Rename: this is the twin-stack app layer (was gemeo-world-model). World model now at Raras-AI/gemeo-world-model.

README.md

@@ -43,42 +43,60 @@ extra_gated_fields:
   I agree to non-clinical research use only: checkbox
 ---
 
-# GEMEO — Rare-Disease Patient World Model
+# GEMEO Twin Stack — Application Layer for the GEMEO Patient World Model
 
-> A graph-native, continuously-evolving **digital twin** for rare-disease
-> patients. Six inference modes — trajectory, diagnosis, risk/survival,
-> counterfactual, repurposing, cohort — over the same PrimeKG-grounded,
-> SUS-anchored backbone. Research preview. **Not a medical device.**
+> The graph-native **digital-twin application stack** that runs on top of
+> the [GEMEO World Model](https://huggingface.co/Raras-AI/gemeo-world-model).
+> Six inference modes — trajectory, diagnosis, risk/survival,
+> counterfactual, repurposing, cohort — wired together with auxiliary heads,
+> KG embeddings, and a FastAPI surface. Research preview. **Not a medical device.**
 
 **Authors:** Raras.ai team · **Contact:** dimas@raras.ai
 **Source:** github companion repo (raras.org)
 **Paper v1 (Zenodo):** [DOI 10.5281/zenodo.20092131](https://doi.org/10.5281/zenodo.20092131)
-**Companion model (CDF backbone):** [Raras-AI/gemeo-cdf-v2](https://huggingface.co/Raras-AI/gemeo-cdf-v2)
-**Companion model (mobile decision-support):** [Raras-AI/araras-gemma4](https://huggingface.co/spaces/Raras-AI/araras-gemma4)
+**🌍 World Model (the dynamics core this stack runs on top of):** [Raras-AI/gemeo-world-model](https://huggingface.co/Raras-AI/gemeo-world-model)
+**📱 Mobile decision-support sibling:** [Raras-AI/araras-gemma4](https://huggingface.co/Raras-AI/araras-gemma4)
 **License:** CC-BY-NC 4.0 + non-clinical-use rider (see [LICENSE](./LICENSE))
 
+> **Note on naming.** Previously released as `Raras-AI/gemeo-world-model`
+> (HF auto-redirects). Renamed to `gemeo-twin-stack` because the actual
+> world model — the generative dynamics core — is the Causal Diffusion
+> Forcing transformer now living at the new `gemeo-world-model` slug. This
+> repo is the **application layer** (encoder, cohort, risk, whatif,
+> repurpose, ask, ground_sus, api) that turns the world model into a
+> usable digital twin with six inference modes.
+
 ---
 
 ## What this is
 
-GEMEO is not a single model. It is a **module** (≈22k LOC) that wires
-together a heterogeneous-graph backbone with six inference modes for
-rare-disease patient digital twins. Each mode has a clean Python API, a
-bootstrap implementation that runs today, and an optional learned
-component that drops in when a checkpoint exists.
+This is the **application layer** of GEMEO — a module (≈22k LOC) that
+takes the GEMEO World Model (a Causal Diffusion Forcing transformer,
+published separately at [Raras-AI/gemeo-world-model](https://huggingface.co/Raras-AI/gemeo-world-model))
+and wires it together with auxiliary heads, KG embeddings, and tooling
+to produce a complete digital-twin product. Each inference mode has a
+clean Python API, a bootstrap implementation that runs today, and an
+optional learned slot that drops in when a checkpoint exists.
 
 ```
-GEMEO World Model
+GEMEO Twin Stack  (this repo)
 ├── Patient embedding       (gemeo/encoder.py)        HGT scaffolded; bootstrap = weighted KG embedding
 ├── Cohort retrieval        (gemeo/cohort.py)         kNN + Cypher overlap on PrimeKG
 ├── Subgraph reasoning      (gemeo/subgraph.py)       1-hop sparsification (learned variant in train/)
-├── Trajectory              (gemeo/trajectory.py)     bootstrap LLM-over-natural-history; CDF backbone via gemeo-cdf-v2
+├── Trajectory mode         (gemeo/trajectory.py)     ← calls into the GEMEO World Model
+├── Diagnostic mode         (deeprare_diagnosis.py +  ← multi-agent over PrimeKG paths
+│                            fast_dx.py, ensemble)
 ├── Risk / survival         (gemeo/risk.py)           NeuralSurv trained on DATASUS SIM (c-index 0.70)
 ├── Drug repurposing        (gemeo/repurpose.py)      TxGNN slot + SUS auxiliary head
-├── Counterfactual          (gemeo/whatif.py)         do-calculus mutator
+├── Counterfactual          (gemeo/whatif.py)         do-calculus mutator; uses world-model rollout
 ├── Active learning         (gemeo/ask.py)            info-gain over KG annotations
 ├── SUS grounding           (gemeo/ground_sus.py)     PCDT/CEAF/UF coverage check
 └── FastAPI                 (gemeo/api.py)            production /api/gemeo/* endpoints
+
+GEMEO World Model  (separate repo: Raras-AI/gemeo-world-model)
+└── Causal Diffusion Forcing transformer (19.86M params)
+    The generative dynamics core. Trajectory + counterfactual modes
+    above delegate to it.
 ```
 
