Search

Software defects heavily affect software's functionalities and may cause huge losses. Recently, many AI-based approaches have been proposed to detect defects, which can be divided into two categories: software defect prediction and automatic unit test generation. While these approaches have made great progress in software defect detection, they still have several limitations in practical application, including the low confidence of prediction models and the inefficiency of unit testing models. To address these limitations, we propose a WYSIWYG (i.e., What You See Is What You Get) approach: Attention-based Self-guided Automatic Unit Test GenERation (AUGER), which contains two stages: defect detection and error triggering. In the former stage, AUGER first detects the proneness of defects. Then, in the latter stage, it guides to generate unit tests for triggering such an error with the help of critical information obtained by the former stage. To evaluate the effectiveness of AUGER, we conduct a large-scale experiment by comparing with the state-of-the-art (SOTA) approaches on the widely used datasets (i.e., Bears, Bugs.jar, and Defects4J). AUGER makes great improvements by 4.7% to 35.3% and 17.7% to 40.4% in terms of F1-score and Precision in defect detection, and can trigger 23 to 84 more errors than SOTAs in unit test generation. Besides, we also conduct a further study to verify the generalization in practical usage by collecting a new dataset from real-world projects., Comment: Accepted By ICSE'25

Large language models (LLMs), such as ChatGPT released by OpenAI, have attracted significant attention from both industry and academia due to their demonstrated ability to generate high-quality content for various tasks. Despite the impressive capabilities of LLMs, there are growing concerns regarding their potential risks in various fields, such as news, education, and software engineering. Recently, several commercial and open-source LLM-generated content detectors have been proposed, which, however, are primarily designed for detecting natural language content without considering the specific characteristics of program code. This paper aims to fill this gap by proposing a novel ChatGPT-generated code detector, CodeGPTSensor, based on a contrastive learning framework and a semantic encoder built with UniXcoder. To assess the effectiveness of CodeGPTSensor on differentiating ChatGPT-generated code from human-written code, we first curate a large-scale Human and Machine comparison Corpus (HMCorp), which includes 550K pairs of human-written and ChatGPT-generated code (i.e., 288K Python code pairs and 222K Java code pairs). Based on the HMCorp dataset, our qualitative and quantitative analysis of the characteristics of ChatGPT-generated code reveals the challenge and opportunity of distinguishing ChatGPT-generated code from human-written code with their representative features. Our experimental results indicate that CodeGPTSensor can effectively identify ChatGPT-generated code, outperforming all selected baselines., Comment: 30 pages, 6 figures, Accepted by TOSEM'24

In comparison to simpler data such as chemical formulas and lattice structures, electronic band structure data provide a more fundamental and intuitive insight into superconducting phenomena. In this work, we generate superconductor's lattice structure files optimized for density functional theory (DFT) calculations. Through DFT, we obtain electronic band superconductors, including band structures, density of states (DOS), and Fermi surface data. Additionally, we outline efficient methodologies for acquiring structure data, establish high-throughput DFT computational protocols, and introduce tools for extracting this data from large-scale DFT calculations. As an example, we have curated a dataset containing information on 2474 superconductors along with their experimentally determined superconducting transition temperatures, which is well-suited for machine learning applications. This work also provides guidelines for accessing and utilizing this dataset. Furthermore, we present a neural network model designed for training with this data. All the aforementioned data and code are publicly available at http://www.superband.work.

Energy band theory is a foundational framework in condensed matter physics. In this work, we employ a deep learning method, BNAS, to find a direct correlation between electronic band structure and superconducting transition temperature. Our findings suggest that electronic band structures can act as primary indicators of superconductivity. To avoid overfitting, we utilize a relatively simple deep learning neural network model, which, despite its simplicity, demonstrates predictive capabilities for superconducting properties. By leveraging the attention mechanism within deep learning, we are able to identify specific regions of the electronic band structure most correlated with superconductivity. This novel approach provides new insights into the mechanisms driving superconductivity from an alternative perspective. Moreover, we predict several potential superconductors that may serve as candidates for future experimental synthesis.

