diff --git a/.github/copilot-instructions.md b/.github/copilot-instructions.md
index 3bcf718..5b5e94b 100644
--- a/.github/copilot-instructions.md
+++ b/.github/copilot-instructions.md
@@ -145,7 +145,7 @@ Prefer GPU-accelerated operations:
 - **DARTS v2**: RTS labels (year, area, count, density)
 - **ERA5**: Climate data (40-year history, Arctic-aligned years)
 - **ArcticDEM**: 32m resolution terrain (slope, aspect, indices)
-- **AlphaEarth**: 256-dimensional satellite embeddings
+- **AlphaEarth**: 64-dimensional satellite embeddings
 - **Watermask**: Ocean exclusion layer
 
 ## Model Support
diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md
index 8da0fab..b55b2f3 100644
--- a/ARCHITECTURE.md
+++ b/ARCHITECTURE.md
@@ -69,7 +69,7 @@ The pipeline follows a sequential processing approach where each stage produces
 
 **AlphaEarth Embeddings (`alphaearth.py`)**
 
-- Extracts 256-dimensional satellite image embeddings via Google Earth Engine
+- Extracts 64-dimensional satellite image embeddings via Google Earth Engine
 - Uses foundation models to capture visual patterns
 - Partitions large grids using KMeans clustering
 - Temporal sampling across multiple years
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 89f06f0..bc4d1f7 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -33,7 +33,7 @@ This will set up the complete environment including RAPIDS, PyTorch, and all geo
 - `grids.py`: H3/HEALPix spatial grid systems
 - `darts.py`, `era5.py`, `arcticdem.py`, `alphaearth.py`: Data source processors
 - `dataset.py`: Dataset assembly and feature engineering
-- `training.py`: Model training with eSPA/SPARTAn
+- `training.py`: Model training with eSPA, XGBoost, Random Forest, KNN
 - `inference.py`: Prediction generation
 
 ## Coding Standards