach also accurately predicts the costs of PTCoTD with an average prediction deviation of only 8.3%. Our study provides valuable insights into PT co-evolution scenarios and their effects, which can guide practices and inspire future work on software testing and maintenance.

Tests, as an essential artifact, should co-evolve with the production code to ensure that the associated production code satisfies specification. However, developers often postpone or even forget to update tests, making the tests outdated and lag behind the code. To predict which tests need to be updated when production code is changed, it is challenging to identify all related tests and determine their change probabilities due to complex change scenarios. This paper fills the gap and proposes a hybrid approach named COTE to predict code-to-test co-evolution. We first compute the linked test candidates based on different code-to-test dependencies. After that, we identify common co-change patterns by building a method-level dependence graph. For the remaining ambiguous patterns, we leverage a pre-trained language model which captures the semantic features of code and the change reasons contained in commit messages to judge one test’s likelihood of being updated. Experiments on our datasets consisting of 6,314 samples extracted from 5,000 Java projects show that COTE outperforms state-of-the-art approaches, achieving a precision of 89.0% and a recall of 71.6%. This work can help practitioners reduce test maintenance costs and improve software quality.

In the rapidly advancing field of software development, the demand for practical code translation tools has surged, driven by the need for interoperability across different programming environments. Existing learning-based approaches often need help with low-resource programming languages that lack sufficient parallel code corpora for training. To address these limitations, we propose a novel training framework that begins with monolingual seed corpora, generating parallel datasets via back-translation and incorporating compiler feedback to optimize the translation model.As a case study, we apply our method to train a code translation model for a new-born low-resource programming language, Cangjie. We also construct a parallel test dataset forJava-to-Cangjietranslation and test cases to evaluate the effectiveness of our approach. Experimental results demonstrate that compiler feedback greatly enhances syntactical correctness, semantic accuracy, and test pass rates of the translatedCangjiecode. These findings highlight the potential of our method to support code translation in low-resource settings, expanding the capabilities of learning-based models for programming languages with limited data availability.

In the wake of developments in the field of Natural Language Processing, Question Answering (QA) software has penetrated our daily lives. Due to the data-driven programming paradigm, QA software inevitably contains bugs, i.e., misbehaving in real-world applications. Current testing techniques for testing QA software include two folds, reference-based testing and metamorphic testing.

Search-based unit test generation methods have been considered effective and widely applied, and Large Language Models (LLMs) have also demonstrated their powerful generation ability. Therefore, some scholars have proposed using LLMs to enhance search-based unit test generation methods and have preliminarily confirmed that LLMs can help alleviate the problem of test coverage plateaus. However, it is still unclear when and how LLMs should intervene in the time-consuming test generation process. This paper explores the application of LLMs at various stages of search-based test generation (SBTG) (including the initial stage, the test generation period, and the test coverage plateaus), as well as strategies for controlling the frequency of LLM intervention. A comprehensive empirical study was conducted on 486 Python benchmark modules from 27 projects. The experimental results show that 1) LLM intervention has a positive effect at any stage, whether to improve coverage over a fixed period or to reduce the time to reach a specific coverage; 2) a reasonable intervention frequency is crucial for LLMs to have a positive effect on SBTG. This work can better help understand when and how LLMs should be applied in SBTG and provide valuable suggestions for developers in practice.

Machine translation has become an integral part of daily life, with terminology translation playing a crucial role in ensuring the accuracy of translation results. However, existing translation systems, such as Google Translate, have been shown to occasionally produce errors in terminology translation. Current metrics for assessing terminology translation rely on reference translations and bilingual dictionaries, limiting their effectiveness in large-scale automated MT system testing.

Android platform offers a hybrid concurrency model encompassing multi-threading and asynchronous messaging for concurrent programming. The model is powerful but complex, making it difficult for developers to analyze concurrent behaviors. Data race, a prevalent concurrency defect in real-world Android applications, often results in abnormal executions of mobile applications, even crashes. Despite quite a few studies on detecting data races, it still suffers from high false positives with static analysis techniques and high false negatives with dynamic analysis techniques. To address this issue, this paper presents a predictive approach, PredRacer, for detecting data races in Android applications. It first captures an execution trace of an Android application, and then reorders the events within the trace based on partial orders. Finally, it checks the feasibility of the generated event sequence, which contains a potential data race. PredRacer increases the search scope and reduces false negatives while mitigating false positives by incorporating the happen-before relations specific to the Android concurrency model. The effectiveness of PredRacer is evaluated using the BenchERoid data set. Experimental results demonstrate that PredRacer achieves high precision, recall, and F1 score, outperforming the state-of-the-art techniques. A collection of 20 open-source Android applications is further utilized to assess the effectiveness of PredRacer, and an evaluation of 300 wild apps is conducted to assess its efficiency and scalability.

