Nathan Cooper

David N. Palacio, Alejandro Velasco, Nathan Cooper et al.

Neural Language Models of Code, or Neural Code Models (NCMs), are rapidly progressing from research prototypes to commercial developer tools. As such, understanding the capabilities and limitations of such models is becoming critical. However, the abilities of these models are typically measured using automated metrics that often only reveal a portion of their real-world performance. While, in general, the performance of NCMs appears promising, currently much is unknown about how such models arrive at decisions. To this end, this paper introduces $do_{code}$, a post hoc interpretability method specific to NCMs that is capable of explaining model predictions. $do_{code}$ is based upon causal inference to enable programming language-oriented explanations. While the theoretical underpinnings of $do_{code}$ are extensible to exploring different model properties, we provide a concrete instantiation that aims to mitigate the impact of spurious correlations by grounding explanations of model behavior in properties of programming languages. To demonstrate the practical benefit of $do_{code}$, we illustrate the insights that our framework can provide by performing a case study on two popular deep learning architectures and ten NCMs. The results of this case study illustrate that our studied NCMs are sensitive to changes in code syntax. All our NCMs, except for the BERT-like model, statistically learn to predict tokens related to blocks of code (\eg brackets, parenthesis, semicolon) with less confounding bias as compared to other programming language constructs. These insights demonstrate the potential of $do_{code}$ as a useful method to detect and facilitate the elimination of confounding bias in NCMs.

Yanfu Yan, Nathan Cooper, Oscar Chaparro et al.

Video-based bug reports are increasingly being used to document bugs for programs centered around a graphical user interface (GUI). However, developing automated techniques to manage video-based reports is challenging as it requires identifying and understanding often nuanced visual patterns that capture key information about a reported bug. In this paper, we aim to overcome these challenges by advancing the bug report management task of duplicate detection for video-based reports. To this end, we introduce a new approach, called JANUS, that adapts the scene-learning capabilities of vision transformers to capture subtle visual and textual patterns that manifest on app UI screens - which is key to differentiating between similar screens for accurate duplicate report detection. JANUS also makes use of a video alignment technique capable of adaptive weighting of video frames to account for typical bug manifestation patterns. In a comprehensive evaluation on a benchmark containing 7,290 duplicate detection tasks derived from 270 video-based bug reports from 90 Android app bugs, the best configuration of our approach achieves an overall mRR/mAP of 89.8%/84.7%, and for the large majority of duplicate detection tasks, outperforms prior work by around 9% to a statistically significant degree. Finally, we qualitatively illustrate how the scene-learning capabilities provided by Janus benefits its performance.

Marco Bellagente, Jonathan Tow, Dakota Mahan et al.

We introduce StableLM 2 1.6B, the first in a new generation of our language model series. In this technical report, we present in detail the data and training procedure leading to the base and instruction-tuned versions of StableLM 2 1.6B. The weights for both models are available via Hugging Face for anyone to download and use. The report contains thorough evaluations of these models, including zero- and few-shot benchmarks, multilingual benchmarks, and the MT benchmark focusing on multi-turn dialogues. At the time of publishing this report, StableLM 2 1.6B was the state-of-the-art open model under 2B parameters by a significant margin. Given its appealing small size, we also provide throughput measurements on a number of edge devices. In addition, we open source several quantized checkpoints and provide their performance metrics compared to the original model.

Nikhil Pinnaparaju, Reshinth Adithyan, Duy Phung et al.

We introduce Stable Code, the first in our new-generation of code language models series, which serves as a general-purpose base code language model targeting code completion, reasoning, math, and other software engineering-based tasks. Additionally, we introduce an instruction variant named Stable Code Instruct that allows conversing with the model in a natural chat interface for performing question-answering and instruction-based tasks. In this technical report, we detail the data and training procedure leading to both models. Their weights are available via Hugging Face for anyone to download and use at https://huggingface.co/stabilityai/stable-code-3b and https://huggingface.co/stabilityai/stable-code-instruct-3b. This report contains thorough evaluations of the models, including multilingual programming benchmarks, and the MT benchmark focusing on multi-turn dialogues. At the time of its release, Stable Code is the state-of-the-art open model under 3B parameters and even performs comparably to larger models of sizes 7 billion and 15 billion parameters on the popular Multi-PL benchmark. Stable Code Instruct also exhibits state-of-the-art performance on the MT-Bench coding tasks and on Multi-PL completion compared to other instruction tuned models. Given its appealing small size, we also provide throughput measurements on a number of edge devices. In addition, we open source several quantized checkpoints and provide their performance metrics compared to the original model.

Amit Seal Ami, Scott Marsden, Kevin Moran et al.