 ---
@@ -93,7 +111,7 @@ GEMEO World Model
 | | timeout rate | 0.0% | |
 | **Risk / survival** (NeuralSurv, DATASUS SIM) | val c-index | **0.70** (best @ ep 30) | 4,624 SIM mortality records, 37,494 censoring samples |
 | | final c-index | 0.694 | after 100 epochs |
-| **Trajectory backbone** ([gemeo-cdf-v2](https://huggingface.co/Raras-AI/gemeo-cdf-v2)) | val cross-entropy | 0.030 | per-token diffusion forcing |
+| **World Model backbone** ([gemeo-world-model](https://huggingface.co/Raras-AI/gemeo-world-model)) | val cross-entropy | 0.030 | per-token diffusion forcing |
 | | calibration ICI | 0.0006 | well calibrated |
 | | training | 5.8 min on 1×H100 | $0.48 |
 
@@ -118,7 +136,7 @@ twin.trajectory.horizons   # 6/12/24-month event predictions
 ```
 
 Backbone: bootstrap LLM-over-natural-history today, [Causal Diffusion
-Forcing](https://huggingface.co/Raras-AI/gemeo-cdf-v2) when the CDF
+Forcing](https://huggingface.co/Raras-AI/gemeo-world-model) when the CDF
 checkpoint is mounted.
 
 ### 2 · Diagnosis
@@ -207,9 +225,11 @@ LICENSE
 README.md   ← this file
 ```
 
-The CDF trajectory backbone is published separately at
-[**Raras-AI/gemeo-cdf-v2**](https://huggingface.co/Raras-AI/gemeo-cdf-v2)
-(~80 MB) — keep that repo for the heavy ckpt, this repo for the wiring.
+The GEMEO World Model (the Causal Diffusion Forcing dynamics core) is
+published separately at
+[**Raras-AI/gemeo-world-model**](https://huggingface.co/Raras-AI/gemeo-world-model)
+(~80 MB) — keep that repo for the heavy ckpt, this repo for the
+application stack that runs on top of it.
 
 ---
 
@@ -314,8 +334,9 @@ world model, multimodal substrate.
 
 ## Changelog
 
-- **2026-05 (this release)** — Initial public release of the world-model module + NeuralSurv ckpt (c-index 0.70) + DT-FM baseline + PrimeKG-derived embeddings + RareBench v49 results.
-- **2026-05** — CDF v2 trajectory backbone published at [Raras-AI/gemeo-cdf-v2](https://huggingface.co/Raras-AI/gemeo-cdf-v2).
+- **2026-05 (this release)** — Initial public release of the twin-stack application layer + NeuralSurv ckpt (c-index 0.70) + DT-FM baseline + PrimeKG-derived embeddings + RareBench v49 results.
+- **2026-05-19** — Renamed from `Raras-AI/gemeo-world-model` → `Raras-AI/gemeo-twin-stack` (HF auto-redirects). The slug `gemeo-world-model` now hosts the actual Causal Diffusion Forcing world model.
+- **2026-05** — GEMEO World Model v2 (CDF backbone) published at [Raras-AI/gemeo-world-model](https://huggingface.co/Raras-AI/gemeo-world-model).
 - **2026-04** — GEMEO v1 paper published on Zenodo (DOI 10.5281/zenodo.20092131).
 
 ---