As a fundamental component of software documentation, code comments could help developers comprehend and maintain programs. Several datasets of method header comments have been proposed in previous studies for machine learning-based code comment generation. As part of code comments, inline code comments are also crucial for code understanding activities. However, unlike method header comments written in a standard format and describing the whole method code, inline comments are often written in arbitrary formats by developers due to timelines pressures and different aspects of code snippets in the method are described. Currently, there is no large-scale dataset used for inline comments generation considering these. Hence, this naturally inspires us to explore whether we can construct a dataset to foster machine learning research that not only performs fine-grained noise-cleaning but conducts a taxonomy of inline comments. To this end, we first collect inline comments and code snippets from 8000 Java projects on GitHub. Then, we conduct a manual review to obtain heuristic rules, which could be used to clean the data noise in a fine-grained manner. As a result, we construct a large-scale benchmark dataset named ICG with 5,740,770 pairs of inline comments and code snippets. We then build a comprehensive taxonomy and conduct a statistical and manual analysis to explore the performances of different categories of inline comments, such as helpfulness in code understanding. After that, we provide and compare several baseline models to automatically generate inline comments, such as CodeBERT, to enhance the usability of the benchmark for researchers. The availability of our benchmark and baselines can help develop and validate new inline comment generation methods, which would also further facilitate code understanding activities.

Abstract Gradual typing integrates static and dynamic typing by introducing a dynamic type and a consistency relation. A problem of gradual type systems is that dynamic types can easily hide erroneous data flows since consistency relations are not transitive. Therefore, a more rigorous static check is required to reveal these hidden data flows statically. However, in order to preserve the expressiveness of gradually typed languages, static checks for gradually typed languages cannot simply reject programs with potentially erroneous data flows. By contrast, a more reasonable request is to show how these data flows can affect the execution of the program. In this paper, we propose and formalize Static Blame , a framework that can reveal hidden data flows for gradually typed programs and establish the correspondence between static-time data flows and runtime behavior. With this correspondence, we build a classification of potential errors detected from hidden data flows and formally characterize the possible impact of potential errors in each category on program execution, without simply rejecting the whole program. We implemented Static Blame on Grift, an academic gradually typed language, and evaluated the effectiveness of Static Blame by mutation analysis to verify our theoretical results. Our findings revealed that Static Blame exhibits a notable level of precision and recall in detecting type-related bugs. Furthermore, we conducted a manual classification to elucidate the reasons behind instances of failure. We also evaluated the performance of Static Blame, showing a quadratic growth in run time as program size increases.

Summary Natural language inference (NLI) is a task to infer the relationship between the premise and hypothesis sentences, whose models have essential applications in the many natural language processing (NLP) fields, for example, machine reading comprehension and recognizing textual entailment. Due to the data‐driven programming paradigm, bugs inevitably occur in NLI models during the application process, which calls for novel automatic testing techniques to deal with NLI testing challenges. The main difficulty in achieving automatic testing for NLI models is the oracle problem; that is, it may be too expensive to label NLI model inputs manually and hence be too challenging to verify the correctness of model outputs. To tackle the oracle problem, this study proposes a novel automatic testing method hybrid mutation driven testing (HMT), which extends the mutation idea applied in other NLP domains successfully. Specifically, as there are two sets of sentences, that is, premise and hypothesis, to be mutated, we propose four mutation operators to achieve the hybrid mutation strategy, which mutate the premise and the hypothesis sentences jointly or individually. We assume that the mutation would not affect the outputs; that is, if the original and mutated outputs are inconsistent, inconsistency bugs could be detected without knowing the true labels. To evaluate our method HMT, we conduct experiments on two widely used datasets with two advanced models and generate more than 520,000 mutations by applying our mutation operators. Our experimental results show that (a) our method, HMT, can effectively generate mutated testing samples, (b) our method can effectively trigger the inconsistency bugs of the NLI models, and (c) all four mutation operators can independently trigger inconsistency bugs.

