Periodontal pocket depth is a widely used biomarker for diagnosing risk of periodontal disease. However, pocket depth typically exhibits skewness and heavy-tailedness, and its relationship with clinical risk factors is often nonlinear. Motivated by periodontal studies, this paper develops a robust single-index modal regression framework for analyzing skewed and heavy-tailed data. Our method has the following novel features: (1) a flexible two-piece scale Student-$t$ error distribution that generalizes both normal and two-piece scale normal distributions; (2) a deep neural network with guaranteed monotonicity constraints to estimate the unknown single-index function; and (3) theoretical guarantees, including model identifiability and a universal approximation theorem. Our single-index model combines the flexibility of neural networks and the two-piece scale Student-$t$ distribution, delivering robust mode-based estimation that is resistant to outliers, while retaining clinical interpretability through parametric index coefficients. We demonstrate the performance of our method through simulation studies and an application to periodontal disease data from the HealthPartners Institute of Minnesota. The proposed methodology is implemented in the \textsf{R} package \href{https://doi.org/10.32614/CRAN.package.DNNSIM}{\textsc{DNNSIM}}.
Studies of hadron resonances and their properties are limited by the accuracy and consistency of measured datasets, which can originate from many different experiments. We have used Gaussian Processes (GP) to build interpolated datasets, including quantification of uncertainties, so that data from different sources can be used in model fitting without the need for arbitrary weighting. GPs predict values and uncertainties of observables at any kinematic point. Bayesian inference is used to optimise the hyperparameters of the GP model. We demonstrate that the GP successfully interpolates data with quantified uncertainties by comparison with generated pseudodata. We also show that this methodology can be used to investigate the consistency of data from different sources. GPs provide a robust, model-independent method for interpolating typical datasets used in hadron resonance studies, removing the limitations of arbitrary weighting in sparse datasets.
Backward stochastic differential equation (BSDE)-based deep learning methods provide an alternative to Physics-Informed Neural Networks (PINNs) for solving high-dimensional partial differential equations (PDEs), offering algorithmic advantages in settings such as stochastic optimal control, where the PDEs of interest are tied to an underlying dynamical system. However, existing BSDE-based solvers have empirically been shown to underperform relative to PINNs in the literature. In this paper, we identify the root cause of this performance gap as a discretization bias introduced by the standard Euler-Maruyama (EM) integration scheme applied to short-horizon self-consistency BSDE losses, which shifts the optimization landscape off target. We find that this bias cannot be satisfactorily addressed through finer step sizes or longer self-consistency horizons. To properly handle this issue, we propose a Stratonovich-based BSDE formulation, which we implement with stochastic Heun integration. We show that our proposed approach completely eliminates the bias issues faced by EM integration. Furthermore, our empirical results show that our Heun-based BSDE method consistently outperforms EM-based variants and achieves competitive results with PINNs across multiple high-dimensional benchmarks. Our findings highlight the critical role of integration schemes in BSDE-based PDE solvers, an algorithmic detail that has received little attention thus far in the literature.
Off-policy evaluation (OPE) and off-policy learning (OPL) for contextual bandit policies leverage historical data to evaluate and optimize a target policy. Most existing OPE/OPL methods--based on importance weighting or imputation--assume common support between the target and logging policies. When this assumption is violated, these methods typically require unstable extrapolation, truncation, or conservative strategies for individuals outside the common support assumption. However, such approaches can be inadequate in settings where explicit evaluation or optimization for such individuals is required. To address this issue, we propose DOLCE: Decomposing Off-policy evaluation/learning into Lagged and Current Effects, a novel estimator that leverages contextual information from multiple time points to decompose rewards into lagged and current effects. By incorporating both past and present contexts, DOLCE effectively handles individuals who violate the common support assumption. We show that the proposed estimator is unbiased under two assumptions--local correctness and conditional independence. Our experiments demonstrate that DOLCE achieves substantial improvements in OPE and OPL, particularly as the proportion of individuals outside the common support assumption increases.
