probe model pr

README.md

@@ -1,84 +1,44 @@
 ---
-license: cc-by-4.0
+license: mit
 library_name: pytorch
 tags:
   - digital-twins
   - scene-graphs
-  - dynamic-scene-graphs
   - robotics
-  - support-relations
-  - graph-maintenance
-  - counterfactual-evidence
-  - pytorch
+  - computer-vision
+  - graph-neural-network
 ---
 
 # CF-SupportNet
 
-CF-SupportNet is the learned edge-scoring component of **MedPhyGraph** (ECCV 2026 TwinWorld Workshop). It is **not** the full MedPhyGraph framework by itself: MedPhyGraph additionally applies deterministic State Consistency and Union-Based Transition-Aware Consistency — non-learned, code-only operations — on top of these scores to produce the final maintained support graph. See the [project page](https://medphygraph.github.io/) for the paper and complete pipeline code.
+CF-SupportNet is the learned edge-scoring component of **MedPhyGraph**
+(ECCV 2026 TwinWorld Workshop). It is NOT the full MedPhyGraph
+framework by itself: MedPhyGraph also applies deterministic State
+Consistency and Union-Based Transition-Aware Consistency (non-learned,
+code-only) on top of these scores to produce the final maintained
+support graph. See the paper and code at
+https://medphygraph.github.io/ for the complete pipeline.
 
 ## Files
 
-| File | Role |
-|---|---|
-| `health_dyphygraph_r1.0_seed0.pt` | Primary checkpoint — used for all headline results in the paper (ρ=1.0, seed 0) |
-| `health_dyphygraph_r1.0_seed{1-4}.pt` | Used only for the paper's multi-seed reproducibility audit; not intended as alternative production checkpoints |
+- `health_dyphygraph_r1.0_seed0.pt` — primary checkpoint used for all
+  headline paper results (rho=1.0, seed 0)
+- `health_dyphygraph_r1.0_seed{1-4}.pt` — used only for the paper's
+  multi-seed reproducibility audit; not intended as alternative
+  production checkpoints
 
 ## Architecture
 
-- One-layer GRU, hidden width 64 (temporal encoder over counterfactual evidence channels)
-- Geometry branch: 2 → 32 → 32 MLP (static geometric channels)
-- Fusion branch: 96 → 64 → 64 MLP, dropout 0.1
-- **25,409 trainable parameters** total
-
-Full architectural and training details are in the paper, Section 3.4.
-
-## Results
-
-Frozen seed-0 checkpoint, full observation (ρ=1.0):
-
-| Protocol | Transition-Macro Dyn-F1 | Pooled Delta Micro-F1 | Transfer Dyn-F1 |
-|---|---|---|---|
-| Core (15 transfers: 9 Procedural, 6 Isaac) | 1.000 | 1.000 | 1.000 |
-| Expanded (217 transfers, 19 templates) | 0.998 | 0.998 | 0.998 |
-
-*Req. Success, Transfer, Add, and Remove for the expanded suite are reported in the paper's main Results table; Transition-Macro and Pooled Delta Micro-F1 for the expanded suite are from the paper's Supplementary component analysis.*
-
-Across seeds 0–4, pooled Transfer Dyn-F1 on the expanded suite is 0.997 ± 0.001.
-
-## Loading the checkpoint
-
-```python
-from huggingface_hub import hf_hub_download
-import torch
-
-path = hf_hub_download(
-    repo_id="MedPhyGraph/CF-SupportNet",
-    filename="health_dyphygraph_r1.0_seed0.pt",
-)
-state_dict = torch.load(path, map_location="cpu", weights_only=True)
-```
-
-> This repository hosts raw PyTorch weights only, not a packaged `from_pretrained`-compatible class. To reconstruct the model, define the architecture above (or import it from the [code repository](https://medphygraph.github.io/)) and load `state_dict` into it directly.
-
-## Limitations
-
-- The counterfactual evidence used at both training and inference comes from an analytic AABB-based host-removal proxy, not a full physics simulator — it does not model mesh collisions, contact forces, or materials.
-- Operates downstream of perception on structured object states (poses, categories, AABB extents); it does not take raw RGB-D or perception input.
-- Evaluates direct, primary `SupportedBy` relations only.
-- Assumes the correct destination candidate is present in the candidate set at inference; if it is not, a support transfer cannot be recovered by the scorer or the downstream graph-maintenance stages.
-- Does not model distributed support, articulated contact, or temporary/transient support.
-
-## Related artifacts
-
-- Structured training/evaluation data (procedural + Isaac for Healthcare-derived scenes): `MedPhyGraph/support-graph-data` *(forthcoming)*
+One-layer GRU (hidden width 64), fusion MLP, 25,409 trainable
+parameters. Full training details in the paper, Section 3.4.
 
 ## Citation
 
 ```bibtex
 @inproceedings{gholizadeh2026medphygraph,
-  title     = {MedPhyGraph: Counterfactual Support-Graph Maintenance for Dynamic Built-Environment Digital Twins},
-  author    = {Gholizadeh HamlAbadi, Kamran and Vahdati, Monica and El Saddik, Abdulmotaleb},
-  booktitle = {ECCV 2026 Workshop on Visual Intelligence for Built Environment Digital Twins (TwinWorld)},
-  year      = {2026}
+  title={MedPhyGraph: Counterfactual Support-Graph Maintenance for Dynamic Built-Environment Digital Twins},
+  author={Gholizadeh HamlAbadi, Kamran and Vahdati, Monica and El Saddik, Abdulmotaleb},
+  booktitle={ECCV 2026 TwinWorld Workshop},
+  year={2026}
 }
-```
+```