Abstract Issue tracking systems are now prevalent in software development, which would help developers submit and discuss issues to solve development problems on software projects. Most previous studies have been conducted to analyze issue relations within projects, such as recommending similar or duplicate bug issues. However, along with the popularization of co‐developing through multiple projects, many issues are cross‐project correlated (CPC), that is, one issue is associated with another issue in a different project. When developers meet with CPC issues, it may primarily increase the difficulties of solving them because they need information from not only their projects but also other related projects that developers are not familiar with. Identifying a CPC issue as early as possible is a fundamental challenge for both managers and developers to allocate the resources for software maintenance and estimate the effort to solve it. This paper proposes 11 issue metrics of two groups to describe textual summary and reporters' activity, which can be extracted just after the issue was reported. We employ these 11 issue metrics to construct just‐in‐time (JIT) prediction models to identify CPC issues. To evaluate the effect of CPC issue prediction models, we conduct experiments on 16 open‐source data science and deep learning projects and compare our prediction model with two baseline models based on textual features (i.e., Term Frequency‐Inverse Document Frequency [TF‐IDF] and Word Embedding), which are commonly adopted by previous studies on issue prediction. The results show that the JIT prediction model based on issue metrics has significantly improved the performance of CPC issue prediction under two evaluation indicators, Matthew's correlation coefficient (MCC) and F1. In addition, we find that the prediction model is more suitable for large‐scale complex core projects in the open‐source ecosystem.

In recent years, dynamic languages such as Python have become popular due to their flexibility and productivity. The lack of static typing makes programs face the challenges of fixing type errors, early bug detection, and code understanding. To alleviate these issues, PEP 484 introduced optional type annotations for Python in 2014, but unfortunately, a large number of programs are still not annotated by developers. Annotation generation tools can utilize type inference techniques. However, several important aspects of type annotation generation are overlooked by existing works, such as in-depth effectiveness analysis, potential improvement exploration, and practicality evaluation. And it is unclear how far we have been and how far we can go. In this paper, we set out to comprehensively investigate the effectiveness of type inference tools for generating type annotations, applying three categories of state-of-the-art tools on a carefully-cleaned dataset. First, we use a comprehensive set of metrics and categories, finding that existing tools have different effectiveness and cannot achieve both high accuracy and high coverage. Then, we summarize six patterns to present the limitations in type annotation generation. Next, we implement a simple but effective tool to demonstrate that existing tools can be improved in practice. Finally, we conduct a controlled experiment showing that existing tools can reduce the time spent annotating types and determine more precise types, but cannot reduce subjective difficulty. Our findings point out the limitations and improvement directions in type annotation generation, which can inspire future work.

Background. Software testing is a critical activity for ensuring the quality and reliability of software systems. To evaluate the effectiveness of different test suites, researchers have developed a variety of metrics. Problem. However, comparing these metrics is challenging due to the lack of a standardized evaluation framework including comprehensive factors. As a result, researchers often focus on single factors (e.g., size), which finally leads to different or even contradictory conclusions. After comparing dozens of pieces of work in detail, we have found two main problems most troubling to our community: (1) researchers tend to oversimplify the description of the ground truth they use, and (2) data involving real defects is not suitable for analysis using traditional statistical indicators. Objective. We aim at scrutinizing the whole process of comparing test suites for our community. Method. To hit this aim, we propose a framework ASSENT (ev A luating te S t S uite E ffective N ess me T rics) to guide the follow-up research for evaluating a test suite effectiveness metric. ASSENT consists of three fundamental components: ground truth, benchmark test suites, and agreement indicator. Its functioning is as follows: first, users clarify the ground truth for determining the real order in effectiveness among test suites. Second, users generate a set of benchmark test suites and derive their ground truth order in effectiveness. Third, users use the metric to derive the order in effectiveness for the same test suites. Finally, users calculate the agreement indicator between the two orders derived by two metrics. Result. With ASSENT, we are able to compare the accuracy of different test suite effectiveness metrics. We apply ASSENT to evaluate representative test suite effectiveness metrics, including mutation score and code coverage metrics. Our results show that, based on the real faults, mutation score, and subsuming mutation score are the best metrics to quantify test suite effectiveness. Meanwhile, by using mutants instead of real faults, test effectiveness will be overestimated by more than 20% in values. Conclusion. We recommend that the standardized evaluation framework ASSENT should be used for evaluating and comparing test effectiveness metrics in the future work.

The emergence of build automation tools with dependency management features has significantly impacted software development. However, in the configuration process, improper settings of some configuration items, such as the dependency scope setting, may cause severe problems in the development process. Improper setting of dependency scope may cause problems such as missing dependencies and redundant dependencies, and may even spread the problem to the downstream of the software ecosystem.

