Examples in web API specifications can be essential for API testing, API understanding, and even building chat-bots for APIs. Unfortunately, most API specifications lack human-written examples. This paper introduces a novel technique for generating examples for web API specifications. We start from in-context learning (Icl): given an API parameter, use a prompt context containing a few examples from other similar API parameters to call a model to generate new examples. However, while ICL tends to generate correct examples, those lack diversity, which is also important for most downstream tasks. Therefore, we extend the technique to iterated-calls ICL (IcIcl): use a few different prompt contexts, each containing a few examples, to iteratively call the model with each context. Our intrinsic evaluation demonstrates that IcIcl improves both correctness and diversity of generated examples. More importantly, our extrinsic evaluation demonstrates that those generated examples significantly improve the performance of downstream tasks of testing, understanding, and chat-bots for APIs.

Code generation models can help improve many common software tasks ranging from code completion to defect prediction. Most of the existing benchmarks for code generation LLMs focus on code authoring or code completion. Surprisingly, there has been far less effort dedicated to benchmarking software testing, despite the strong correlation between well-tested software and effective bug detection. To address this gap, we create and release TestGenEval, a large-scale benchmark to measure test generation performance. Based on SWEBench, TestGenEval comprises 68,647 tests from 1,210 code and test file pairs across 11 well-maintained Python repositories. It covers initial tests authoring, test suite completion, and code coverage improvements. Test authoring simulates the process of a developer writing a test suite from scratch, while test completion mimics the scenario where a developer aims to improve the coverage of an existing test suite. We evaluate several popular models, with sizes ranging from 7B to 405B parameters. Our detailed analysis highlights TestGenEval's contribution to a comprehensive evaluation of test generation performance. In particular, models struggle to generate high-coverage test suites, with the best model, GPT-4o, achieving an average coverage of only 35.2\%. This is primarily due to models struggling to reason about execution, and their frequent assertion errors when addressing complex code paths.

An "adequate" test suite should effectively find all inconsistencies between a system's requirements/specifications and its implementation. Practitioners frequently use code coverage to approximate adequacy, while academics argue that mutation score may better approximate true (oracular) adequacy coverage. High code coverage is increasingly attainable even on large systems via automatic test generation, including fuzzing. In light of all of these options for measuring and improving testing effort, how should a QA engineer spend their time? We propose a new framework for reasoning about the extent, limits, and nature of a given testing effort based on an idea we call the oracle gap, or the difference between source code coverage and mutation score for a given software element. We conduct (1) a large-scale observational study of the oracle gap across popular Maven projects, (2) a study that varies testing and oracle quality across several of those projects and (3) a small-scale observational study of highly critical, well-tested code across comparable blockchain projects. We show that the oracle gap surfaces important information about the extent and quality of a test effort beyond either adequacy metric alone. In particular, it provides a way for practitioners to identify source files where it is likely a weak oracle tests important code.

Testing is an integral but often neglected part of the software development process. Classical test generation tools such as EvoSuite generate behavioral test suites by optimizing for coverage, but tend to produce tests that are hard to understand. Language models trained on code can generate code that is highly similar to that written by humans, but current models are trained to generate each file separately, as is standard practice in natural language processing, and thus fail to consider the code-under-test context when producing a test file. In this work, we propose the Aligned Code And Tests Language Model (CAT-LM), a GPT-style language model with 2.7 Billion parameters, trained on a corpus of Python and Java projects. We utilize a novel pretraining signal that explicitly considers the mapping between code and test files when available. We also drastically increase the maximum sequence length of inputs to 8,192 tokens, 4x more than typical code generation models, to ensure that the code context is available to the model when generating test code. We analyze its usefulness for realistic applications, showing that sampling with filtering (e.g., by compilability, coverage) allows it to efficiently produce tests that achieve coverage similar to ones written by developers while resembling their writing style. By utilizing the code context, CAT-LM generates more valid tests than even much larger language models trained with more data (CodeGen 16B and StarCoder) and substantially outperforms a recent test-specific model (TeCo) at test completion. Overall, our work highlights the importance of incorporating software-specific insights when training language models for code and paves the way to more powerful automated test generation.

Mutation testing is a powerful technique for assessing and improving test suite quality that artificially introduces bugs and checks whether the test suites catch them. However, it is also computationally expensive and thus does not scale to large systems and projects. One promising recent approach to tackling this scalability problem uses machine learning to predict whether the tests will detect the synthetic bugs, without actually running those tests. However, existing predictive mutation testing approaches still misclassify 33% of detection outcomes on a randomly sampled set of mutant-test suite pairs. We introduce MutationBERT, an approach for predictive mutation testing that simultaneously encodes the source method mutation and test method, capturing key context in the input representation. Thanks to its higher precision, MutationBERT saves 33% of the time spent by a prior approach on checking/verifying live mutants. MutationBERT, also outperforms the state-of-the-art in both same project and cross project settings, with meaningful improvements in precision, recall, and F1 score. We validate our input representation, and aggregation approaches for lifting predictions from the test matrix level to the test suite level, finding similar improvements in performance. MutationBERT not only enhances the state-of-the-art in predictive mutation testing, but also presents practical benefits for real-world applications, both in saving developer time and finding hard to detect mutants that prior approaches do not.

Bounded-exhaustive testing (BET), which exercises a program under test for all inputs up to some bounds, is an effective method for detecting software bugs. Systematic property-based testing is a BET approach where developers write test generation programs that describe properties of test inputs. Hybrid test generation programs offer the most expressive way to write desired properties by freely combining declarative filters and imperative generators. However, exploring hybrid test generation programs, to obtain test inputs, is both computationally demanding and challenging to parallelize. We present the first programming and execution models, dubbed Tempo, for parallel exploration of hybrid test generation programs. We describe two different strategies for mapping the computation to parallel hardware and implement them both for GPUs and CPUs. We evaluated Tempo by generating instances of various data structures commonly used for benchmarking in the BET domain. Additionally, we generated CUDA programs to stress test CUDA compilers, finding four bugs confirmed by the developers.