license: agpl-3.0
tags:
- rare-disease
- world-model
- diffusion-forcing
- clinical-ai
- patient-digital-twin
GEMEO Architecture (Reference)
This HuggingFace repository is a discoverability mirror for the GEMEO reference architecture, which is maintained on GitHub:
Code (AGPL-3.0): https://github.com/rarasAI/gemeo Model weights (CC-BY-NC-4.0): https://huggingface.co/Raras-AI/gemeo-sus Benchmark (CC-BY-NC-4.0): https://huggingface.co/datasets/Raras-AI/rarebench-br-trajectory Paper (DOI, always-latest): https://doi.org/10.5281/zenodo.20092130
What GEMEO is
The first world-model architecture for rare disease: a three-pillar pipeline (Propose -> Simulate -> Verify) that grounds onset candidates in the genome and a biomedical knowledge graph, simulates patient trajectories with a recurrence-aware Causal Diffusion Forcing transformer, and adjudicates every prediction with an agentic differential-diagnosis agent (traceable evidence path per decision).
License
- Code / reference implementation: AGPL-3.0 (open-core). Commercial licenses available: dimas@raras.ai.
- Trained weights (
gemeo-sus) and benchmark: CC-BY-NC-4.0.
How to use
Clone the GitHub repo and follow ADAPTING_TO_A_NEW_DATABASE.md:
git clone https://github.com/rarasAI/gemeo
Research preview, not a medical device.