Machine translation systems have penetrated our daily lives, providing translation services from source language to target language to millions of users online daily. Word Sense Disambiguation (WSD) is one of the essential functional requirements of machine translation systems, which aims to determine the exact sense of polysemes in the given context. Commercial machine translation systems (e.g., Google Translate) have been shown to fail in identifying the proper sense and consequently cause translation errors. However, to our knowledge, no prior studies focus on testing such WSD bugs for machine translation systems.

Python has become increasingly popular and widely used in many fields. Dynamic features of Python provide much convenience for developers. However, they can also cause many type-related bugs undetected until runtime, which increases the cost of maintenance. Static type checking is essential to find bugs early, and the introduction of gradual typing and type annotations makes it easier to perform static type analysis. However, it remains to be investigated how well gradual typing improves real bug detection. Therefore, we conducted a comprehensive study on three widely used checkers: MyPy, PyRight, and PyType. We used a benchmark containing 10 popular Python projects with 40 real type-related bugs. First, we performed static type checking on the projects with and without type annotations to evaluate the effectiveness of finding real bugs. Second, we manually analyzed the missing bugs and investigated the reasons. The results show that the three tools can detect 29 of the 40 studied bugs after annotating, while only 14 bugs are detected before annotating. We also found that type annotations can substantially improve the ability of static type checkers to detect real bugs. A detailed analysis of bugs missed by the checkers shows that: (i) the accuracy of type analysis is challenged when it comes to programs with complicated dynamic features, such as dynamically changing object’s attributes, even with annotations; (ii) the inaccurate type annotations can undermine the ability of static type checkers to detect real bugs; (iii) static type checkers have different checking strategies in some cases, which has an impact on real bug detection. Our study can not only enable developers to better understand static type checking and make better use of them but also guide future research.

There has been an increasing interest in enhancing the fairness of machine learning (ML). Despite the growing number of fairness-improving methods, we lack a systematic understanding of the trade-offs among factors considered in the ML pipeline when fairness-improving methods are applied. This understanding is essential for developers to make informed decisions regarding the provision of fair ML services. Nonetheless, it is extremely difficult to analyze the trade-offs when there are multiple fairness parameters and other crucial metrics involved, coupled, and even in conflict with one another. This paper uses causality analysis as a principled method for analyzing trade-offs between fairness parameters and other crucial metrics in ML pipelines. To practically and effectively conduct causality analysis, we propose a set of domain-specific optimizations to facilitate accurate causal discovery and a unified, novel interface for trade-off analysis based on well-established causal inference methods. We conduct a comprehensive empirical study using three real-world datasets on a collection of widely-used fairness-improving techniques. Our study obtains actionable suggestions for users and developers of fair ML. We further demonstrate the versatile usage of our approach in selecting the optimal fairness-improving method, paving the way for more ethical and socially responsible AI technologies.

Automation testing is widely used in the functional testing of web applications. However, during the evolution of web applications, such web test scripts tend to break. It is essential to repair such broken test scripts to make regression testing run successfully. As manual repairing is time-consuming and expensive, researchers focus on automatic repairing techniques. Empirical study shows that the web element locator is the leading cause of web test breakages. Most existing repair techniques utilize Document Object Model attributes or visual appearances of elements to find their location but neglect their semantic information.

Background. Code-line-level bugginess identification (CLBI) is a vital technique that can facilitate developers to identify buggy lines without expending a large amount of human effort. Most of the existing studies tried to mine the characteristics of source codes to train supervised prediction models, which have been reported to be able to discriminate buggy code lines amongst others in a target program. Problem. However, several simple and clear code characteristics, such as complexity of code lines, have been disregarded in the current literature. Such characteristics can be acquired and applied easily in an unsupervised way to conduct more accurate CLBI, which also can decrease the application cost of existing CLBI approaches by a large margin. Objective. We aim at investigating the status quo in the field of CLBI from the perspective of (1) how far we have really come in the literature, and (2) how far we have yet to go in the industry, by analyzing the performance of state-of-the-art (SOTA) CLBI approaches and tools, respectively. Method. We propose a simple heuristic baseline solution GLANCE (aimin G at contro L - AN d C ompl E x-statements) with three implementations (i.e., GLANCE-MD, GLANCE-EA, and GLANCE-LR). GLANCE is a two-stage CLBI framework: first, use a simple model to predict the potentially defective files; second, leverage simple code characteristics to identify buggy code lines in the predicted defective files. We use GLANCE as the baseline to investigate the effectiveness of the SOTA CLBI approaches, including natural language processing (NLP) based, model interpretation techniques (MIT) based, and popular static analysis tools (SAT). Result. Based on 19 open-source projects with 142 different releases, the experimental results show that GLANCE framework has a prediction performance comparable or even superior to the existing SOTA CLBI approaches and tools in terms of 8 different performance indicators. Conclusion. The results caution us that, if the identification performance is the goal, the real progress in CLBI is not being achieved as it might have been envisaged in the literature and there is still a long way to go to really promote the effectiveness of static analysis tools in industry. In addition, we suggest using GLANCE as a baseline in future studies to demonstrate the usefulness of any newly proposed CLBI approach.

