The Programming Framework: A General Method for Process Analysis Using LLMs and Mermaid Visualization

Read full text
Authors: Gary Welz
Cited by: 10

Abstract

Scientific and technical fields rely heavily on textual process descriptions that are difficult to compare, analyze, or reuse computationally. We introduce the Programming Framework, a methodology for transforming textual process descriptions into structured, computable flowcharts using large language models (LLMs) and Mermaid diagram syntax. The framework suggests a five-category color-coding system (Red: triggers/inputs, Yellow: structures/objects, Green: processing/operations, Blue: intermediates/states, Violet: products/outputs) for consistent representation across disciplines, with customization for domain-specific needs. We demonstrate effectiveness through application across biology (100+ processes via the Genome Logic Modeling Project), chemistry (70+ processes), mathematics, physics, and computer science. The methodology enables researchers, educators, and AI systems to visualize, compare, and optimize processes across scientific disciplines. The Programming Framework is designed as reusable infrastructure that others can adopt, extend, and critique, with all methodology, tools, and examples publicly available.

Fields of Study & Subjects

Machine Learning in Materials Science Biomedical Text Mining and Ontologies Scientific Computing and Data Management

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
3 February 2026
Language
EN
Document type
Preprint