Next Generation Reservoir Computing (NGRC) is a low-cost machine learning method for forecasting chaotic time series from data. However, ensuring the dynamical stability of NGRC models during autonomous prediction remains a challenge. In this work, we uncover a key connection between the numerical conditioning of the NGRC feature matrix -- formed by polynomial evaluations on time-delay coordinates -- and the long-term NGRC dynamics. Merging tools from numerical linear algebra and ergodic theory of dynamical systems, we systematically study how the feature matrix conditioning varies across hyperparameters. We demonstrate that the NGRC feature matrix tends to be ill-conditioned for short time lags and high-degree polynomials. Ill-conditioning amplifies sensitivity to training data perturbations, which can produce unstable NGRC dynamics. We evaluate the impact of different numerical algorithms (Cholesky, SVD, and LU) for solving the regularized least-squares problem.
Appropriate modelling of extreme skew surges is crucial, particularly for coastal risk management. Our study focuses on modelling extreme skew surges along the French Atlantic coast, with a particular emphasis on investigating the extremal dependence structure between stations. We employ the peak-over-threshold framework, where a multivariate extreme event is defined whenever at least one location records a large value, though not necessarily all stations simultaneously. A novel method for determining an appropriate level (threshold) above which observations can be classified as extreme is proposed. Two complementary approaches are explored. First, the multivariate generalized Pareto distribution is employed to model extremes, leveraging its properties to derive a generative model that predicts extreme skew surges at one station based on observed extremes at nearby stations. Second, a novel extreme regression framework is assessed for point predictions. This specific regression framework enables accurate point predictions using only the "angle" of input variables, i.e. input variables divided by their norms. The ultimate objective is to reconstruct historical skew surge time series at stations with limited data. This is achieved by integrating extreme skew surge data from stations with longer records, such as Brest and Saint-Nazaire, which provide over 150 years of observations.
Large quantities of social activity data, such as weekly web search volumes and the number of new infections with infectious diseases, reflect peoples' interests and activities. It is important to discover temporal patterns from such data and to forecast future activities accurately. However, modeling and forecasting social activity data streams is difficult because they are high-dimensional and composed of multiple time-varying dynamics such as trends, seasonality, and interest diffusion. In this paper, we propose D-Tracker, a method for continuously capturing time-varying temporal patterns within social activity tensor data streams and forecasting future activities. Our proposed method has the following properties: (a) Interpretable: it incorporates the partial differential equation into a tensor decomposition framework and captures time-varying temporal patterns such as trends, seasonality, and interest diffusion between locations in an interpretable manner; (b) Automatic: it has no hyperparameters and continuously models tensor data streams fully automatically; (c) Scalable: the computation time of D-Tracker is independent of the time series length. Experiments using web search volume data obtained from GoogleTrends, and COVID-19 infection data obtained from COVID-19 Open Data Repository show that our method can achieve higher forecasting accuracy in less computation time than existing methods while extracting the interest diffusion between locations. Our source code and datasets are available at {https://github.com/Higashiguchi-Shingo/D-Tracker.
With the recent development of new geometric and angular-radial frameworks for multivariate extremes, reliably simulating from angular variables in moderate-to-high dimensions is of increasing importance. Empirical approaches have the benefit of simplicity, and work reasonably well in low dimensions, but as the number of variables increases, they can lack the required flexibility and scalability. Classical parametric models for angular variables, such as the von Mises-Fisher (vMF) distribution, provide an alternative. Exploiting mixtures of vMF distributions increases their flexibility, but there are cases where even this is not sufficient to capture the intricate features that can arise in data. Owing to their flexibility, generative deep learning methods are able to capture complex data structures; they therefore have the potential to be useful in the simulation of angular variables. In this paper, we explore a range of deep learning approaches for this task, including generative adversarial networks, normalizing flows and flow matching. We assess their performance via a range of metrics and make comparisons to the more classical approach of using a mixture of vMF distributions. The methods are also applied to a metocean data set, demonstrating their applicability to real-world, complex data structures.