Managing cross-project dependencies is tricky in modern software development. A primary way to manage dependencies is using dependency configuration files, which brings convenience to the entire software ecosystem, including developers, maintainers, and users. However, developers may introduce dependency smells if dependency configuration files are not well written and maintained. Dependency smells are recurring violations of dependency management in dependency configuration files and can potentially lead to severe consequences. This paper provides an in-depth look at three dependency smells, namely,Missing Dependency,Bloated Dependency, andVersion Constraint Inconsistencyin Python projects. First, we implement a tool calledPythonCross-projectDependency- PyCD to accurately extract dependency information from configuration files. The evaluation result on 212 Python projects shows that PyCD outperforms state-of-the-art tools. Then, we make an empirical study for three dependency smells in 132 Python projects to investigate the pervasiveness, causes, and evolution. The results show that: 1) dependency smells are prevalent in Python projects and exist inconsistently in different projects; 2) dependency smells are introduced into Python projects for different reasons, mainly due to the problems of synchronous update and collaborative development; and 3) dependency smells can be removed with different patterns according to different dependency smells. Furthermore, we report and get responses for 40 harmful dependency smell instances, 34 of which have been responded that these dependency smells do exist in the projects, and 10 instances are fixed or under process. The feedback from developers indicates that dependency smells can have a negative impact on project maintenance. Our study highlights that these dependency smells deserve the attention of developers.

Static analysis (SA) tools can generate useful static warnings to reveal the problematic code snippets in a software system without dynamically executing the corresponding source code. In the literature, static warnings are of paramount importance because they can easily indicate specific types of software defects in the early stage of a software development process, which accordingly reduces the maintenance costs by a substantial margin. Unfortunately, due to the conservative approximations of such SA tools, a large number of false positive (FP for short) warnings (i.e., they do not indicate real bugs) are generated, making these tools less effective. During the past two decades, therefore, many false positive mitigation (FPM for short) approaches have been proposed so that more accurate and critical warnings can be delivered to developers. This paper offers a detailed survey of research achievements on the topic of FPM. Given the collected 130 surveyed papers, we conduct a comprehensive investigation from five different perspectives. First, we reveal the research trends of this field. Second, we classify the existing FPM approaches into five different types and then present the concrete research progress. Third, we analyze the evaluation system applied to examine the performance of the proposed approaches in terms of studied SA tools, evaluation scenarios, performance indicators, and collected datasets, respectively. Fourth, we summarize the four types of empirical studies relating to SA warnings to exploit the insightful findings that are helpful to reduce FP warnings. Finally, we sum up 10 challenges unresolved in the literature from the aspects of systematicness, effectiveness, completeness, and practicability and outline possible research opportunities based on three emerging techniques in the future.

The label quality of defect data sets has a direct influence on the reliability of defect prediction models. In this paper, we conduct a systematic study of inconsistent defect labels in multi-version-project defect data sets, i.e., many instances having the same source code but different labels over multiple versions of a software project. First, we report the phenomena of inconsistent labels by real examples and analyze their essence in the context of defect prediction. Then, we uncover the causes that lead to the occurrence of inconsistent labels for the representative label collection approaches. Finally, we investigate the actual influence of inconsistent labels on defect prediction models. We find that inconsistent labels in general exist in six multi-version-project defect data sets (either widely used or the most up-to-date in the literature) collected by diverse label collection approaches. In particular, inconsistent labels in a training data set significantly reduce the prediction performance of a model, while inconsistent labels in a test data set can lead to a considerable evaluation bias on the real performance. Therefore, we recommend that: on the one hand, researchers leverage our findings to make targeted methodological improvements on existing defect label collection approaches to reduce the generation of inconsistent labels; on the other hand, practitioners detect and exclude inconsistent labels in defect data sets to avoid their potential negative influence on defect prediction.

