ترغب بنشر مسار تعليمي؟ اضغط هنا

Measuring Coding Challenge Competence With APPS

104   0   0.0 ( 0 )
 نشر من قبل Dan Hendrycks
 تاريخ النشر 2021
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

While programming is one of the most broadly applicable skills in modern society, modern machine learning models still cannot code solutions to basic problems. Despite its importance, there has been surprisingly little work on evaluating code generation, and it can be difficult to accurately assess code generation performance rigorously. To meet this challenge, we introduce APPS, a benchmark for code generation. Unlike prior work in more restricted settings, our benchmark measures the ability of models to take an arbitrary natural language specification and generate satisfactory Python code. Similar to how companies assess candidate software developers, we then evaluate models by checking their generated code on test cases. Our benchmark includes 10,000 problems, which range from having simple one-line solutions to being substantial algorithmic challenges. We fine-tune large language models on both GitHub and our training set, and we find that the prevalence of syntax errors is decreasing exponentially as models improve. Recent models such as GPT-Neo can pass approximately 20% of the test cases of introductory problems, so we find that machine learning models are now beginning to learn how to code. As the social significance of automatic code generation increases over the coming years, our benchmark can provide an important measure for tracking advancements.



قيم البحث

اقرأ أيضاً

Automated unit test case generation tools facilitate test-driven development and support developers by suggesting tests intended to identify flaws in their code. Existing approaches are usually guided by the test coverage criteria, generating synthet ic test cases that are often difficult for developers to read or understand. In this paper we propose AthenaTest, an approach that aims to generate unit test cases by learning from real-world focal methods and developer-written testcases. We formulate unit test case generation as a sequence-to-sequence learning task, adopting a two-step training procedure consisting of denoising pretraining on a large unsupervised Java corpus, and supervised finetuning for a downstream translation task of generating unit tests. We investigate the impact of natural language and source code pretraining, as well as the focal context information surrounding the focal method. Both techniques provide improvements in terms of validation loss, with pretraining yielding 25% relative improvement and focal context providing additional 11.1% improvement. We also introduce Methods2Test, the largest publicly available supervised parallel corpus of unit test case methods and corresponding focal methods in Java, which comprises 780K test cases mined from 91K open-source repositories from GitHub. We evaluate AthenaTest on five defects4j projects, generating 25K passing test cases covering 43.7% of the focal methods with only 30 attempts. We execute the test cases, collect test coverage information, and compare them with test cases generated by EvoSuite and GPT-3, finding that our approach outperforms GPT-3 and has comparable coverage w.r.t. EvoSuite. Finally, we survey professional developers on their preference in terms of readability, understandability, and testing effectiveness of the generated tests, showing overwhelmingly preference towards AthenaTest.
127 - Jack Lanchantin , Ji Gao 2018
Statistical language models are powerful tools which have been used for many tasks within natural language processing. Recently, they have been used for other sequential data such as source code.(Ray et al., 2015) showed that it is possible train an n-gram source code language mode, and use it to predict buggy lines in code by determining unnatural lines via entropy with respect to the language model. In this work, we propose using a more advanced language modeling technique, Long Short-term Memory recurrent neural networks, to model source code and classify buggy lines based on entropy. We show that our method slightly outperforms an n-gram model in the buggy line classification task using AUC.
The process of developing a mobile application typically starts with the ideation and conceptualization of its user interface. This concept is then translated into a set of mock-ups to help determine how well the user interface embodies the intended features of the app. After the creation of mock-ups developers then translate it into an app that runs in a mobile device. In this paper we propose an approach, called GUIGLE, that aims to facilitate the process of conceptualizing the user interface of an app through GUI search. GUIGLE indexes GUI images and metadata extracted using automated dynamic analysis on a large corpus of apps extracted from Google Play. To perform a search, our approach uses information from text displayed on a screen, user interface components, the app name, and screen color palettes to retrieve relevant screens given a query. Furthermore, we provide a lightweight query language that allows for intuitive search of screens. We evaluate GUIGLE with real users and found that, on average, 68.8% of returned screens were relevant to the specified query. Additionally, users found the various different features of GUIGLE useful, indicating that our search engine provides an intuitive user experience. Finally, users agree that the information presented by GUIGLE is useful in conceptualizing the design of new screens for applications.
Mobile apps are now ubiquitous. Before developing a new app, the development team usually endeavors painstaking efforts to review many existing apps with similar purposes. The review process is crucial in the sense that it reduces market risks and pr ovides inspiration for app development. However, manual exploration of hundreds of existing apps by different roles (e.g., product manager, UI/UX designer, developer) in a development team can be ineffective. For example, it is difficult to completely explore all the functionalities of the app in a short period of time. Inspired by the conception of storyboard in movie production, we propose a system, StoryDroid, to automatically generate the storyboard for Android apps, and assist different roles to review apps efficiently. Specifically, StoryDroid extracts the activity transition graph and leverages static analysis techniques to render UI pages to visualize the storyboard with the rendered pages. The mapping relations between UI pages and the corresponding implementation code (e.g., layout code, activity code, and method hierarchy) are also provided to users. Our comprehensive experiments unveil that StoryDroid is effective and indeed useful to assist app development. The outputs of StoryDroid enable several potential applications, such as the recommendation of UI design and layout code.
Validation of Android apps via testing is difficult owing to the presence of flaky tests. Due to non-deterministic execution environments, a sequence of events (a test) may lead to success or failure in unpredictable ways. In this work, we present an approach and tool FlakeShovel for detecting flaky tests through systematic exploration of event orders. Our key observation is that for a test in a mobile app, there is a testing framework thread which creates the test events, a main User-Interface (UI) thread processing these events, and there may be several other background threads running asynchronously. For any event e whose execution involves potential non-determinism, we localize the earliest (latest) event after (before) which e must happen.We then efficiently explore the schedules between the upper/lower bound events while grouping events within a single statement, to find whether the test outcome is flaky. We also create a suite of subject programs called DroidFlaker to study flaky tests in Android apps. Our experiments on subject-suite DroidFlaker demonstrate the efficacy of our flaky test detection. Our work is complementary to existing flaky test detection tools like Deflaker which check only failing tests. FlakeShovel can detect flaky tests among passing tests, as shown by our approach and experiments.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا