A YAML-Driven Metaprompt Orchestration Framework for Governance-Aligned, Attribution-Enforced Automated Research Workflows: Integrating NIST AI RMF, ISO/IEC 42001, ORCID, and DOI Provenance in Agentic AI Systems

Read full text Summarise with VIRAT
Authors: Ariel J. Furlow
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The YAML-based system introduces a deterministic prompt architecture for AI systems, emphasizing reproducibility and compliance with governance frameworks such as NIST AI RMF and ISO/IEC 42001. Key features include YAML-state initialization, hyperparameter locking, and a forensic audit battery. The framework aims to address issues of variability in AI interactions, ensuring high-integrity outputs and proper attribution through automated ORCID and DOI linking. It also outlines a comprehensive implementation strategy, including applications in biosecurity, AI governance, and research reproducibility. # Overview of the Framework The research architecture for Ariel J. Furlow is a groundbreaking development in research automation that emphasizes the coordination of agent capabilities, regulatory conformance, and protection of intellectual contributions. The framework targets key pain points researchers face in handling publication lifecycles, meeting governance requirements, and preserving accurate credit for work. ### Importance of the Framework In a context where research outputs must be both reproducible and aligned with rigorous oversight standards, this architecture offers a streamlined approach to publication management and version control while protecting intellectual ownership. By automating these essential tasks, it boosts efficiency and precision, enabling researchers like Ariel J. Furlow to concentrate on innovation and substantive scientific progress instead of administrative overhead. ### Claims and Contributions 1. Novel Architecture: The system proposes an original, modular, YAML-based design that connects platforms such as Notion, Zenodo, GitHub, and arXiv to support seamless metaprompt extraction and governance-gap diagnostics. 2. Attribution Protections: It programmatically associates ORCID and DOI identifiers with live verification, markedly lowering the chance of miscredit in collaborative work. 3. Governance Compliance: It is the first solution to automatically align research products with established governance frameworks (NIST AI RMF, ISO/IEC 42001), improving compliance and audit preparedness. 4. Collaborative Metaprompts: The framework delivers neutral, expertise-aware prompts that aid the workflow without imitating the researcher’s stylistic voice, thereby upholding the authenticity of intellectual contributions. 5. Cross-Platform Synchronization: Using a pipeline built on GitHub Actions plus the Notion and Zenodo APIs, it keeps research portfolios synchronized and metadata consistently updated. 6. Built-In Reproducibility: Through YAML frontmatter and rigorously structured metadata, the system maintains an immutable record of artifacts, directly addressing reproducibility challenges in AI/ML research. ### Conclusion The framework not only defines a new problem space within research automation but also lays down a fresh engineering foundation for managing and attributing scholarly work. It establishes a methodological benchmark centered on governance conformance and intellectual integrity, representing a substantial step forward in how research ecosystems are organized and trusted.

Fields of Study & Subjects

Scientific Computing and Data Management Ethics and Social Impacts of AI Research Data Management Practices

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
21 March 2026
Language
EN