Large Language Models (LLMs) and pre-trained Language Models (LMs) have achieved impressive success on many software engineering tasks (e.g., code completion and code generation). By leveraging huge existing code corpora (e.g., GitHub), these models aim to understand the patterns in source code and use these patterns to predict code properties. However, fine-tuning LLMs is time-consuming and costly for end users and small organizations. Furthermore, fine-tuning LMs heavily depends on the amount and quality of datasets available. As a result, the current lack of data and the high cost of collecting it in real-world scenarios further limit the applicability of LMs. In this paper, we leverage the powerful generation capabilities of LLMs to enhance pre-trained LMs. Specifically, we use LLMs to generate domain-specific data, thereby improving the performance of pre-trained LMs on the target tasks. We conduct experiments by combining different LLMs in our generation phase and introducing various LMs to learn from the LLM-generated data. Then, we compare the performance of these LMs before and after learning the data. We find that LLM-generated data significantly enhances the performance of LMs. The improvement can reach up to 58.36% for fault localization and up to 6.09% for clone detection. Our study highlights that using LLMs to generate data for LMs can improve performance by a large margin.

Though many deep learning-based models have made great progress in vulnerability detection, we have no good understanding of these models, which limits the further advancement of model capability, understanding of the mechanism of model detection, and efficiency and safety of practical application of models. In this paper, we extensively and comprehensively investigate two types of state-of-the-art learning-based approaches (sequence-based and graph-based) by conducting experiments on a recently built large-scale dataset. We investigate seven research questions from five dimensions, namely model capabilities, model interpretation, model stability, ease of use of model, and model economy. We experimentally demonstrate the priority of sequence-based models and the limited abilities of both LLM (ChatGPT) and graph-based models. We explore the types of vulnerability that learning-based models skilled in and reveal the instability of the models though the input is subtlely semantical-equivalently changed. We empirically explain what the models have learned. We summarize the pre-processing as well as requirements for easily using the models. Finally, we initially induce the vital information for economically and safely practical usage of these models., Comment: 13 pages, 5 figures

Transition metal dichalcogenides (TMDs), exhibit a range of crystal structures and topological quantum states. The 1$T$ phase, in particular, shows promise for superconductivity driven by electron-phonon coupling, strain, pressure, and chemical doping. In this theoretical investigation, we explore 1$T$-RhSeTe as a novel type of TMD superconductor with topological electronic states. The optimal doping structure and atomic arrangement of 1$T$-RhSeTe are constructed. Phonon calculations validate the integrity of the constructed doping structure. The analysis of the electron-phonon coupling (EPC) using the Electron-phonon Wannier (EPW) method has confirmed the existence of a robust electron-phonon interaction in 1$T$-RhSeTe, resulting in total EPC constant $\lambda$ = 2.02, the logarithmic average frequency $\omega_{\text{log}}$ = 3.15 meV and $T_c$ = 4.61 K, consistent with experimental measurements and indicative of its classification as a BCS superconductor. The band structure analysis revealed the presence of Dirac-like band crossing points. The topological non-trivial electronic structures of the 1$T$-RhSeTe are confirmed via the evolution of Wannier charge centers (WCCs). Collectively, these distinctive properties underscore 1$T$-RhSeTe as a possible candidate for a topological superconductor, warranting further investigation into its potential implications and applications., Comment: 7 pages, 4 figures

