Stack Trace Deduplication: Faster, More Accurately, and in More Realistic Scenarios

In large-scale software systems, there are often no fully-fledged bug reports with human-written descriptions when an error occurs. In this case, developers rely on stack traces, i.e., series of function calls that led to the error. Since there can be tens and hundreds of thousands of them describing the same issue from different users, automatic deduplication into categories is necessary to allow for processing. Recent works have proposed powerful deep learning-based approaches for this, but they are evaluated and compared in isolation from real-life workflows, and it is not clear whether they will actually work well at scale. To overcome this gap, this work presents three main contributions: a novel model, an industry-based dataset, and a multi-faceted evaluation. Our model consists of two parts - (1) an embedding model with byte-pair encoding and approximate nearest neighbor search to quickly find the most relevant stack traces to the incoming one, and (2) a reranker that re-ranks the most fitting stack traces, taking into account the repeated frames between them. To complement the existing datasets collected from open-source projects, we share with the community SlowOps - a dataset of stack traces from IntelliJ-based products developed by JetBrains, which has an order of magnitude more stack traces per category. Finally, we carry out an evaluation that strives to be realistic: measuring not only the accuracy of categorization, but also the operation time and the ability to create new categories. The evaluation shows that our model strikes a good balance - it outperforms other models on both open-source datasets and SlowOps, while also being faster on time than most. We release all of our code and data, and hope that our work can pave the way to further practice-oriented research in the area.

Drawing Pandas: A Benchmark for LLMs in Generating Plotting Code

This paper introduces the human-curated PandasPlotBench dataset, designed to evaluate language models' effectiveness as assistants in visual data exploration. Our benchmark focuses on generating code for visualizing tabular data - such as a Pandas DataFrame - based on natural language instructions, complementing current evaluation tools and expanding their scope. The dataset includes 175 unique tasks. Our experiments assess several leading Large Language Models (LLMs) across three visualization libraries: Matplotlib, Seaborn, and Plotly. We show that the shortening of tasks has a minimal effect on plotting capabilities, allowing for the user interface that accommodates concise user input without sacrificing functionality or accuracy. Another of our findings reveals that while LLMs perform well with popular libraries like Matplotlib and Seaborn, challenges persist with Plotly, highlighting areas for improvement. We hope that the modular design of our benchmark will broaden the current studies on generating visualizations. Our benchmark is available online: https://huggingface.co/datasets/JetBrains-Research/plot_bench. The code for running the benchmark is also available: https://github.com/JetBrains-Research/PandasPlotBench.

Towards Realistic Evaluation of Commit Message Generation by Matching Online and Offline Settings

Commit message generation (CMG) is a crucial task in software engineering that is challenging to evaluate correctly. When a CMG system is integrated into the IDEs and other products at JetBrains, we perform online evaluation based on user acceptance of the generated messages. However, performing online experiments with every change to a CMG system is troublesome, as each iteration affects users and requires time to collect enough statistics. On the other hand, offline evaluation, a prevalent approach in the research literature, facilitates fast experiments but employs automatic metrics that are not guaranteed to represent the preferences of real users. In this work, we describe a novel way we employed to deal with this problem at JetBrains, by leveraging an online metric - the number of edits users introduce before committing the generated messages to the VCS - to select metrics for offline experiments. To support this new type of evaluation, we develop a novel markup collection tool mimicking the real workflow with a CMG system, collect a dataset with 57 pairs consisting of commit messages generated by GPT-4 and their counterparts edited by human experts, and design and verify a way to synthetically extend such a dataset. Then, we use the final dataset of 656 pairs to study how the widely used similarity metrics correlate with the online metric reflecting the real users' experience. Our results indicate that edit distance exhibits the highest correlation, whereas commonly used similarity metrics such as BLEU and METEOR demonstrate low correlation. This contradicts the previous studies on similarity metrics for CMG, suggesting that user interactions with a CMG system in real-world settings differ significantly from the responses by human labelers operating within controlled research environments. We release all the code and the dataset for researchers: https://jb.gg/cmg-evaluation.