The ellipsis of the syntactic structure is a common phenomenon in ordinary textual documents. Existing studies have found that despite syntactic ellipsis could help avoid repetition of normative documents, it could also, for example, lead to ambiguity and hamper the understandability of document contents. As a fundamental component of software, code comments are generally written by developers in a non-structured way just like normative documents. This naturally inspires us to explore whether syntactic ellipsis is also a common phenomenon in code comments and what potential negative effects would such ellipsis have on software tasks such as code/comments comprehension activities. Such explorations, in our opinion, are expected to facilitate the research on code comments and comments-related software tasks. To this end, we conduct the first large-scale study to explore the syntactic structure ellipsis problem of code comments, with a focus on Java inline comments. Specifically, we construct a data set of 1,000 Java projects with 1,307,457 inline comments and associated codes. Based on this data set, we first study the prevalence of syntactic structure ellipsis in inline comments. We find that syntactic structure ellipsis is quite common in inline comments where 83.6% comments have structure ellipsis (such as subject/predicate omissions). Then, we investigate the effects of syntactic structure ellipsis on code/comment understanding activities. As a result, we find that there indeed exists a negative relationship between them, with a medium effect size. Based on these findings, we further propose neural network based approaches to complete the ellipsis parts for the inline comments. With our approach, we could achieve: 1) a medium improvement in assisting code/comment understanding activities, and 2) a substantial improvement of 11.3% in comment-assisted code abbreviation extension task.

With the widespread application of machine learning (ML) software, especially in high-risk tasks, the concern about their unfairness has been raised towards both developers and users of ML software. The unfairness of ML software indicates the software behavior affected by the sensitive features (e.g., sex), which leads to biased and illegal decisions and has become a worthy problem for the whole software engineering community.

Background. Mutation testing is a commonly used defect injection technique for evaluating the effectiveness of a test suite. However, it is usually computationally expensive. Therefore, many mutation reduction strategies, which aim to reduce the number of mutants, have been proposed. Problem. It is important to measure the ability of a mutation reduction strategy to maintain test suite effectiveness evaluation. However, existing evaluation indicators are unable to measure the “order-preserving ability”, i.e., to what extent the mutation score order among test suites is maintained before and after mutation reduction. As a result, misleading conclusions can be achieved when using existing indicators to evaluate the reduction effectiveness. Objective. We aim to propose evaluation indicators to measure the “order-preserving ability” of a mutation reduction strategy, which is important but missing in our community. Method. Given a test suite on a Software Under Test (SUT) with a set of original mutants, we leverage the test suite to generate a group of test suites that have a partial order relationship in defect detecting ability. When evaluating a reduction strategy, we first construct two partial order relationships among the generated test suites in terms of mutation score, one with the original mutants and another with the reduced mutants. Then, we measure the extent to which the partial order under the original mutants remains unchanged in the partial order under the reduced mutants. The more partial order is unchanged, the stronger the Order Preservation ( OP ) of the mutation reduction strategy is, and the more effective the reduction strategy is. Furthermore, we propose Effort-aware Relative Order Preservation ( EROP ) to measure how much gain a mutation reduction strategy can provide compared with a random reduction strategy. Result. The experimental results show that OP and EROP are able to efficiently measure the “order-preserving ability” of a mutation reduction strategy. As a result, they have a better ability to distinguish various mutation reduction strategies compared with the existing evaluation indicators. In addition, we find that Subsuming Mutant Selection (SMS) and Clustering Mutant Selection (CMS) are more effective than the other strategies under OP and EROP. Conclusion. We suggest, for the researchers, that OP and EROP should be used to measure the effectiveness of a mutant reduction strategy, and for the practitioners, that SMS and CMS should be given priority in practice.

Knowing the effectiveness of a test suite is essential for many activities such as assessing the test adequacy of code and guiding the generation of new test cases. Mutation testing is a commonly used defect injection technique for evaluating the effectiveness of a test suite. However, it is usually computationally expensive, as a large number of mutants (buggy versions) are needed to be generated from a production code under test and executed against the test suite. In order to reduce the expensive testing cost, recent studies proposed to use supervised models to predict the effectiveness of a test suite without executing the test suite against the mutants. Nonetheless, the training of such a supervised model requires labeled data, which still depends on the costly mutant execution. Furthermore, existing models are based on traditional supervised learning techniques, which assume that the training and testing data come from the same distribution. But, in practice, software systems are subject to considerable concept drifts, i.e., the same distribution assumption usually does not hold. This can lead to inaccurate predictions of a learned supervised model on the target code as time progresses. To tackle these problems, in this paper, we propose a Coverage-Based Unsupervised Approach (CBUA) for evaluating the effectiveness of a test suite. Given a production code under test, the corresponding mutants, and a test suite, CBUA first collects the coverage information of the mutated statements in the target production code under the execution of the test suite. Then, CBUA employs coverage to estimate the probability of each mutant being alive. As such, a mutation score is computed to evaluate the test suite effectiveness and the predicted labels (i.e., killed or alive) are obtained. The whole process only requires a one-time execution of the test suite against the target production code, without involving any mutant execution and any training data. CBUA can ensure the score monotonicity property (i.e., adding test cases to a test suite does not decrease its mutation score), which may be violated by a supervised approach. The experimental results show that CBUA is very competitive with the state-of-the-art supervised approaches in prediction accuracy. In particular, CBUA is shown to be more effective in finding mutants that are covered but not killed by a test suite, which is helpful in identifying the weaknesses in the current test suite and generating new test cases accordingly. Since CBUA is an easy-to-implement approach with a low cost, we suggest that it should be used as a baseline approach for comparison when any novel prediction approach is proposed in future studies.

