Search

Code completion is essential in software development, helping developers by predicting code snippets based on context. Among completion tasks, Method Body Completion (MBC) is particularly challenging as it involves generating complete method bodies based on their signatures and context. This task becomes significantly harder in large repositories, where method bodies must integrate repositoryspecific elements such as custom APIs, inter-module dependencies, and project-specific conventions. In this paper, we introduce RAMBO, a novel RAG-based approach for repository-level MBC. Instead of retrieving similar method bodies, RAMBO identifies essential repository-specific elements, such as classes, methods, and variables/fields, and their relevant usages. By incorporating these elements and their relevant usages into the code generation process, RAMBO ensures more accurate and contextually relevant method bodies. Our experimental results with leading code LLMs across 40 Java projects show that RAMBO significantly outperformed the state-of-the-art repository-level MBC approaches, with the improvements of up to 46% in BLEU, 57% in CodeBLEU, 36% in Compilation Rate, and up to 3X in Exact Match. Notably, RAMBO surpassed RepoCoder Oracle method by up to 12% in Exact Match, setting a new benchmark for repository-level MBC.

Large Language Models for Code (code LLMs) have demonstrated remarkable performance across various software engineering (SE) tasks, increasing the application of code LLMs in software development. Despite the success of code LLMs, there remain significant concerns about the actual capabilities and reliability of these models, "whether these models really learn the semantics of code from the training data and leverage the learned knowledge to perform the SE tasks". In this paper, we introduce EMPICA, a comprehensive framework designed to systematically and empirically evaluate the capabilities of code LLMs in understanding code semantics. Specifically, EMPICA systematically introduces controlled modifications/transformations into the input code and examines the models' responses. Generally, code LLMs must be robust to semantically equivalent code inputs and be sensitive to non-equivalent ones for all SE tasks. Specifically, for every SE task, given an input code snippet c and its semantic equivalent variants, code LLMs must robustly produce consistent/equivalent outputs while they are expected to generate different outputs for c and its semantic non-equivalent variants. Our experimental results on three representative code understanding tasks, including code summarization, method name prediction, and output prediction, reveal that the robustness and sensitivity of the state-of-the-art code LLMs to code transformations vary significantly across tasks and transformation operators. In addition, the code LLMs exhibit better robustness to the semantic preserving transformations than their sensitivity to the semantic non-preserving transformations. These results highlight a need to enhance the model's capabilities of understanding code semantics, especially the sensitivity property.

Software patches are pivotal in refining and evolving codebases, addressing bugs, vulnerabilities, and optimizations. Patch descriptions provide detailed accounts of changes, aiding comprehension and collaboration among developers. However, manual description creation poses challenges in terms of time consumption and variations in quality and detail. In this paper, we propose PATCHEXPLAINER, an approach that addresses these challenges by framing patch description generation as a machine translation task. In PATCHEXPLAINER, we leverage explicit representations of critical elements, historical context, and syntactic conventions. Moreover, the translation model in PATCHEXPLAINER is designed with an awareness of description similarity. Particularly, the model is explicitly trained to recognize and incorporate similarities present in patch descriptions clustered into groups, improving its ability to generate accurate and consistent descriptions across similar patches. The dual objectives maximize similarity and accurately predict affiliating groups. Our experimental results on a large dataset of real-world software patches show that PATCHEXPLAINER consistently outperforms existing methods, with improvements up to 189% in BLEU, 5.7X in Exact Match rate, and 154% in Semantic Similarity, affirming its effectiveness in generating software patch descriptions., Comment: Accepted for publication in Information and Software Technology