The correct use of cryptography is central to ensuring data security in modern software systems. Hence, several academic and commercial static analysis tools have been developed for detecting and mitigating crypto-API misuse. While developers are optimistically adopting these crypto-API misuse detectors (or crypto-detectors) in their software development cycles, this momentum must be accompanied by a rigorous understanding of their effectiveness at finding crypto-API misuse in practice. This paper describes the MASC framework, which enables a systematic and data-driven evaluation of crypto-detectors using mutation testing. We ground MASC in a comprehensive view of the problem space by developing a data-driven taxonomy of existing crypto-API misuse, containing 107 misuse cases organized among nine semantic clusters. We develop 19 generalizable usage-based mutation operators and three mutation scopes that can expressively instantiate thousands of compilable variants of the misuse cases for thoroughly evaluating crypto-detectors. Using MASC, in a previous study, we evaluated nine major crypto-detectors and discovered 19 unique, undocumented flaws that severely impact the ability of crypto-detectors to discover misuses in practice. This paper substantially extends our MASC framework and offers updated evaluation of the crypto-detectors in our 2022 study, in addition to 5 more, major crypto-detectors. Through this work, we find 6 new, undocumented flaws, and demonstrate that these flaws affect the crypto-detectors regardless of their origin; open-source community, industry, and/or research. We conclude with a discussion on the diverse perspectives that influence the design of crypto-detectors and future directions towards building security-focused crypto-detectors by design.

Michael Pieler, Marco Bellagente, Hannah Teufel et al.

Recently published work on rephrasing natural text data for pre-training LLMs has shown promising results when combining the original dataset with the synthetically rephrased data. We build upon previous work by replicating existing results on C4 and extending them with our optimized rephrasing pipeline to the English, German, Italian, and Spanish Oscar subsets of CulturaX. Our pipeline leads to increased performance on standard evaluation benchmarks in both the mono- and multilingual setup. In addition, we provide a detailed study of our pipeline, investigating the choice of the base dataset and LLM for the rephrasing, as well as the relationship between the model size and the performance after pre-training. By exploring data with different perceived quality levels, we show that gains decrease with higher quality. Furthermore, we find the difference in performance between model families to be bigger than between different model sizes. This highlights the necessity for detailed tests before choosing an LLM to rephrase large amounts of data. Moreover, we investigate the effect of pre-training with synthetic data on supervised fine-tuning. Here, we find increasing but inconclusive results that highly depend on the used benchmark. These results (again) highlight the need for better benchmarking setups. In summary, we show that rephrasing multilingual and low-quality data is a very promising direction to extend LLM pre-training data.

Matteo Ciniselli, Nathan Cooper, Luca Pascarella et al.

Code completion aims at speeding up code writing by predicting the next code token(s) the developer is likely to write. Works in this field focused on improving the accuracy of the generated predictions, with substantial leaps forward made possible by deep learning (DL) models. However, code completion techniques are mostly evaluated in the scenario of predicting the next token to type, with few exceptions pushing the boundaries to the prediction of an entire code statement. Thus, little is known about the performance of state-of-the-art code completion approaches in more challenging scenarios in which, for example, an entire code block must be generated. We present a large-scale study exploring the capabilities of state-of-the-art Transformer-based models in supporting code completion at different granularity levels, including single tokens, one or multiple entire statements, up to entire code blocks (e.g., the iterated block of a for loop). We experimented with several variants of two recently proposed Transformer-based models, namely RoBERTa and the Text-To-Text Transfer Transformer (T5), for the task of code completion. The achieved results show that Transformer-based models, and in particular the T5, represent a viable solution for code completion, with perfect predictions ranging from ~29%, obtained when asking the model to guess entire blocks, up to ~69%, reached in the simpler scenario of few tokens masked from the same code statement.

Matteo Ciniselli, Nathan Cooper, Luca Pascarella et al.

Code completion is one of the main features of modern Integrated Development Environments (IDEs). Its objective is to speed up code writing by predicting the next code token(s) the developer is likely to write. Research in this area has substantially bolstered the predictive performance of these techniques. However, the support to developers is still limited to the prediction of the next few tokens to type. In this work, we take a step further in this direction by presenting a large-scale empirical study aimed at exploring the capabilities of state-of-the-art deep learning (DL) models in supporting code completion at different granularity levels, including single tokens, one or multiple entire statements, up to entire code blocks (e.g., the iterated block of a for loop). To this aim, we train and test several adapted variants of the recently proposed RoBERTa model, and evaluate its predictions from several perspectives, including: (i) metrics usually adopted when assessing DL generative models (i.e., BLEU score and Levenshtein distance); (ii) the percentage of perfect predictions (i.e., the predicted code snippets that match those written by developers); and (iii) the "semantic" equivalence of the generated code as compared to the one written by developers. The achieved results show that BERT models represent a viable solution for code completion, with perfect predictions ranging from ~7%, obtained when asking the model to guess entire blocks, up to ~58%, reached in the simpler scenario of few tokens masked from the same code statement.