One Step at a Time: Combining LLMs and Static Analysis to Generate Next-Step Hints for Programming Tasks

Students often struggle with solving programming problems when learning to code, especially when they have to do it online, with one of the most common disadvantages of working online being the lack of personalized help. This help can be provided as next-step hint generation, i.e., showing a student what specific small step they need to do next to get to the correct solution. There are many ways to generate such hints, with large language models (LLMs) being among the most actively studied right now. While LLMs constitute a promising technology for providing personalized help, combining them with other techniques, such as static analysis, can significantly improve the output quality. In this work, we utilize this idea and propose a novel system to provide both textual and code hints for programming tasks. The pipeline of the proposed approach uses a chain-of-thought prompting technique and consists of three distinct steps: (1) generating subgoals - a list of actions to proceed with the task from the current student's solution, (2) generating the code to achieve the next subgoal, and (3) generating the text to describe this needed action. During the second step, we apply static analysis to the generated code to control its size and quality. The tool is implemented as a modification to the open-source JetBrains Academy plugin, supporting students in their in-IDE courses. To evaluate our approach, we propose a list of criteria for all steps in our pipeline and conduct two rounds of expert validation. Finally, we evaluate the next-step hints in a classroom with 14 students from two universities. Our results show that both forms of the hints - textual and code - were helpful for the students, and the proposed system helped them to proceed with the coding tasks.

Long Code Arena: a Set of Benchmarks for Long-Context Code Models

Nowadays, the fields of code and natural language processing are evolving rapidly. In particular, models become better at processing long context windows - supported context sizes have increased by orders of magnitude over the last few years. However, there is a shortage of benchmarks for code processing that go beyond a single file of context, while the most popular ones are limited to a single method. With this work, we aim to close this gap by introducing Long Code Arena, a suite of six benchmarks for code processing tasks that require project-wide context. These tasks cover different aspects of code processing: library-based code generation, CI builds repair, project-level code completion, commit message generation, bug localization, and module summarization. For each task, we provide a manually verified dataset for testing, an evaluation suite, and open-source baseline solutions based on popular LLMs to showcase the usage of the dataset and to simplify adoption by other researchers. We publish the benchmark page on HuggingFace Spaces with the leaderboard, links to HuggingFace Hub for all the datasets, and link to the GitHub repository with baselines: https://huggingface.co/spaces/JetBrains-Research/long-code-arena.

Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forward

The last several years saw the emergence of AI assistants for code -- multi-purpose AI-based helpers in software engineering. Their quick development makes it necessary to better understand how specifically developers are using them, why they are not using them in certain parts of their development workflow, and what needs to be improved. In this work, we carried out a large-scale survey aimed at how AI assistants are used, focusing on specific software development activities and stages. We collected opinions of 481 programmers on five broad activities: (a) implementing new features, (b) writing tests, (c) bug triaging, (d) refactoring, and (e) writing natural-language artifacts, as well as their individual stages. Our results show that usage of AI assistants varies depending on activity and stage. For instance, developers find writing tests and natural-language artifacts to be the least enjoyable activities and want to delegate them the most, currently using AI assistants to generate tests and test data, as well as generating comments and docstrings most of all. This can be a good focus for features aimed to help developers right now. As for why developers do not use assistants, in addition to general things like trust and company policies, there are fixable issues that can serve as a guide for further research, e.g., the lack of project-size context, and lack of awareness about assistants. We believe that our comprehensive and specific results are especially needed now to steer active research toward where users actually need AI assistants.

Full Line Code Completion: Bringing AI to Desktop

In recent years, several industrial solutions for the problem of multi-token code completion have appeared, each making a great advance in the area but mostly focusing on cloud-based runtime and avoiding working on the end user's device. In this work, we describe our approach for building a multi-token code completion feature for the JetBrains' IntelliJ Platform, which we call Full Line Code Completion. The feature suggests only syntactically correct code and works fully locally, i.e., data querying and the generation of suggestions happens on the end user's machine. We share important time and memory-consumption restrictions, as well as design principles that a code completion engine should satisfy. Working entirely on the end user's device, our code completion engine enriches user experience while being not only fast and compact but also secure. We share a number of useful techniques to meet the stated development constraints and also describe offline and online evaluation pipelines that allowed us to make better decisions. Our online evaluation shows that the usage of the tool leads to 1.5 times more code in the IDE being produced by code completion. The described solution was initially started with the help of researchers and was bundled into two JetBrains' IDEs - PyCharm Pro and DataSpell - at the end of 2023, so we believe that this work is useful for bridging academia and industry, providing researchers with the knowledge of what happens when complex research-based solutions are integrated into real products.