Due to the hydrolytic instability of $LiPF_6$ in carbonate-based solvents, HF is a typical impurity in Li-ion battery electrolytes. HF significantly influences the performance of Li-ion batteries, for example by impacting the formation of the solid electrolyte interphase at the anode and by affecting transition metal dissolution at the cathode. Additionally, HF complicates studying fundamental interfacial electrochemistry of Li-ion battery electrolytes, such as direct anion reduction, because it is electrocatalytically relatively unstable, resulting in LiF passivation layers. Methods to selectively remove ppm levels of HF from $LiPF_6$-containing carbonate-based electrolytes are limited. We introduce and benchmark a simple yet efficient electrochemical in situ method to selectively remove ppm amounts of HF from $LiPF_6$-containing carbonate-based electrolytes. The basic idea is the application of a suitable potential to a high surface-area metallic electrode upon which only HF reacts (electrocatalytically) while all other electrolyte components are unaffected under the respective conditions., Comment: 31 pages, 19 figures

The peculiar defect-related photon emission processes in 2D hexagonal boron nitride (hBN) have become a topic of intense research due to their potential applications in quantum information and sensing technologies. Recent efforts have focused on activating and modulating the defect energy levels in hBN by methods that can be integrated on a chip, and understanding the underlying physical mechanism. Here, we report on exotic single photon and enhanced deep-level emissions in 2D hBN strain superlattice, which is fabricated by transferring multilayer hBN onto hexagonal close-packed silica spheres on silica substrate. We realize effective activation of the single photon emissions (SPEs) in the multilayer hBN at the positions that are in contact with the apex of the SiO2 spheres. At these points, the local tensile strain induced blue-shift of the SPE is found to be up to 12 nm. Furthermore, high spatial resolution cathodoluminescence measurments show remarkable strain-enhanced deep-level (DL) emissions in the multilayer hBN with the emission intensity distribution following the periodic hexagonal pattern of the strain superlattice. The maximum DL emission enhancement is up to 350% with a energy redshift of 6 nm. Our results provide a simple on-chip compatible method for activating and tuning the defect-related photon emissions in multilayer hBN, demonstrating the potential of hBN strain superlattice as a building block for future on-chip quantum nanophotonic devices.

We derive the Cardano formula of cubic equations by completing the cube, and provide radical solutions to some algebraic equations of higher degree by completing powers. The main idea of completing powers arises from Harrison's center theory of higher degree forms. A very simple criterion for such algebraic equations is presented, and the computation amounts to solving linear equations and quadratic equations., Comment: 11 pages. Minor revision. A new version with more details will be published in the American Mathematical Monthly

A math word problem (MWP) is a coherent narrative which reflects the underlying logic of math equations. Successful MWP generation can automate the writing of mathematics questions. Previous methods mainly generate MWP text based on inflexible pre-defined templates. In this paper, we propose a neural model for generating MWP text from math equations. Firstly, we incorporate a matching model conditioned on the domain knowledge to retrieve a MWP instance which is most consistent with the ground-truth, where the domain is a latent variable extracted with a domain summarizer. Secondly, by constructing a Quantity Cell Graph (QCG) from the retrieved MWP instance and reasoning over it, we improve the model's comprehension of real-world scenarios and derive a domain-constrained instance sketch to guide the generation. Besides, the QCG also interacts with the equation encoder to enhance the alignment between math tokens (e.g., quantities and variables) and MWP text. Experiments and empirical analysis on educational MWP set show that our model achieves impressive performance in both automatic evaluation metrics and human evaluation metrics.

The paper [Shi19] uses the Craig-Wayne-Bourgain method to construct solutions of an elliptic problem involving parameters. The results of [Shi19] include regularity assumptions on the perturbation and involve excluding parameters. The paper [Shi19] also constructs response solutions to a quasi-periodically perturbed (ill-posed evolution) problem. In this paper, we use several classical methods (freezing of coefficients, alternative methods for nonlinear elliptic equations) to extend the results of [Shi19]. We weaken the regularity assumptions on the perturbation and we describe the phenomena that happens for all parameters. In the ill-posed problem, we use a recently developed time-dependent center manifold theorem which allows to reduce the problem to a finite-dimensional ODE with quasi-periodic dependence on time. The bounded and sufficiently small solutions of these ODE give solutions of the ill-posed PDE., Comment: 34 pages