METARO^(3):Metamorphic Relation Group for Automatic Program Repair

The application of metamorphic testing(MT)on automatic program repair(APR-MT)is used to generate a patch without test oracles by examining whether the input metamorphic relation(MR)is satisfied or not.However,the delivered patch is plausible since it may satisfy the input MR but violate other MRs.This inspires us to propose an improved approach to enhance the effectiveness of APR-MT with metamorphic relation group.Ourapproach involves three major steps.First,we formally define the repair process of APR-MT by building the model of automatic program repair and metamorphic testing separately.Then,we propose the advanced model of automatic program repair based on metamorphic relation group,named METARO^(3),which takes several MRs as input while only one MR is used in APR-MT.We additionally present two kinds of selection strategies to rank MRs in descending order of the fault detection capability,which helps shorten the repair time of finding a patch.To demonstrate the feasibility and procedure of our approach,an illustration example was conducted.The results show that METARO^(3) can improve the effectiveness of APR-MT significantly.

Automatic Algorithm Programming Model Based on the Improved Morgan's Refinement Calculus

The automatic algorithm programming model can increase the dependability and efficiency of algorithm program development,including specification generation,program refinement,and formal verification.However,the existing model has two flaws:incompleteness of program refinement and inadequate automation of formal verification.This paper proposes an automatic algorithm programming model based on the improved Morgan’s refinement calculus.It extends the Morgan’s refinement calculus rules and designs the C++generation system for realizing the complete process of refinement.Meanwhile,the automation tools VCG(Verification Condition Generator)and Isabelle are used to improve the automation of formal verification.An example of a stock’s maximum income demonstrates the effectiveness of the proposed model.Furthermore,the proposed model has some relevance for automatic software generation.

Multi-View Feature Fusion Model for Software Bug Repair Pattern Prediction

Many search-based Automatic Program Repair(APR)techniques employ a set of repair patterns to generate candidate patches.Regarding repair pattern selection,existing search-based APR techniques either randomly select a repair pattern from the repair pattern set to apply or prioritize all repair patterns based on the bug's context information.In this paper,we introduce PatternNet,a multi-view feature f usion model capable of predicting the repair pattern for a reported software bug.To accomplish this task,PatternNet first extracts multiview features from the pair of buggy code and bug report using different models.Specifically,a transformer-based model(i.e.,UniXcoder)is utilized to obtain the bimodal feature representation of the buggy code and bug report.Additionally,an Abstract Syntax Tree(AST)-based neural model(i.e.,ASTNN)is employed to learn the feature representation of the buggy code.Second,a co-attention mechanism is adopted to capture the dependencies between the statement trees in the AST of the buggy code and the textual tokens of the reported bug,resulting in co-attentive features between statement trees and reported bug's textual tokens.Finally,these multi-view features are combined i nto a unified representation using a feature fusion network.We quantitatively demonstrate the effectiveness of PatternNet and the feature fusion network for predicting software bug repair patterns.

Predicting Effectiveness of Generate-and-Validate Patch Generation Systems Using Random Forest

改进自动程序修理(4 月) 的有实行可能的一个方法技术是造能预言一个错误上的一种 4 月技术的一个应用程序是否是有效的预言模型。存在预言模型有一些限制。首先，预言模型被造，手精心制作通常没能捕获程序的语义特征的特征修理任务。第二，预言模型的表演仅仅在 Genprog 上被评估，一种基因编程的基于的 4 月技术。这份报纸开发预言模型，即，为 SPR 的随机的森林预言模型，另一种 generate--- 并且验证 4 月技术，它罐头把无效修理例子与有效修理例子区分开来。而非手工制作的特征，我们深信仰自动地学习的使用特征网络(DBN ) 预言当模特儿训练。实验结果表演与基线模型相比，也就是说所有有效模型，我们的建议模型能至少改进 F1 由 9% 并且 AUC (区域在下面操作特征曲线的接收装置) 在 19% 。同时，使用有学问的特征的预言模型至少在 11% 以 F1