diff --git a/analysis/README.md b/analysis/README.md
index 0486604..39b938b 100644
--- a/analysis/README.md
+++ b/analysis/README.md
@@ -131,7 +131,7 @@ python3 scripts/convert_csv_to_json.py data/synthetic_1.4.0/readings.csv
 python3 scripts/export_model_for_js.py data/synthetic_1.4.0/readings.csv
 ```
 
-→ `json/` (one bicorder.json-spec reading per protocol); `bicorder_model.json` in this directory, read by `bicorder-app` at build time (requires step 3 first; see `INTEGRATION_GUIDE.md`)
+→ `json/` (one bicorder.json-spec reading per protocol). The optional `export_model_for_js.py` refreshes the research-only `bicorder_model.json` in this directory (app integration removed in bicorder v1.3.0; requires step 3 first)
 
 ---
 
@@ -348,7 +348,7 @@ This simple version-matching approach ensures compatibility without complex stru
 
 ### Files
 
-- `bicorder_model.json` (~5KB) - Trained LDA model with coefficients and scaler parameters; read by `bicorder-app` at build time
+- `bicorder_model.json` (~5KB) - Trained LDA model with coefficients and scaler parameters; research-only since v1.3.0 (the app no longer reads it)
 - `bicorder-app/src/bicorder-classifier.ts` - TypeScript classifier implementation in the web app
 - `ascii_bicorder.py` (updated) - Python script now calculates automated analysis values
 - `../bicorder.json` (updated) - Added bureaucratic ↔ relational gradient to analysis section
@@ -361,7 +361,7 @@ The calculation happens automatically when generating bicorder output:
 python3 ascii_bicorder.py bicorder.json bicorder.txt
 ```
 
-For web integration, see `INTEGRATION_GUIDE.md`. The app (`bicorder-app/`) has its own classifier implementation and reads `bicorder_model.json` from this directory at build time.
+For the history of the web integration, see `INTEGRATION_GUIDE.md`. The app (`bicorder-app/`) used to deploy its own TypeScript classifier and read `bicorder_model.json` from this directory at build time; that integration was removed in v1.3.0, so this model is now research-only.
 
 ### Key Features
 
diff --git a/analysis/WORKFLOW.md b/analysis/WORKFLOW.md
index 0042d5c..6c40440 100644
--- a/analysis/WORKFLOW.md
+++ b/analysis/WORKFLOW.md
@@ -25,7 +25,7 @@ The scripts automatically draw the gradients from the current state of the [bico
 9. **scripts/univariate_analysis.py** - Per-protocol and per-gradient averages, distributions, and summary stats (replaces the ad-hoc averages workflow)
 10. **scripts/compare_analyses.py** - Compare readings CSVs to a reference (Euclidean distance, RMSE, correlation); canonicalizes renamed gradients so versions can be compared
 11. **scripts/visualize_clusters.py** - Additional cluster visualizations
-12. **scripts/export_model_for_js.py** - Export trained model to `bicorder_model.json` (read by `bicorder-app` at build time)
+12. **scripts/export_model_for_js.py** - Export trained model to `bicorder_model.json` (research-only since v1.3.0 — the app integration was removed)
 
 Version-agnostic helpers shared by these scripts live in **scripts/bicorder_common.py**: the historical gradient rename map, version detection (from the `bicorder_version`/`version` column, falling back to the `data/<type>_<version>/` directory convention), and training-CSV selection. When gradients are renamed in `../bicorder.json`, update `COLUMN_RENAMES` in that one module.
 
diff --git a/analysis/scripts/export_model_for_js.py b/analysis/scripts/export_model_for_js.py
index 1f97dcd..c06b821 100644
--- a/analysis/scripts/export_model_for_js.py
+++ b/analysis/scripts/export_model_for_js.py
@@ -1,6 +1,9 @@
 #!/usr/bin/env python3
 """
-Export the cluster classification model to JSON for use in JavaScript.
+Export the cluster classification model to JSON.
+
+Research-only export: the bicorder-app integration was removed in bicorder
+v1.3.0, so nothing in the app reads this model anymore.
 
 Reads dimension names directly from bicorder.json so the model always
 stays in sync with the current bicorder structure. Column renames and the