Multivariate time series classification is an important computational task arising in applications where data is recorded over time and over multiple channels. For example, a smartwatch can record the acceleration and orientation of a person's motion, and these signals are recorded as multivariate time series. We can classify this data to understand and predict human movement and various properties such as fitness levels. In many applications classification alone is not enough, we often need to classify but also understand what the model learns (e.g., why was a prediction given, based on what information in the data). The main focus of this paper is on analysing and evaluating explanation methods tailored to Multivariate Time Series Classification (MTSC). We focus on saliency-based explanation methods that can point out the most relevant channels and time series points for the classification decision. We analyse two popular and accurate multivariate time series classifiers, ROCKET and dResNet, as well as two popular explanation methods, SHAP and dCAM. We study these methods on 3 synthetic datasets and 2 real-world datasets and provide a quantitative and qualitative analysis of the explanations provided. We find that flattening the multivariate datasets by concatenating the channels works as well as using multivariate classifiers directly and adaptations of SHAP for MTSC work quite well. Additionally, we also find that the popular synthetic datasets we used are not suitable for time series analysis., Comment: Accepted at AALTD '23 (8th International Workshop on Advanced Analytics and Learning on Temporal Data, ECMLPKDD 2023)

Learning and remembering to use APIs are difficult. Several techniques have been proposed to assist developers in using APIs. Most existing techniques focus on recommending the right API methods to call, but very few techniques focus on recommending API arguments. In this paper, we propose ARIST, a novel automated argument recommendation approach which suggests arguments by predicting developers' expectations when they define and use API methods. To implement this idea in the recommendation process, ARIST combines program analysis (PA), language models (LMs), and several features specialized for the recommendation task which consider the functionality of formal parameters and the positional information of code elements (e.g., variables or method calls) in the given context. In ARIST, the LMs and the recommending features are used to suggest the promising candidates identified by PA. Meanwhile, PA navigates the LMs and the features working on the set of the valid candidates which satisfy syntax, accessibility, and type-compatibility constraints defined by the programming language in use. Our evaluation on a large dataset of real-world projects shows that ARIST improves the state-of-the-art approach by 19% and 18% in top-1 precision and recall for recommending arguments of frequently-used libraries. For general argument recommendation task, i.e., recommending arguments for every method call, ARIST outperforms the baseline approaches by up to 125% top-1 accuracy. Moreover, for newly-encountered projects, ARIST achieves more than 60% top-3 accuracy when evaluating on a larger dataset. For working/maintaining projects, with a personalized LM to capture developers' coding practice, ARIST can productively rank the expected arguments at the top-1 position in 7/10 requests.

Time series classification is a task which deals with temporal sequences, a prevalent data type common in domains such as human activity recognition, sports analytics and general sensing. In this area, interest in explainability has been growing as explanation is key to understand the data and the model better. Recently, a great variety of techniques have been proposed and adapted for time series to provide explanation in the form of saliency maps, where the importance of each data point in the time series is quantified with a numerical value. However, the saliency maps can and often disagree, so it is unclear which one to use. This paper provides a novel framework to quantitatively evaluate and rank explanation methods for time series classification. We show how to robustly evaluate the informativeness of a given explanation method (i.e., relevance for the classification task), and how to compare explanations side-by-side. The goal is to recommend the best explainer for a given time series classification dataset. We propose AMEE, a Model-Agnostic Explanation Evaluation framework, for recommending saliency-based explanations for time series classification. In this approach, data perturbation is added to the input time series guided by each explanation. Our results show that perturbing discriminative parts of the time series leads to significant changes in classification accuracy, which can be used to evaluate each explanation. To be robust to different types of perturbations and different types of classifiers, we aggregate the accuracy loss across perturbations and classifiers. This novel approach allows us to recommend the best explainer among a set of different explainers, including random and oracle explainers. We provide a quantitative and qualitative analysis for synthetic datasets, a variety of timeseries datasets, as well as a real-world case study with known expert ground truth., Comment: Accepted for publication in Data Mining and Knowledge Discovery

