Mattia Fazzini

Shiyang Li, Haoyang Chen, Mattia Fazzini et al.

Debugging CUDA programs has long been challenging because failures often arise from subtle interactions among hardware behavior, compiler decisions, memory hierarchy, and asynchronous execution. More importantly, with the rapid expansion of GPU usage across scientific computing, machine learning, graphics, and systems workloads, CUDA debugging has become more challenging than ever. Current evaluations of LLM-based CUDA programming largely miss this setting: a model can pass correctness tests with repair by degeneration, simplifying the CUDA code into a safer but slower program that abandons the original optimization structure. We introduce CUDABEAVER, a benchmark for CUDA debugging from real failing workspaces produced during LLM-based CUDA generation. Each task provides the broken candidate, native build/test commands, raw error evidence, and a single editable file. CUDABEAVER evaluates whether a fixer truly repairs the failing CUDA code or merely finds a slower test-passing replacement, reporting results by failure category, debugging trajectory, stagnation mode, and performance preservation. We further propose pass@k(M,C,A), a protocol-conditional CUDA debugging metric by making the fixer M, corpus C, and protocol axes Aexplicit. Using this metric across 213 tasks and seven frontier LLMs, we show that protocol-aware evaluation gives a more faithful view of CUDA debugging ability: when performance-loss tolerance is high, fixers appear much stronger, but even a minor stricter performance requirement can sharply reduce measured success, shifting scores by up to 40 percentage points.

Tyler Wendland, Jingyang Sun, Junayed Mahmud et al.

Software maintenance constitutes a large portion of the software development lifecycle. To carry out maintenance tasks, developers often need to understand and reproduce bug reports. As such, there has been increasing research activity coalescing around the notion of automating various activities related to bug reporting. A sizable portion of this research interest has focused on the domain of mobile apps. However, as research around mobile app bug reporting progresses, there is a clear need for a manually vetted and reproducible set of real-world bug reports that can serve as a benchmark for future work. This paper presents ANDROR2: a dataset of 90 manually reproduced bug reports for Android apps listed on Google Play and hosted on GitHub, systematically collected via an in-depth analysis of 459 reports extracted from the GitHub issue tracker. For each reproduced report, ANDROR2 includes the original bug report, an apk file for the buggy version of the app, an executable reproduction script, and metadata regarding the quality of the reproduction steps associated with the original report. We believe that the ANDROR2 dataset can be used to facilitate research in automatically analyzing, understanding, reproducing, localizing, and fixing bugs for mobile applications as well as other software maintenance activities more broadly.

Mattia Fazzini, Eduardo Noronha de A. Freitas, Shauvik Roy Choudhary et al.

Because Mobile apps are extremely popular and often mission critical nowadays, companies invest a great deal of resources in testing the apps they provide to their customers. Testing is particularly important for Android apps, which must run on a multitude of devices and operating system versions. Unfortunately, as we confirmed in many interviews with quality assurance professionals, app testing is today a very human intensive, and therefore tedious and error prone, activity. To address this problem, and better support testing of Android apps, we propose a new technique that allows testers to easily create platform independent test scripts for an app and automatically run the generated test scripts on multiple devices and operating system versions. The technique does so without modifying the app under test or the runtime system, by (1) intercepting the interactions of the tester with the app and (2) providing the tester with an intuitive way to specify expected results that it then encode as test oracles. We implemented our technique in a tool named Barista and used the tool to evaluate the practical usefulness and applicability of our approach. Our results show that Barista can faithfully encode user defined test cases as test scripts with built-in oracles, generates test scripts that can run on multiple platforms, and can outperform a state-of-the-art tool with similar functionality. Barista and our experimental infrastructure are publicly available.