Add paper link and pipeline tag

README.md

@@ -1,21 +1,25 @@
 ---
 license: apache-2.0
+pipeline_tag: image-classification
 tags:
-  - medical-imaging
-  - ct-scan
-  - multi-label-classification
-  - radiology
-  - disease-detection
+- medical-imaging
+- ct-scan
+- multi-label-classification
+- radiology
+- disease-detection
 ---
 
 # Janus
 
-Multi-label abdominal disease classification from 3-D CT scans.
-DINOv3 backbone with four ablation variants: GAP, Masked Attention,
-Scalar Fusion, and Gated Fusion.
+Official model weights for **JANUS**, a physiology-guided dual-stream architecture for robust CT triage. JANUS conditions visual embeddings on macro-radiomic priors via Anatomically Guided Gating to improve discrimination and reliability under distribution shift.
+
+- **Paper:** [JANUS: Anatomy-Conditioned Gating for Robust CT Triage Under Distribution Shift](https://huggingface.co/papers/2605.13813)
+- **Repository:** [https://github.com/lavsendahal/janus](https://github.com/lavsendahal/janus)
 
 ## Ablation variants
 
+The repository contains weights for different model variants explored in the paper:
+
 | Variant | Folder | Macro AUROC | Needs seg masks | Needs radiomics |
 |---|---|---|---|---|
 | GAP (baseline) | `gap/` | 0.8488 | — | — |
@@ -23,8 +27,7 @@ Scalar Fusion, and Gated Fusion.
 | Scalar Fusion | `scalar-fusion/` | 0.8332 | ✓ | ✓ |
 | **Gated Fusion** | **`gated-fusion/`** | **0.8811** | ✓ | ✓ |
 
-Each folder contains `model.safetensors` and `config.json` (labels, image size,
-input requirements, best macro AUROC).
+Each folder contains `model.safetensors` and `config.json` (labels, image size, input requirements, best macro AUROC).
 
 ## Quick-start — GAP variant (self-contained)
 
@@ -35,23 +38,11 @@ pip install torch transformers safetensors nibabel scipy huggingface_hub
 python inference.py ct.nii.gz --variant gap --top 10
 ```
 
-Example output:
-```
-Disease                                    Prob
-──────────────────────────────────────────────────
-  Atherosclerosis                         0.821  ████████████████
-  Renal Cyst                              0.714  ██████████████
-  Hepatic Steatosis                       0.431  ████████
-  ...
-```
-
 ## Full pipeline (masked-attn / gated-fusion / scalar-fusion)
 
-These variants require organ segmentation masks (and radiomics features for
-fusion models). Use the full Janus preprocessing pipeline:
+These variants require organ segmentation masks (and radiomics features for fusion models). Use the full Janus preprocessing pipeline:
 
-**Source code:** https://github.com/lavsendahal/janus
-*(Repository is currently private — request access if needed.)*
+**Source code:** [https://github.com/lavsendahal/janus](https://github.com/lavsendahal/janus)
 
 ```bash
 git clone https://github.com/lavsendahal/janus
@@ -68,14 +59,17 @@ python -m janus.inference --variant gated-fusion --ct ct.nii.gz
 
 ## Diseases (30 labels)
 
-Hepatomegaly, Splenomegaly, Cardiomegaly, Prostatomegaly, Hepatic Steatosis,
-Osteopenia, Gallstones, AAA, Aortic Valve Calcification, Coronary Calcification,
-Atherosclerosis, Thrombosis, Bowel Obstruction, Appendicitis, Hiatal Hernia,
-Submucosal Edema, Free Air, Biliary Ductal Dilation, Absent Gallbladder,
-Pancreatic Atrophy, Hydronephrosis, Renal Cyst, Renal Hypodensities,
-Pleural Effusion, Atelectasis, Ascites, Anasarca, Metastatic Disease,
-Lymphadenopathy, Fracture.
+Hepatomegaly, Splenomegaly, Cardiomegaly, Prostatomegaly, Hepatic Steatosis, Osteopenia, Gallstones, AAA, Aortic Valve Calcification, Coronary Calcification, Atherosclerosis, Thrombosis, Bowel Obstruction, Appendicitis, Hiatal Hernia, Submucosal Edema, Free Air, Biliary Ductal Dilation, Absent Gallbladder, Pancreatic Atrophy, Hydronephrosis, Renal Cyst, Renal Hypodensities, Pleural Effusion, Atelectasis, Ascites, Anasarca, Metastatic Disease, Lymphadenopathy, Fracture.
 
 ## Citation
 
-If you use this model, please cite the Janus paper (forthcoming).
+If you use this model, please cite the following:
+
+```bibtex
+@article{janus2026,
+  title={JANUS: Anatomy-Conditioned Gating for Robust CT Triage Under Distribution Shift},
+  author={Dahal, Lavsen and others},
+  journal={arXiv preprint arXiv:2605.13813},
+  year={2026}
+}
+```