r

This study investigates the human–computer interaction (HCI) principles underlying Tidyverse’s widely adopted interface design, specifically for data wrangling and visualization tasks. Adopting a mixed-methods approach—integrating empirical user behavior observation, usability evaluation, and functional coverage analysis—we propose an iterative design framework grounded in three pillars: user feedback integration, domain-wide functional coverage, and explicit visibility of system constraints—balancing user-centered and work-domain-oriented design. Key usability-enhancing design elements are identified, including syntactic consistency, progressive disclosure of complexity, and explicit error messaging. The findings elucidate the HCI foundations of Tidyverse’s success and distill a reusable design paradigm for R package development. This work provides both theoretical grounding and practical guidelines for designers and developers of data science tools.

Despite the growing adoption of pre-trained code language models (Code-PLMs), their capabilities on the R programming language—particularly under its dual-paradigm ecosystem (Tidyverse vs. Base R)—remain systematically unexplored. Method: We introduce the first open-source, style-annotated R code dataset and conduct a comprehensive empirical study across four axes: cross-paradigm evaluation, cross-project generalization, multilingual fine-tuning ablation, and human evaluation—focusing on code summarization and method name prediction. Contribution/Results: (1) Syntax paradigm significantly impacts model performance, especially degrading summarization quality; (2) R-specific contextual dependencies severely hinder cross-project transfer; (3) Generic multilingual fine-tuning does not consistently improve R-specific task performance; (4) All evaluated Code-PLMs exhibit performance degradation on R tasks, corroborated by human assessment indicating low-quality generated summaries. This work establishes the first benchmark, dataset, and empirical foundation for R-oriented code intelligence research.

Addressing challenges in FAIR principle implementation—including fragmented data and code lifecycles, lack of executable environments, and high technical barriers—this study proposes a unified open-science platform. The platform uniquely integrates version control, containerized computational environments, and modular project scaffolding to support end-to-end reproducible research, from grant proposal to publication. It interoperates with mainstream scientific toolchains, supports deployment on both local workstations and institutional servers, and provides a lightweight graphical user interface. Empirical validation demonstrates successful re-execution of over a dozen interdisciplinary studies published more than ten years ago, confirming the platform’s robust long-term reproducibility, cross-platform compatibility, and seamless execution across diverse domains. By significantly lowering technical adoption barriers for researchers, the platform enables practical integration of FAIR principles and reproducibility practices into routine scientific workflows.

To address performance bottlenecks and poor memory efficiency in complex statistical computing and data transformation within R, this paper introduces a high-performance R infrastructure built upon a C/C++ backend engine. The method employs a novel class-agnostic design paradigm, featuring deep optimization of the R API, extension of the S3/S4 generic systems, integration of memory-pool management, and support for parallel vectorized operations. It delivers unified, efficient handling of core R data structures—including vectors, matrices, and data.frames—as well as widely adopted ecosystem extensions (e.g., tibble, data.table, sf). Benchmarking against base R and popular packages such as dplyr demonstrates speedups ranging from several-fold to over an order of magnitude on typical data manipulation tasks, alongside substantial reductions in memory footprint. The infrastructure achieves a balanced trade-off among high performance, broad compatibility, and seamless integration with the R ecosystem.

Novice learners often struggle with foundational data wrangling concepts and face significant barriers in programming initiation. Method: This study introduces an embodied pedagogy using Mathlink® cubes as tangible manipulatives to scaffold hands-on tasks—such as filtering, selecting, and transforming data—thereby bridging concrete physical actions to abstract computational thinking; instruction then transitions systematically to implementing equivalent operations in R’s dplyr package. Contribution/Results: To our knowledge, this is the first application of physical building blocks in data wrangling education, operationalized through task-based, experiential learning (“learning by doing”). Empirical evaluation demonstrates statistically significant improvements in students’ conceptual accuracy and cross-context transferability for core operations (e.g., filter, select, mutate), alongside higher coding initiation efficiency and superior long-term concept retention compared to purely digital instruction. The approach enhances both accessibility and conceptual depth in data literacy education.

This work addresses the challenges of poor readability, reproducibility, and maintainability in R scripts, which are exacerbated by the lack of effective tooling. To tackle this, the authors propose flowR, a plugin integrated into Positron and VS Code that innovatively combines incremental interprocedural data-flow and control-flow analysis to construct a unified data-flow graph accommodating R’s dynamic semantics. The system offers interactive visualization, static backward program slicing, inline value annotations, and linting capabilities, all built upon a modular, extensible architecture. Experimental results demonstrate that flowR constructs complete data-flow graphs in an average of 576 milliseconds, enabling near real-time feedback and substantially enhancing script understandability and maintainability.

This study addresses the limitations of traditional residual plot diagnostics—namely, their reliance on subjective human interpretation, low efficiency, and poor scalability—by introducing computer vision techniques for the first time to automate the assessment of residual plots in linear models. The authors develop the R package autovi and an accompanying Shiny-based interactive web application, autovi.web. Their approach leverages deep visual models to quantify the strength of structural signals in residual plots and produces interpretable diagnostic metrics. This methodology significantly enhances the consistency and efficiency of model fit evaluation, offering statisticians and data analysts a robust, objective, and scalable tool for automated diagnostic assessment in statistical modeling.

This work addresses the challenge of highly manual and non-generalizable environment configuration in repository-level software engineering tasks by introducing RAT, the first language-agnostic framework for fully automated repository setup. RAT establishes an end-to-end pipeline comprising semantic initialization, task planning, invocation of specialized tools, and robust sandbox construction. To evaluate such systems realistically, the authors also release RATBench, the first benchmark reflecting the true distribution and heterogeneity of real-world code repositories. Experimental results demonstrate that RAT significantly outperforms strong existing baselines on RATBench, achieving an average 29.6% improvement in Environment Setup Success Rate (ESSR). This advance overcomes prior limitations that relied on predefined artifacts or were confined to specific programming languages.

This work addresses the lack of an integrated Retrieval-Augmented Generation (RAG) development and evaluation toolkit in the R programming language, where existing solutions predominantly rely on the Python ecosystem. The authors propose ragR, the first native R framework enabling end-to-end RAG workflows—including document ingestion, vector storage, similarity-based retrieval, evidence synthesis, and structured question-answering logging—and faithfully reimplements the four core RAGAS evaluation metrics: context precision, context recall, faithfulness, and answer relevance. Experimental results demonstrate that ragR yields evaluation outcomes highly consistent with those produced by the original Python-based RAGAS implementation. This provides R users with a lightweight, reproducible, and self-contained environment for RAG research and education without requiring language switching.