Update README.md

README.md

@@ -13,31 +13,92 @@ tags:
   - arxiv:2607.19316
 ---
 
-# VEDB SimCLR ResNet-18 — Fovea-Gaze
+# VEDB SimCLR ResNet-18 — NSD Voxelwise Encoding Models
 
-This repository contains the **Fovea-Gaze SimCLR ResNet-18 checkpoint** associated with:
+This repository contains **subject-specific voxelwise encoding-model fits** from:
 
-**Diaz, D. M., & Henderson, M. M. (2026). _Eccentricity-Constrained CNN Training Reveals Adaptive Information Coding Around the Visual Field._ Proceedings of the 9th Conference on Cognitive Computational Neuroscience.**
+**Diaz, D. M., & Henderson, M. M. (2026). *Eccentricity-Constrained CNN Training Reveals Adaptive Information Coding Around the Visual Field.* Proceedings of the 9th Conference on Cognitive Computational Neuroscience.**
 
-**DOI:** `10.32470/0416gfsq`  
+**DOI:** `10.32470/0416gfsq`
 **arXiv:** `2607.19316`
 
-This model is part of the **[Eccentricity-Constrained SimCLR Models (VEDB)](https://hf.co/collections/DM-Diaz/eccentricity-constrained-simclr-models-vedb)** collection.
+The encoding models were fit to fMRI responses from the **Natural Scenes Dataset (NSD)** using representations extracted from four VEDB-pretrained SimCLR ResNet-18 models:
 
-## Model
+* **Baseline**
+* **Fovea-Gaze**
+* **Periph**
+* **Periph-NF**
 
-- **Architecture:** ResNet-18
-- **Training:** SimCLR self-supervised pretraining
-- **Dataset:** Visual Experience Dataset (VEDB)
-- **Condition:** Fovea-Gaze
-- **Epoch:** 120
-- **Checkpoint:** `simclr_resnet18_fovea-gaze_epoch120.pth.tar`
+## Repository Structure
 
-The **Fovea-Gaze** condition was pretrained using gaze-centered central visual information derived from VEDB frames.
+```text
+baseline/
+fovea-gaze/
+periph/
+periph-nf/
+```
+
+Each folder contains voxelwise encoding-model fits for **NSD subjects S1–S8**.
+
+Example:
+
+```text
+fovea-gaze/
+├── NSD_S1_resnet18-Fovea-Gaze_concat.npy
+├── NSD_S2_resnet18-Fovea-Gaze_concat.npy
+├── ...
+└── NSD_S8_resnet18-Fovea-Gaze_concat.npy
+```
+
+## Encoding Models
+
+For each subject and visual-field condition, features were extracted from:
+
+```text
+conv1
+layer1.1
+layer2.1
+layer3.1
+layer4.1
+avgpool
+```
+
+Layer features were dimensionally reduced with PCA, concatenated, and used to fit **voxelwise L2-regularized linear regression (ridge) encoding models**.
+
+Each `.npy` file contains a saved Python dictionary including:
+
+* fitted voxelwise `weights`
+* held-out `r2`
+* held-out `corr`
+* candidate `lambdas`
+* `best_lambda_inds`
+* voxel mask and index information
+* voxel noise ceilings
+* subject and model metadata
+
+## Loading a Fit
+
+```python
+import numpy as np
+
+fit = np.load(
+    "baseline/NSD_S1_resnet18-Baseline_concat.npy",
+    allow_pickle=True
+).item()
+
+weights = fit["weights"]
+r2 = fit["r2"]
+corr = fit["corr"]
+best_lambda_inds = fit["best_lambda_inds"]
+```
+
+## Related Models
+
+The pretrained SimCLR checkpoints used to generate these representations are available in the **Eccentricity-Constrained SimCLR Models (VEDB)** Hugging Face collection.
 
 ## Release Status
 
-The pretrained checkpoint is available now. A complete model card, training documentation, and evaluation code will be added shortly.
+Encoding-model fits are available now. Additional documentation and analysis code are forthcoming.
 
 ## Citation