The boom of DL technology leads to massive DL models built and shared, which facilitates the acquisition and reuse of DL models. For a given task, we encounter multiple DL models available with the same functionality, which are considered as candidates to achieve this task. Testers are expected to compare multiple DL models and select the more suitable ones w.r.t. the whole testing context. Due to the limitation of labeling effort, testers aim to select an efficient subset of samples to make an as precise rank estimation as possible for these models. To tackle this problem, we propose Sample Discrimination based Selection (SDS) to select efficient samples that could discriminate multiple models, i.e., the prediction behaviors (right/wrong) of these samples would be helpful to indicate the trend of model performance. To evaluate SDS, we conduct an extensive empirical study with three widely-used image datasets and 80 real world DL models. The experiment results show that, compared with state-of-the-art baseline methods, SDS is an effective and efficient sample selection method to rank multiple DL models.

Background. Self-admitted technical debt (SATD) is a special kind of technical debt that is intentionally introduced and remarked by code comments. Those technical debts reduce the quality of software and increase the cost of subsequent software maintenance. Therefore, it is necessary to find out and resolve these debts in time. Recently, many automatic approaches have been proposed to identify SATD. Problem. Popular IDEs support a number of predefined task annotation tags for indicating SATD in comments, which have been used in many projects. However, such clear prior knowledge is neglected by existing SATD identification approaches when identifying SATD. Objective. We aim to investigate how far we have really progressed in the field of SATD identification by comparing existing approaches with a simple approach that leverages the predefined task tags to identify SATD. Method. We first propose a simple heuristic approach that fuzzily Matches task Annotation Tags ( MAT ) in comments to identify SATD. In nature, MAT is an unsupervised approach, which does not need any data to train a prediction model and has a good understandability. Then, we examine the real progress in SATD identification by comparing MAT against existing approaches. Result. The experimental results reveal that: (1) MAT has a similar or even superior performance for SATD identification compared with existing approaches, regardless of whether non-effort-aware or effort-aware evaluation indicators are considered; (2) the SATDs (or non-SATDs) correctly identified by existing approaches are highly overlapped with those identified by MAT ; and (3) supervised approaches misclassify many SATDs marked with task tags as non-SATDs, which can be easily corrected by their combinations with MAT . Conclusion. It appears that the problem of SATD identification has been (unintentionally) complicated by our community, i.e., the real progress in SATD comments identification is not being achieved as it might have been envisaged. We hence suggest that, when many task tags are used in the comments of a target project, future SATD identification studies should use MAT as an easy-to-implement baseline to demonstrate the usefulness of any newly proposed approach.

The dynamic typing discipline of Python allows developers to program at a high level of abstraction. However, type related bugs are commonly encountered in Python systems due to the lack of type declaration and static type checking. Especially, the misuse of dynamic typing discipline produces underlying bugs and increases maintenance efforts. In this paper, we introduce six types of dynamic typing related practices in Python programs, which are the common but potentially risky usage of dynamic typing discipline by developers. We also implement a tool named PYDYPE to detect them. Based on this tool, we conduct an empirical study on nine real-world Python systems (with the size of more than 460KLOC) to understand dynamic typing related practices. We investigate how widespread the dynamic typing related practices are, why they are introduced into the systems, whether their usage correlates with increased likelihood of bug occurring, and how developers fix dynamic typing related bugs. The results show that: (1) dynamic typing related practices exist inconsistently in different systems and Inconsistent Variable Types is most prevalent; (2) they are introduced into systems mainly during early development phase to promote development efficiency; (3) they have a significant positive correlation with bug occurring; (4) developers tend to add type checks or exception handling to fix dynamic typing related bugs. These results benefit future research in coding convention, language design, bug detection and fixing.

