As the popularity of Internet of Things (IoT) platforms grows, users gain unprecedented control over their homes, health monitoring, and daily task automation. However, the testing of software for these platforms poses significant challenges due to their diverse composition, e.g., common smart home platforms are often composed of varied types of devices that use a diverse array of communication protocols, connections to mobile apps, cloud services, as well as integration among various platforms. This paper is the first to uncover both the practices and perceptions behind testing in IoT platforms, particularly open-source smart home platforms. Our study is composed of two key components. First, we mine and empirically analyze the code and integrations of two highly popular and well maintained open-source IoT platforms, OpenHAB and HomeAssistant. Our analysis involves the identification of functional and related test methods based on the focal method approach. We find that OpenHAB has only 0.04 test ratio (~ 4K focal test methods from ~ 76K functional methods) in Java files, while HomeAssistant exhibits higher test ratio of 0.42, which reveals a significant dearth of testing. Second, to understand the developers' perspective on testing in IoT, and to explain our empirical observations, we survey 80 open-source developers actively engaged in IoT platform development. Our analysis of survey responses reveals a significant focus on automated (unit) testing, and a lack of manual testing, which supports our empirical observations, as well as testing challenges specific to IoT. Together, our empirical analysis and survey yield 10 key findings that uncover the current state of testing in IoT platforms, and reveal key perceptions and challenges. These findings provide valuable guidance to the research community in navigating the complexities of effectively testing IoT platforms.

Large Language Models (LLMs), such as transformer-based neural networks trained on billions of parameters, have become increasingly prevalent in software engineering (SE). These models, trained on extensive datasets that include code repositories, exhibit remarkable capabilities for SE tasks. However, evaluating their effectiveness poses significant challenges, primarily due to the potential overlap between the datasets used for training and those employed for evaluation. To address this issue, we introduce SnipGen, a comprehensive repository mining framework designed to leverage prompt engineering across various downstream tasks for code generation. SnipGen aims to mitigate data contamination by generating robust testbeds and crafting tailored data points to assist researchers and practitioners in evaluating LLMs for code-related tasks. In our exploratory study, SnipGen mined approximately 227K data points from 338K recent code changes in GitHub commits, focusing on method-level granularity. SnipGen features a collection of prompt templates that can be combined to create a Chain-of-Thought-like sequence of prompts, enabling a nuanced assessment of LLMs’ code generation quality. By providing the mining tool, the methodology, and the dataset, SnipGen empowers researchers and practitioners to rigorously evaluate and interpret LLMs’ performance in software engineering contexts.

One of the most common solutions adopted by software researchers to address code generation is by training Large Language Models (LLMs) on massive amounts of source code. LLMs are rooted in the concept of emergent capabilities in which machines statistically learn complex patterns from code data. Although a number of studies have shown that LLMs have been effectively evaluated on popular accuracy metrics (e.g., BLEU, CodeBleu), previous research has largely overlooked the role of Causal Inference as a fundamental component of the interpretability of LLMs’ performance. Existing benchmarks and datasets are meant to highlight the difference between the expected and the generated outcome, but do not take into account confounding variables (e.g., lines of code, number of tokens, prompt size) that equally influence the accuracy metrics. The fact remains that, when dealing with generative software tasks by LLMs, no benchmark is available to tell researchers how to quantify neither the causal effect of SE-based treatments nor the correlation of confounders to the model’s performance. In an effort to bring statistical rigor to the evaluation of LLMs, this paper introduces a benchmarking strategy named Galeras comprised of curated testbeds for three SE tasks (i.e., code completion, code summarization, and commit generation) to help aid the interpretation of LLMs’ performance.We illustrate the insights of our benchmarking strategy by conducting a case study on the performance of ChatGPT under distinct prompt engineering methods. The results of the case study demonstrate the positive causal influence of prompt semantics on ChatGPT’s generative performance by an average treatment effect of ≈ 3%. Moreover, it was found that confounders such as prompt size are highly correlated with accuracy metrics (≈ 0.412). The end result of our case study is to showcase causal inference evaluations, in practice, to reduce confounding bias. By reducing the bias, we offer an interpretable solution for the accuracy metric under analysis.