Rxiv-Maker: an automated template engine for streamlined scientific publications

TL;DR

The paper addresses the burden of manually typesetting and keeping manuscripts synchronized with evolving data in computational research. It introduces Rxiv-Maker, a local-first framework that compiles Markdown with executable code into publication-ready PDFs or Word documents by running embedded scripts and translating to LaTeX, with intelligent caching and Git-based collaboration. Its key contributions include self-updating manuscripts, programmatic figure generation, a multi-pass Markdown-to-LaTeX translator, and integrated validation and containerized deployment for reproducible publishing. The approach reduces transcription errors, accelerates writing, and supports transparent, auditable workflows from draft to submission across multiple formats.

Abstract

The rapid growth of preprint servers has accelerated scientific dissemination but has also shifted the technical burden of manuscript preparation to authors. This challenge is particularly acute in computational research, where manuscripts must remain synchronised with evolving data and code. We present Rxiv-Maker, a framework that resolves this by converting simple Markdown files into professionally typeset, publication-ready PDFs. Its core feature is the ability to execute embedded code, creating a self-updating manuscript where figures and statistical values are generated directly from source data during compilation. This ensures that the final document is always current and fully reproducible. By integrating with standard tools like Git and Visual Studio (VS) Code, Rxiv-Maker provides an efficient, transparent, and collaborative authoring experience, applying principles of software engineering to academic writing to foster open and verifiable science.

Figures (6)

• Figure 1: System Architecture. Rxiv-Maker integrates Markdown content, YAML metadata, executable scripts, and bibliographies through a processing engine that combines local execution with LaTeX PDF compilation or Word (.docx) generation to produce publication-ready documents.
• Figure 2: Processing Pipeline. User-provided content (left) undergoes automated processing (right), including parsing, script execution, document compilation (PDF/Word), and final output generation.
• Figure 3: Embedded Python for dynamic content. This figure shows a Python script embedded in the manuscript's source code. The script is executed at build time to compute data attributes (e.g., total submissions and span of years) and inject the resulting values directly into the text. This process, rendered here with syntax highlighting from the Rxiv-Maker VS Code extension, eliminates manual transcription errors and ensures the text remains synchronised with the source data.
• Figure S1: The growth of preprint submissions on the arXiv server (1991-2025). This figure was generated from public arXiv statistics using a Python script executed by the Rxiv-Maker pipeline, demonstrating reproducible, data-driven visualisation.
• Figure S2: Preprint Submission Trends Across Multiple Servers (2018-2025). This figure, showing preprints indexed by PubMed from major repositories, was generated from public data PubMedByYear2025 using a reproducible R script within the Rxiv-Maker pipeline.