Blocking bugs are a severe type of bugs that prevent other bugs from being fixed. As software becomes increasingly complex and large, blocking bugs occur in many large-scale software, especially in software ecosystems. Blocking bugs may have a high negative impact on software development and maintenance. Usually, blocking bugs preventing more bugs should be more concerned. In this paper, we focus on a special type of blocking bugs that block at least two bugs, which we call Critical Blocking Bugs (CBBs).

With the increasing application of deep learning (DL) models in many safety-critical scenarios, effective and efficient DL testing techniques are much in demand to improve the quality of DL models. One of the major challenges is the data gap between the training data to construct the models and the testing data to evaluate them. To bridge the gap, testers aim to collect an effective subset of inputs from the testing contexts, with limited labeling effort, for retraining DL models.

Edge Computing provides mobile and Internet-of-Things (IoT) app vendors with a new distributed computing paradigm which allows an app vendor to deploy its app at hired edge servers distributed near app users at the edge of the cloud. This way, app users can be allocated to hired edge servers nearby to minimize network latency and energy consumption. A cost-effective edge user allocation (EUA) requires maximum app users to be served with minimum overall system cost. Finding a centralized optimal solution to this EUA problem is NP-hard. Thus, we propose EUAGame, a game-theoretic approach that formulates the EUA problem as a potential game. We analyze the game and show that it admits a Nash equilibrium. Then, we design a novel decentralized algorithm for finding a Nash equilibrium in the game as a solution to the EUA problem. The performance of this algorithm is theoretically analyzed and experimentally evaluated. The results show that the EUA problem can be solved effectively and efficiently.

Accurate software defect prediction could help software practitioners allocate test resources to defect-prone modules effectively and efficiently. In the last decades, much effort has been devoted to build accurate defect prediction models, including developing quality defect predictors and modeling techniques. However, current widely used defect predictors such as code metrics and process metrics could not well describe how software modules change over the project evolution, which we believe is important for defect prediction. In order to deal with this problem, in this paper, we propose to use the Historical Version Sequence of Metrics (HVSM) in continuous software versions as defect predictors. Furthermore, we leverage Recurrent Neural Network (RNN), a popular modeling technique, to take HVSM as the input to build software prediction models. The experimental results show that, in most cases, the proposed HVSM-based RNN model has significantly better effort-aware ranking effectiveness than the commonly used baseline models.

Background. Recent years have seen an increasing interest in cross-project defect prediction (CPDP), which aims to apply defect prediction models built on source projects to a target project. Currently, a variety of (complex) CPDP models have been proposed with a promising prediction performance. Problem. Most, if not all, of the existing CPDP models are not compared against those simple module size models that are easy to implement and have shown a good performance in defect prediction in the literature. Objective. We aim to investigate how far we have really progressed in the journey by comparing the performance in defect prediction between the existing CPDP models and simple module size models. Method. We first use module size in the target project to build two simple defect prediction models, ManualDown and ManualUp, which do not require any training data from source projects. ManualDown considers a larger module as more defect-prone, while ManualUp considers a smaller module as more defect-prone. Then, we take the following measures to ensure a fair comparison on the performance in defect prediction between the existing CPDP models and the simple module size models: using the same publicly available data sets, using the same performance indicators, and using the prediction performance reported in the original cross-project defect prediction studies. Result. The simple module size models have a prediction performance comparable or even superior to most of the existing CPDP models in the literature, including many newly proposed models. Conclusion. The results caution us that, if the prediction performance is the goal, the real progress in CPDP is not being achieved as it might have been envisaged. We hence recommend that future studies should include ManualDown/ManualUp as the baseline models for comparison when developing new CPDP models to predict defects in a complete target project.

With the popularity of social network and the increasing number of Web Services, making individual service recommendation has been a hot research spot nowadays. In this paper, we present a service recommendation algorithm named as URPC-Rec (User Relationships & Preferences Clustering and Recommendation), which first clusters users based on their history behaviors such as the services they ever invoked, and then makes personalized recommendations for users considering both the clustering results and user basic information and relationships, such as gender, age, occupation, preference tags, etc. The case study indicates that URPC-Rec can effectively reduce the dimensionality of sparse matrix, and partially solve the cold-start problem of recommendation systems. The comprehensive experiment shows that URPC-Rec algorithm with user relationships and references has better recommending result than the one without user information and the collaborative filtering approach.