Evaluating synthetic tabular data is challenging, since they can differ from the real data in so many ways. There exist numerous metrics of synthetic data quality, ranging from statistical distances to predictive performance, often providing conflicting results. Moreover, they fail to explain or pinpoint the specific weaknesses in the synthetic data. To address this, we apply explainable AI (XAI) techniques to a binary detection classifier trained to distinguish real from synthetic data. While the classifier identifies distributional differences, XAI concepts such as feature importance and feature effects, analyzed through methods like permutation feature importance, partial dependence plots, Shapley values and counterfactual explanations, reveal why synthetic data are distinguishable, highlighting inconsistencies, unrealistic dependencies, or missing patterns. This interpretability increases transparency in synthetic data evaluation and provides deeper insights beyond conventional metrics, helping diagnose and improve synthetic data quality. We apply our approach to two tabular datasets and generative models, showing that it uncovers issues overlooked by standard evaluation techniques.
In this study, we focus on the analysis of financial data in a federated setting, wherein data is distributed across multiple clients or locations, and the raw data never leaves the local devices. Our primary focus is not only on the development of efficient learning frameworks (for protecting user data privacy) in the field of federated learning but also on the importance of designing models that are easier to interpret. In addition, we care about the robustness of the framework to outliers. To achieve these goals, we propose a robust federated logistic regression-based framework that strives to strike a balance between these goals. To verify the feasibility of our proposed framework, we carefully evaluate its performance not only on independently identically distributed (IID) data but also on non-IID data, especially in scenarios involving outliers. Extensive numerical results collected from multiple public datasets demonstrate that our proposed method can achieve comparable performance to those of classical centralized algorithms, such as Logistical Regression, Decision Tree, and K-Nearest Neighbors, in both binary and multi-class classification tasks.
We introduce CO2, an efficient algorithm to produce convexly-weighted coresets with respect to generic smooth divergences. By employing a functional Taylor expansion, we show a local equivalence between sufficiently regular losses and their second order approximations, reducing the coreset selection problem to maximum mean discrepancy minimization. We apply CO2 to the Sinkhorn divergence, providing a novel sampling procedure that requires poly-logarithmically many data points to match the approximation guarantees of random sampling. To show this, we additionally verify several new regularity properties for entropically regularized optimal transport of independent interest. Our approach leads to a new perspective linking coreset selection and kernel quadrature to classical statistical methods such as moment and score matching. We showcase this method with a practical application of subsampling image data, and highlight key directions to explore for improved algorithmic efficiency and theoretical guarantees.
In-context learning (ICL) has emerged as a powerful capability of large language models (LLMs), enabling them to perform new tasks based on a few provided examples without explicit fine-tuning. Despite their impressive adaptability, these models remain vulnerable to subtle adversarial perturbations and exhibit unpredictable behavior when faced with linguistic variations. Inspired by software testing principles, we introduce a software testing-inspired framework, called MMT4NL, for evaluating the trustworthiness of in-context learning by utilizing adversarial perturbations and software testing techniques. It includes diverse evaluation aspects of linguistic capabilities for testing the ICL capabilities of LLMs. MMT4NL is built around the idea of crafting metamorphic adversarial examples from a test set in order to quantify and pinpoint bugs in the designed prompts of ICL. Our philosophy is to treat any LLM as software and validate its functionalities just like testing the software. Finally, we demonstrate applications of MMT4NL on the sentiment analysis and question-answering tasks. Our experiments could reveal various linguistic bugs in state-of-the-art LLMs.