Attacks against computer systems exploiting software vulnerabilities can cause substantial damage to the cyber-infrastructure of our modern society and economy. To minimize the consequences, it is vital to detect and fix vulnerabilities as soon as possible. Just-in-time vulnerability detection (JIT-VD) discovers vulnerability-prone ("dangerous") commits to prevent them from being merged into source code and causing vulnerabilities. By JIT-VD, the commits' authors, who understand the commits properly, can review these dangerous commits and fix them if necessary while the relevant modifications are still fresh in their minds. In this paper, we propose CodeJIT, a novel code-centric learning-based approach for just-in-time vulnerability detection. The key idea of CodeJIT is that the meaning of the code changes of a commit is the direct and deciding factor for determining if the commit is dangerous for the code. Based on that idea, we design a novel graph-based representation to represent the semantics of code changes in terms of both code structures and program dependencies. A graph neural network model is developed to capture the meaning of the code changes represented by our graph-based representation and learn to discriminate between dangerous and safe commits. We conducted experiments to evaluate the JIT-VD performance of CodeJIT on a dataset of 20K+ dangerous and safe commits in 506 real-world projects from 1998 to 2022. Our results show that CodeJIT significantly improves the state-of-the-art JIT-VD methods by up to 66% in Recall, 136% in Precision, and 68% in F1. Moreover, CodeJIT correctly classifies nearly 9/10 of dangerous/safe (benign) commits and even detects 69 commits that fix a vulnerability yet produce other issues in source code

Static analysis tools are frequently used to detect potential vulnerabilities in software systems. However, an inevitable problem of these tools is their large number of warnings with a high false positive rate, which consumes time and effort for investigating. In this paper, we present DeFP, a novel method for ranking static analysis warnings. Based on the intuition that warnings which have similar contexts tend to have similar labels (true positive or false positive), DeFP is built with two BiLSTM models to capture the patterns associated with the contexts of labeled warnings. After that, for a set of new warnings, DeFP can calculate and rank them according to their likelihoods to be true positives (i.e., actual vulnerabilities). Our experimental results on a dataset of 10 real-world projects show that using DeFP, by investigating only 60% of the warnings, developers can find +90% of actual vulnerabilities. Moreover, DeFP improves the state-of-the-art approach 30% in both Precision and Recall., Comment: Published in Proceedings of the 28th Asia-Pacific Software Engineering Conference (APSEC'21)

Software fault localization is one of the most expensive, tedious, and time-consuming activities in program debugging. This activity becomes even much more challenging in Software Product Line (SPL) systems due to variability of failures. These unexpected behaviors are induced by variability faults which can only be exposed under some combinations of system features. The interaction among these features causes the failures of the system. Although localizing bugs in single-system engineering has been studied in-depth, variability fault localization in SPL systems still remains mostly unexplored. In this article, we present VarCop, a novel and effective variability fault localization approach. For an SPL system failed by variability bugs, VarCop isolates suspicious code statements by analyzing the overall test results of the sampled products and their source code. The isolated suspicious statements are the statements related to the interaction among the features which are necessary for the visibility of the bugs in the system. The suspiciousness of each isolated statement is assessed based on both the overall test results of the products containing the statement as well as the detailed results of the test cases executed by the statement in these products. On a large dataset of buggy SPL systems, empirical evaluation shows that VarCop significantly improves two state-of-the-art fault localization techniques by 33% and 50% in ranking the incorrect statements in the systems containing a single bug each. In about two-thirds of the cases, VarCop ranks the buggy statements at the top-3 positions in the resulting lists. For multiple-bug cases, VarCop outperforms the state-of-the-art approaches 2 times and 10 times in the proportion of bugs localized at the top-1 positions. In 22% and 65% of the buggy versions, VarCop correctly ranks at least one bug in a system at the top-1 and top-5 positions., Comment: Published in IEEE Transactions on Software Engineering (Early Access)

Software fault localization is one of the most expensive, tedious, and time-consuming activities in program debugging. This activity becomes even much more challenging in Software Product Line (SPL) systems due to the variability of failures in SPL systems. These unexpected behaviors are caused by variability faults which can only be exposed under some combinations of system features. Although localizing bugs in non-configurable code has been investigated in-depth, variability fault localization in SPL systems still remains mostly unexplored. To approach this challenge, we propose a benchmark for variability fault localization with a large set of 1,570 buggy versions of six SPL systems and baseline variability fault localization performance results. Our hope is to engage the community to propose new and better approaches to the problem of variability fault localization in SPL systems., Comment: Published in Proceedings of the 25th ACM International Systems and Software Product Line Conference - Volume A (SPLC '21)