Add evaluation metrics to model card (accuracy@0.5 0.9988, ROC AUC 1.0, gap 0.9482)

README.md

@@ -11,6 +11,25 @@ license: mit
 datasets:
   - LoveJesus/biblical-embedding-dataset-chirho
 pipeline_tag: sentence-similarity
+model-index:
+  - name: biblical-cross-translation-chirho
+    results:
+      - task:
+          type: sentence-similarity
+          name: Cross-Translation Semantic Similarity
+        dataset:
+          type: LoveJesus/biblical-embedding-dataset-chirho
+          name: Biblical Embedding Dataset (Chirho)
+        metrics:
+          - type: accuracy
+            value: 0.9988
+            name: Accuracy@0.5
+          - type: roc_auc
+            value: 1.0000
+            name: ROC AUC
+          - type: spearmanr
+            value: 0.4915
+            name: Spearman Correlation
 ---
 
 <!-- For God so loved the world that he gave his only begotten Son, -->
@@ -54,5 +73,21 @@ print(similarities)
 
 This is model 5 of 5 in the [bible.systems](https://bible.systems) ML pipeline.
 
+## Evaluation Results
+
+Evaluated on a held-out test set of cross-translation verse pairs.
+
+| Metric | Score |
+|--------|-------|
+| **Accuracy@0.5** (cosine sim threshold) | **0.9988** |
+| **ROC AUC** | **1.0000** |
+| **Spearman Correlation** | **0.4915** |
+| **Avg Positive Similarity** | 0.9841 |
+| **Avg Negative Similarity** | 0.0359 |
+| **Similarity Gap** (pos - neg) | **0.9482** |
+
+> The model achieves near-perfect discrimination between same-verse pairs across translations (high positive similarity) and different-verse pairs (low negative similarity), with a gap of 0.95. The Spearman correlation is moderate because within-class similarity variance is low (most positive pairs cluster near 0.98).
+
+
 ---
 *For God so loved the world...* — John 3:16