Bug reports contain the information developers need to triage and fix software bugs. However, unclear, incomplete, or ambiguous information may lead to delays and excessive manual effort spent on bug triage and resolution. In this paper, we explore whether Instruction fine-tuned Large Language Models (LLMs) can automatically transform casual, unstructured bug reports into high-quality, structured bug reports adhering to a standard template. We evaluate three open-source instruction-tuned LLMs (\emph{Qwen 2.5, Mistral, and Llama 3.2}) against ChatGPT-4o, measuring performance on established metrics such as CTQRS, ROUGE, METEOR, and SBERT. Our experiments show that fine-tuned Qwen 2.5 achieves a CTQRS score of \textbf{77%}, outperforming both fine-tuned Mistral (\textbf{71%}), Llama 3.2 (\textbf{63%}) and ChatGPT in 3-shot learning (\textbf{75%}). Further analysis reveals that Llama 3.2 shows higher accuracy of detecting missing fields particularly Expected Behavior and Actual Behavior, while Qwen 2.5 demonstrates superior performance in capturing Steps-to-Reproduce, with an F1 score of 76%. Additional testing of the models on other popular projects (e.g., Eclipse, GCC) demonstrates that our approach generalizes well, achieving up to \textbf{70%} CTQRS in unseen projects' bug reports. These findings highlight the potential of instruction fine-tuning in automating structured bug report generation, reducing manual effort for developers and streamlining the software maintenance process.
AI code generation tools have gained significant popularity among developers, who use them to assist in software development due to their capability to generate code. Existing studies mainly explored the quality, e.g., correctness and security, of AI-generated code, while in real-world software development, the prerequisite is to distinguish AI-generated code from human-written code, which emphasizes the need to explicitly declare AI-generated code by developers. To this end, this study intends to understand the ways developers use to self-declare AI-generated code and explore the reasons why developers choose to self-declare or not. We conducted a mixed-methods study consisting of two phases. In the first phase, we mined GitHub repositories and collected 613 instances of AI-generated code snippets. In the second phase, we conducted a follow-up industrial survey, which received 111 valid responses. Our research revealed the practices followed by developers to self-declare AI-generated code. Most practitioners (76.6%) always or sometimes self-declare AI-generated code. In contrast, other practitioners (23.4%) noted that they never self-declare AI-generated code. The reasons for self-declaring AI-generated code include the need to track and monitor the code for future review and debugging, and ethical considerations. The reasons for not self-declaring AI-generated code include extensive modifications to AI-generated code and the developers' perception that self-declaration is an unnecessary activity. We finally provided guidelines for practitioners to self-declare AI-generated code, addressing ethical and code quality concerns.
This study explores a novel approach to predicting key bug-related outcomes, including the time to resolution, time to fix, and ultimate status of a bug, using data from the Bugzilla Eclipse Project. Specifically, we leverage features available before a bug is resolved to enhance predictive accuracy. Our methodology incorporates sentiment analysis to derive both an emotionality score and a sentiment classification (positive or negative). Additionally, we integrate the bug's priority level and its topic, extracted using a BERTopic model, as features for a Convolutional Neural Network (CNN) and a Multilayer Perceptron (MLP). Our findings indicate that the combination of BERTopic and sentiment analysis can improve certain model performance metrics. Furthermore, we observe that balancing model inputs enhances practical applicability, albeit at the cost of a significant reduction in accuracy in most cases. To address our primary objectives, predicting time-to-resolution, time-to-fix, and bug destiny, we employ both binary classification and exact time value predictions, allowing for a comparative evaluation of their predictive effectiveness. Results demonstrate that sentiment analysis serves as a valuable predictor of a bug's eventual outcome, particularly in determining whether it will be fixed. However, its utility is less pronounced when classifying bugs into more complex or unconventional outcome categories.
Large open-source projects receive a large number of issues (known as bugs), including software defect (i.e., bug) reports and new feature requests from their user and developer communities at a fast rate. The often limited project resources do not allow them to deal with all issues. Instead, they have to prioritize them according to the project's priorities and the issues' severities. In this paper, we propose a novel approach to automated bug prioritization based on the natural language text of the bug reports that are stored in the open bug repositories of the issue-tracking systems. We conduct topic modeling using a variant of LDA called TopicMiner-MTM and text classification with the BERT large language model to achieve a higher performance level compared to the state-of-the-art. Experimental results using an existing reference dataset containing 85,156 bug reports of the Eclipse Platform project indicate that we outperform existing approaches in terms of Accuracy, Precision, Recall, and F1-measure of the bug report priority prediction.