From Commit Message Generation to History-Aware Commit Message Completion

Commit messages are crucial to software development, allowing developers to track changes and collaborate effectively. Despite their utility, most commit messages lack important information since writing high-quality commit messages is tedious and time-consuming. The active research on commit message generation (CMG) has not yet led to wide adoption in practice. We argue that if we could shift the focus from commit message generation to commit message completion and use previous commit history as additional context, we could significantly improve the quality and the personal nature of the resulting commit messages. In this paper, we propose and evaluate both of these novel ideas. Since the existing datasets lack historical data, we collect and share a novel dataset called CommitChronicle, containing 10.7M commits across 20 programming languages. We use this dataset to evaluate the completion setting and the usefulness of the historical context for state-of-the-art CMG models and GPT-3.5-turbo. Our results show that in some contexts, commit message completion shows better results than generation, and that while in general GPT-3.5-turbo performs worse, it shows potential for long and detailed messages. As for the history, the results show that historical information improves the performance of CMG models in the generation task, and the performance of GPT-3.5-turbo in both generation and completion.

All You Need Is Logs: Improving Code Completion by Learning from Anonymous IDE Usage Logs

Integrated Development Environments (IDE) are designed to make users more productive, as well as to make their work more comfortable. To achieve this, a lot of diverse tools are embedded into IDEs, and the developers of IDEs can employ anonymous usage logs to collect the data about how they are being used to improve them. A particularly important component that this can be applied to is code completion, since improving code completion using statistical learning techniques is a well-established research area. In this work, we propose an approach for collecting completion usage logs from the users in an IDE and using them to train a machine learning based model for ranking completion candidates. We developed a set of features that describe completion candidates and their context, and deployed their anonymized collection in the Early Access Program of IntelliJ-based IDEs. We used the logs to collect a dataset of code completions from users, and employed it to train a ranking CatBoost model. Then, we evaluated it in two settings: on a held-out set of the collected completions and in a separate A/B test on two different groups of users in the IDE. Our evaluation shows that using a simple ranking model trained on the past user behavior logs significantly improved code completion experience. Compared to the default heuristics-based ranking, our model demonstrated a decrease in the number of typing actions necessary to perform the completion in the IDE from 2.073 to 1.832. The approach adheres to privacy requirements and legal constraints, since it does not require collecting personal information, performing all the necessary anonymization on the client's side. Importantly, it can be improved continuously: implementing new features, collecting new data, and evaluating new models - this way, we have been using it in production since the end of 2020.

DapStep: Deep Assignee Prediction for Stack Trace Error rePresentation

The task of finding the best developer to fix a bug is called bug triage. Most of the existing approaches consider the bug triage task as a classification problem, however, classification is not appropriate when the sets of classes change over time (as developers often do in a project). Furthermore, to the best of our knowledge, all the existing models use textual sources of information, i.e., bug descriptions, which are not always available. In this work, we explore the applicability of existing solutions for the bug triage problem when stack traces are used as the main data source of bug reports. Additionally, we reformulate this task as a ranking problem and propose new deep learning models to solve it. The models are based on a bidirectional recurrent neural network with attention and on a convolutional neural network, with the weights of the models optimized using a ranking loss function. To improve the quality of ranking, we propose using additional information from version control system annotations. Two approaches are proposed for extracting features from annotations: manual and using an additional neural network. To evaluate our models, we collected two datasets of real-world stack traces. Our experiments show that the proposed models outperform existing models adapted to handle stack traces. To facilitate further research in this area, we publish the source code of our models and one of the collected datasets.