The scoring methods featured on this platform are derived from the robust
Dietary Index
R codebase created by James Jia Da Zhan, whose foundational contributions we gratefully acknowledge.
Leveraging generative AI and codex-driven configurations, we have modernized these methodologies into
an intuitive drag-and-drop web interface. Earlier revisions used Pyodide to run the Python code, but scoring now relies on a fast WebAssembly module compiled from Rust. This approach removes significant
technical and language barriers, enabling researchers from diverse backgrounds to seamlessly engage with validated nutritional scoring routines, without requiring any server setup or coding expertise.
Our codex-configured system integrates generative AI to facilitate transparent validation, robust self-correction,
and comprehensive refinement tools across the entire codebase. A key advantage of this design is built-in peer validation,
inherently provided through reliance on peer-reviewed scholarly publications, thus ensuring immediate credibility and trust.
These intrinsic validation processes accelerate the adoption and practical application of proven research methodologies.
We actively encourage critical feedback, validation testing, and innovative suggestions—whether verifying existing scoring
procedures or proposing new nutritional indices. Researchers and practitioners are invited to fork our repository, file issues,
and contribute actively to future improvements. Through open sharing of this collaborative AI-driven framework, HOBI and
Dr. Strath aim to cultivate an inclusive, transparent nutrition science community, bridging publication and
practice, and ultimately accelerating research that enhances public health outcomes.
Disclaimer: The majority, if not all, content on this platform—including written materials and both frontend
and backend code—is generated by AI. While innovative, not all content has undergone comprehensive human validation, including
this very disclaimer. This project is currently in early alpha development, with validation methods actively evolving. Users should independently verify all results obtained through these tools and employ them at their own risk. Your feedback—positive or critical—is invaluable in refining scientific validation methodologies facilitated by generative AI.