This paper introduces a new optimisation algorithm, called Adaptive Bacterial Colony Optimisation (ABCO), modelled after the foraging behaviour of E. coli bacteria. The algorithm follows three stages--explore, exploit and reproduce--and is adaptable to meet the requirements of its applications. The performance of the proposed ABCO algorithm is compared to that of established optimisation algorithms--particle swarm optimisation (PSO) and ant colony optimisation (ACO)--on a set of benchmark functions. Experimental results demonstrate the benefits of the adaptive nature of the proposed algorithm: ABCO runs much faster than PSO and ACO while producing competitive results and outperforms PSO and ACO in a scenario where the running time is not crucial.
Design Rationale (DR) for software architecture decisions refers to the reasoning underlying architectural choices, which provides valuable insights into the different phases of the architecting process throughout software development. However, in practice, DR is often inadequately documented due to a lack of motivation and effort from developers. With the recent advancements in Large Language Models (LLMs), their capabilities in text comprehension, reasoning, and generation may enable the generation and recovery of DR for architecture decisions. In this study, we evaluated the performance of LLMs in generating DR for architecture decisions. First, we collected 50 Stack Overflow (SO) posts, 25 GitHub issues, and 25 GitHub discussions related to architecture decisions to construct a dataset of 100 architecture-related problems. Then, we selected five LLMs to generate DR for the architecture decisions with three prompting strategies, including zero-shot, chain of thought (CoT), and LLM-based agents. With the DR provided by human experts as ground truth, the Precision of LLM-generated DR with the three prompting strategies ranges from 0.267 to 0.278, Recall from 0.627 to 0.715, and F1-score from 0.351 to 0.389. Additionally, 64.45% to 69.42% of the arguments of DR not mentioned by human experts are also helpful, 4.12% to 4.87% of the arguments have uncertain correctness, and 1.59% to 3.24% of the arguments are potentially misleading. Based on the results, we further discussed the pros and cons of the three prompting strategies and the strengths and limitations of the DR generated by LLMs.
ReasonIR-8B는 일반적인 추론 작업에 특화된 최초의 검색기(리트리버)로, 기존의 검색기들이 추론 작업에서 제한된 성과를 보인 이유는 짧고 직설적인 사실 기반 쿼리와 문서에만 초점을 맞췄기 때문입니다. 이를 해결하기 위해, 합성 데이터 생성 파이프라인을 개발하여 각 문서에 도전적이고 관련성 높은 쿼리와 유사하지만 도움이 되지 않는 하드 네거티브를 생성하였으며, 이를 기존 공개 데이터와 혼합하여 학습시켰습니다. 그 결과, ReasonIR-8B는 BRIGHT 벤치마크에서 reranker 없이 29.9 nDCG@10, reranker와 함께 36.9 nDCG@10의 최고 성과를 달성하였으며, RAG( Retrieval-Augmented Generation) 작업에서 MMLU와 GPQA 성능을 각각 6.4%, 22.6% 향상시켰습니다. 또한, 테스트 시 더 길고 풍부한 쿼리와 결합할 때 성능이 지속적으로 향상되며, 오픈소스로 공개된 코드와 데이터는 향후 대형 언어모델(LLM) 확장에 유용하게 활용될 수 있습니다.
We present a novel benchmark for voice cloning text-to-speech models. The benchmark consists of an evaluation protocol, an open-source library for assessing the performance of voice cloning models, and an accompanying leaderboard. The paper discusses design considerations and presents a detailed description of the evaluation procedure. The usage of the software library is explained, along with the organization of results on the leaderboard.