Madeleine Havranek, Carlos Bernal-Cárdenas, Nathan Cooper et al.

Screen recordings are becoming increasingly important as rich software artifacts that inform mobile application development processes. However, the amount of manual effort required to extract information from these graphical artifacts can hinder resource-constrained mobile developers. This paper presents Video2Scenario (V2S), an automated tool that processes video recordings of Android app usages, utilizes neural object detection and image classification techniques to classify the depicted user actions, and translates these actions into a replayable scenario. We conducted a comprehensive evaluation to demonstrate V2S's ability to reproduce recorded scenarios across a range of devices and a diverse set of usage cases and applications. The results indicate that, based on its performance with 175 videos depicting 3,534 GUI-based actions, V2S is accurate in reproducing $\approx$89\% of actions from collected videos.

Antonio Mastropaolo, Simone Scalabrino, Nathan Cooper et al.

Deep learning (DL) techniques are gaining more and more attention in the software engineering community. They have been used to support several code-related tasks, such as automatic bug fixing and code comments generation. Recent studies in the Natural Language Processing (NLP) field have shown that the Text-To-Text Transfer Transformer (T5) architecture can achieve state-of-the-art performance for a variety of NLP tasks. The basic idea behind T5 is to first pre-train a model on a large and generic dataset using a self-supervised task ( e.g: filling masked words in sentences). Once the model is pre-trained, it is fine-tuned on smaller and specialized datasets, each one related to a specific task ( e.g: language translation, sentence classification). In this paper, we empirically investigate how the T5 model performs when pre-trained and fine-tuned to support code-related tasks. We pre-train a T5 model on a dataset composed of natural language English text and source code. Then, we fine-tune such a model by reusing datasets used in four previous works that used DL techniques to: (i) fix bugs, (ii) inject code mutants, (iii) generate assert statements, and (iv) generate code comments. We compared the performance of this single model with the results reported in the four original papers proposing DL-based solutions for those four tasks. We show that our T5 model, exploiting additional data for the self-supervised pre-training phase, can achieve performance improvements over the four baselines.

Nathan Cooper, Carlos Bernal-Cárdenas, Oscar Chaparro et al.

When a bug manifests in a user-facing application, it is likely to be exposed through the graphical user interface (GUI). Given the importance of visual information to the process of identifying and understanding such bugs, users are increasingly making use of screenshots and screen-recordings as a means to report issues to developers. However, when such information is reported en masse, such as during crowd-sourced testing, managing these artifacts can be a time-consuming process. As the reporting of screen-recordings in particular becomes more popular, developers are likely to face challenges related to manually identifying videos that depict duplicate bugs. Due to their graphical nature, screen-recordings present challenges for automated analysis that preclude the use of current duplicate bug report detection techniques. To overcome these challenges and aid developers in this task, this paper presents Tango, a duplicate detection technique that operates purely on video-based bug reports by leveraging both visual and textual information. Tango combines tailored computer vision techniques, optical character recognition, and text retrieval. We evaluated multiple configurations of Tango in a comprehensive empirical evaluation on 4,860 duplicate detection tasks that involved a total of 180 screen-recordings from six Android apps. Additionally, we conducted a user study investigating the effort required for developers to manually detect duplicate video-based bug reports and compared this to the effort required to use Tango. The results reveal that Tango's optimal configuration is highly effective at detecting duplicate video-based bug reports, accurately ranking target duplicate videos in the top-2 returned results in 83% of the tasks. Additionally, our user study shows that, on average, Tango can reduce developer effort by over 60%, illustrating its practicality.

Cody Watson, Nathan Cooper, David Nader Palacio et al.

An increasingly popular set of techniques adopted by software engineering (SE) researchers to automate development tasks are those rooted in the concept of Deep Learning (DL). The popularity of such techniques largely stems from their automated feature engineering capabilities, which aid in modeling software artifacts. However, due to the rapid pace at which DL techniques have been adopted, it is difficult to distill the current successes, failures, and opportunities of the current research landscape. In an effort to bring clarity to this crosscutting area of work, from its modern inception to the present, this paper presents a systematic literature review of research at the intersection of SE & DL. The review canvases work appearing in the most prominent SE and DL conferences and journals and spans 128 papers across 23 unique SE tasks. We center our analysis around the components of learning, a set of principles that govern the application of machine learning techniques (ML) to a given problem domain, discussing several aspects of the surveyed work at a granular level. The end result of our analysis is a research roadmap that both delineates the foundations of DL techniques applied to SE research, and highlights likely areas of fertile exploration for the future.