Elizabeth Dinella

Ferida Mohammed, Fatma Ayad, Petros Maniatis et al.

Programmers are turning to AI coding assistants to answer questions about their code. Benchmarks are needed to soundly evaluate these systems and understand their performance. To enable such a study, we curate a benchmark of real-world contextualized questions derived from Github pull request comments. Out of this work, we present RubberDuckBench: a multilingual benchmark of questions about code, along with detailed rubrics for evaluating answers. We evaluate a diverse set of 20 LLMs (proprietary & open-source) on answering these questions. We find that even state of the art models fail to give consistent, correct responses across the benchmark. Grok 4 (69.29%), Claude Opus 4 (68.5%), and GPT-5 (67.8%) perform best overall, but do not exhibit pairwise significant superiority over the next 9 best performing models. Most models obtain points through partial credit, with the best performing models only answering at most 2 questions completely correctly across all trials. Furthermore, models often hallucinate with lies in 58.3\% of responses on average. Cost analysis reveals no correlation between expense (API pricing or parameter count) and performance. We intend this benchmark to be a target for future research in trustworthy and correct AI coding assistants.

Benedict Florance Arockiaraj, Elizabeth Dinella, Ankit Billa et al.

Counting objects in an image is a task applicable across many domains. For instance, crowd counting, inventory counting, and cell counting have been the focus of recent research. The major challenges in estimating the count of objects include overlapping objects, object scale issues, occlusions, and varying lighting conditions. In this report, we explore the problem of counting machine washer parts. Our technique is an extension of FamNet with an additional loss component, trained on the given dataset. We compare to three baseline methods: a traditional image processing pipeline, instance segmentation, and density map estimation. We evaluate the performance of these algorithms by computing the Mean Absolute Error (MAE) and the Root Mean Squared Error (RMSE) between the true object counts and the model outputs. Our approach achieves a performance of 1.96 MAE.

Elizabeth Dinella

This paper explores the effectiveness of modular randomized testing for object oriented programs in Java. Modular testing involves testing individual components of a program in isolation. Often times, for effective test generation, a series of non-target setup calls must be included to obtain high coverage of the target component. In this work, we evaluate and improve modular testing with the EvoSuite test generator. We find that due to strict restrictions that disallow calls to non-target setup methods, EvoSuite's modular testing mode is ineffective and often results in low branch coverage. We propose \textsc{emote} (Effective Modular Testing with EvoSuite): an enhancement to EvoSuite that relaxes this restriction, allowing non-target methods to be included in the test prefixes. This modification draws inspiration from developer-written fuzz drivers, which often invoke setup methods to properly initialize the state before testing the target method. To ensure meaningful test generation, we modify EvoSuite's fitness function to focus branch coverage contributions on the call chain originating from the target method. \textsc{emote} is evaluated on a subset of the SF100 benchmark, showing a 15.15\% improvement in coverage of the target methods.

Elizabeth Dinella, Gabriel Ryan, Todd Mytkowicz et al.

Testing is widely recognized as an important stage of the software development lifecycle. Effective software testing can provide benefits such as bug finding, preventing regressions, and documentation. In terms of documentation, unit tests express a unit's intended functionality, as conceived by the developer. A test oracle, typically expressed as an condition, documents the intended behavior of a unit under a given test prefix. Synthesizing a functional test oracle is a challenging problem, as it must capture the intended functionality rather than the implemented functionality. In this paper, we propose TOGA (a neural method for Test Oracle GenerAtion), a unified transformer-based neural approach to infer both exceptional and assertion test oracles based on the context of the focal method. Our approach can handle units with ambiguous or missing documentation, and even units with a missing implementation. We evaluate our approach on both oracle inference accuracy and functional bug-finding. Our technique improves accuracy by 33\% over existing oracle inference approaches, achieving 96\% overall accuracy on a held out test dataset. Furthermore, we show that when integrated with a automated test generation tool (EvoSuite), our approach finds 57 real world bugs in large-scale Java programs, including 30 bugs that are not found by any other automated testing method in our evaluation.

Alexey Svyatkovskiy, Sarah Fakhoury, Negar Ghorbani et al.

Collaborative software development is an integral part of the modern software development life cycle, essential to the success of large-scale software projects. When multiple developers make concurrent changes around the same lines of code, a merge conflict may occur. Such conflicts stall pull requests and continuous integration pipelines for hours to several days, seriously hurting developer productivity. To address this problem, we introduce MergeBERT, a novel neural program merge framework based on token-level three-way differencing and a transformer encoder model. By exploiting the restricted nature of merge conflict resolutions, we reformulate the task of generating the resolution sequence as a classification task over a set of primitive merge patterns extracted from real-world merge commit data. Our model achieves 63-68% accuracy for merge resolution synthesis, yielding nearly a 3x performance improvement over existing semi-structured, and 2x improvement over neural program merge tools. Finally, we demonstrate that MergeBERT is sufficiently flexible to work with source code files in Java, JavaScript, TypeScript, and C# programming languages. To measure the practical use of MergeBERT, we conduct a user study to evaluate MergeBERT suggestions with 25 developers from large OSS projects on 122 real-world conflicts they encountered. Results suggest that in practice, MergeBERT resolutions would be accepted at a higher rate than estimated by automatic metrics for precision and accuracy. Additionally, we use participant feedback to identify future avenues for improvement of MergeBERT.

Elizabeth Dinella, Todd Mytkowicz, Alexey Svyatkovskiy et al.

In collaborative software development, program merging is the mechanism to integrate changes from multiple programmers. Merge algorithms in modern version control systems report a conflict when changes interfere textually. Merge conflicts require manual intervention and frequently stall modern continuous integration pipelines. Prior work found that, although costly, a large majority of resolutions involve re-arranging text without writing any new code. Inspired by this observation we propose the first data-driven approach to resolve merge conflicts with a machine learning model. We realize our approach in a tool DeepMerge that uses a novel combination of (i) an edit-aware embedding of merge inputs and (ii) a variation of pointer networks, to construct resolutions from input segments. We also propose an algorithm to localize manual resolutions in a resolved file and employ it to curate a ground-truth dataset comprising 8,719 non-trivial resolutions in JavaScript programs. Our evaluation shows that, on a held out test set, DeepMerge can predict correct resolutions for 37% of non-trivial merges, compared to only 4% by a state-of-the-art semistructured merge technique. Furthermore, on the subset of merges with upto 3 lines (comprising 24% of the total dataset), DeepMerge can predict correct resolutions with 78% accuracy.