Semantic code search, retrieving code that matches a given natural language query, is an important task to improve productivity in software engineering. Existing code search datasets face limitations: they rely on human annotators who assess code primarily through semantic understanding rather than functional verification, leading to potential inaccuracies and scalability issues. Additionally, current evaluation metrics often overlook the multichoice nature of code search. This paper introduces CoSQA+, pairing high-quality queries from CoSQA with multiple suitable codes. We develop an automated pipeline featuring multiple model-based candidate selections and the novel test-driven agent annotation system. Among a single Large Language Model (LLM) annotator and Python expert annotators (without test-based verification), agents leverage test-based verification and achieve the highest accuracy of 93.9%. Through extensive experiments, CoSQA+ has demonstrated superior quality over CoSQA. Models trained on CoSQA+ exhibit improved performance. We publicly release both CoSQA+-all, which contains 412,080 agent-annotated pairs, and CoSQA+-verified, which contains 1,000 human-verified pairs.

This paper proposes a new structural design to excite surface plasmonic polaritons to enhance the double‐ring interference structure. The double‐ring structure was etched into a thin film to form fundamental interference patterns, and periodic concentric‐ring grooves were employed to gather energy from the surrounding regions through the excitation of surface plasmonic polaritons. Accordingly, the energy of the incident light can be concentrated at the center. The surface plasmon modulates the interference pattern and the transmission spectra. The transmission peak position and its intensity can be tuned by changing the alignment of the grooves. The proposed structure can be applied for designing plasmonic devices as useful components of the plasmonic toolbox.

Sequence-to-sequence models provide a simple and elegant solution for building speech recognition systems by folding separate components of a typical system, namely acoustic (AM), pronunciation (PM) and language (LM) models into a single neural network. In this work, we look at one such sequence-to-sequence model, namely listen, attend and spell (LAS) [1], and explore the possibility of training a single model to serve different English dialects, which simplifies the process of training multi-dialect systems without the need for separate AM, PM and LMs for each dialect. We show that simply pooling the data from all dialects into one LAS model falls behind the performance of a model fine-tuned on each dialect. We then look at incorporating dialect-specific information into the model, both by modifying the training targets by inserting the dialect symbol at the end of the original grapheme sequence and also feeding a 1-hot representation of the dialect information into all layers of the model. Experimental results on seven English dialects show that our proposed system is effective in modeling dialect variations within a single LAS model, outperforming a LAS model trained individually on each of the seven dialects by 3.1~16.5% relative.

Bayesian network (BN) structure learning is an NP hard problem. Search and score algorithms are one of the main approaches proposed for learning BN structure from data. Previous research has shown that the relative performances of such algorithms are problem dependent and that fitness landscape analysis can be used to characterize the difficulty of the search for different scoring functions. In this paper, we construct a classifier based on fitness landscape analysis and receiver operating characteristic curves. The classifier labels search landscapes with the most suitable scoring function. We train the classifier on a number of standard benchmark functions. The classifier forms the basis for a selective hyperheuristic algorithm. This uses an initial landscape analysis stage to select a scoring function using the classifier. The hyperheuristic algorithm is tested on a distribution of unseen problems based on mutations of the standard benchmarks. Our results establish that the hyperheuristic performs better than a uniformly random scoring function selection approach that omit the landscape analysis stage. Therefore the effects on performance of problem-dependency can be significantly reduced.

Algorithms for learning the structure of Bayesian Networks (BN) from data are the focus of intense research interest. Search-and-score algorithms using nature-inspired metaheuristics are an important strand of this research; however performance is variable and strongly problem-dependent. In this paper we use fitness landscape analysis to explain empirically observed performance differences between particular search and-score algorithms on two well-studied benchmark problems. We investigate the average landscape discovered by random walks around optimal points in the space of BN node orderings. Differences in algorithm performance are explained in terms of these landscapes, which in turn are related to properties of the BN structures. These initial findings suggest that fitness landscape analysis is a promising approach for explaining existing empirical performance comparisons with further potential for understanding the relative difficulty of benchmark problems and the robustness of particular algorithms.

Learning Bayesian networks from data is an NP-hard problem with important practical applications. Several researchers have designed algorithms to overcome the computational complexity of this task. Difficult challenges remain however in reducing computation time for structure learning in networks of medium to large size and in understanding problem-dependent aspects of performance. In this paper, we present two novel algorithms (ChainACO and K2ACO) that use Ant Colony Optimization (ACO). Both algorithms search through the space of orderings of data variables. The ChainACO approach uses chain structures to reduce computational complexity of evaluation but at the expense of ignoring the richer structure that is explored in the K2ACO approach. The novel algorithms presented here are ACO versions of previously published GA approaches. We are therefore able to compare ACO vs GA algorithms and Chain vs K2 evaluations. We present a series of experiments on three well-known benchmark problems. Our results show problem-specific trade-offs between solution quality and computational effort. However it seems that the ACO-based approaches might be favored for larger problems, achieving better fitnesses and success rate than their GA counterparts on the largest network studied in our experiments.

In this paper we present an application of an Estimation of Distribution Algorithm (EDA) that uses a Markov network probabilistic model. The application is to the problem of bio-control in mushroom farming, a domain which admits bang-bang-control solutions. The problem is multi-objective and uses a weighted fitness function. Previous work on this problem has applied genetic algorithms (GA) with directed intervention crossover schemes aimed at effective biocontrol at an efficient level of intervention. Here we compare these approaches with the EDA Distribution Estimation Using Markov networks (DEUMd). DEUMdconstructs a probabilistic model using Markov networks. Our experiments compare the quality of solutions produced by DEUMd with the GA approaches and also reveal interesting differences in the search dynamics that have implications for algorithm design.

We explore the application of an Estimation of Distribution Algorithm which uses a Markov Network to the problem of bio-control in mushroom farming. This falls into the category of .bang-bang control. problems and was previously used as an application for genetic algorithms with modified crossover operators. The EDA yields a small improvement in the solutions that are evolved. Moreover, the probabilistic models constructed closely match identifiable features in the underlying dynamics of the problem. We conclude that this is a useful by-product of the probabilistic modelling which can be further exploited.