Upload app.py with huggingface_hub

app.py

@@ -874,9 +874,22 @@ VALIDATION = f"""
     </div>
   </div>
 
-  <img src="data:image/png;base64,{VAL_B64}" style="width:100%;border-radius:6px;margin-bottom:10px;border:1px solid #252a35"/>
-  <img src="data:image/png;base64,{AUC_B64}" style="width:100%;border-radius:6px;margin-bottom:18px;border:1px solid #252a35"/>
+  <div style="margin:18px 0 8px">
+    <div style="color:#f4f4f5;font-size:0.95rem;font-weight:600;margin-bottom:4px">Demo cohort · 5 held-out sites, 10 subjects</div>
+    <div style="color:#8b95a7;font-size:0.82rem;line-height:1.6">Two subjects per site were randomly selected from the ABIDE I held-out pool. The model that trained on <em>all other sites</em> was used — it has never seen any data from these institutions.</div>
+  </div>
+  <img src="data:image/png;base64,{VAL_B64}" style="width:100%;border-radius:6px;margin-bottom:22px;border:1px solid #252a35"/>
+
+  <div style="margin:0 0 8px">
+    <div style="color:#f4f4f5;font-size:0.95rem;font-weight:600;margin-bottom:4px">Full 20-fold LOSO AUC · all 1,102 subjects</div>
+    <div style="color:#8b95a7;font-size:0.82rem;line-height:1.6">Each bar is one site blind to training. AUC 0.7298 is the mean across all 20 folds — every subject is test-only exactly once. Prior art uses same-site splits; this is a strictly harder evaluation.</div>
+  </div>
+  <img src="data:image/png;base64,{AUC_B64}" style="width:100%;border-radius:6px;margin-bottom:22px;border:1px solid #252a35"/>
 
+  <div style="margin:0 0 8px">
+    <div style="color:#f4f4f5;font-size:0.95rem;font-weight:600;margin-bottom:4px">Subject-level predictions · demo cohort</div>
+    <div style="color:#8b95a7;font-size:0.82rem;line-height:1.6">Predictions with 0.4 &lt; p &lt; 0.6 are flagged as inconclusive rather than forced to a label — surfacing borderline cases for clinical review instead of producing a confident wrong answer.</div>
+  </div>
   <div style="background:#161922;border:1px solid #252a35;border-radius:8px;overflow:hidden">
     <table style="width:100%;border-collapse:collapse;font-size:0.86rem">
       <thead><tr>
@@ -895,7 +908,11 @@ VALIDATION = f"""
     <span style="color:#cbd5e1">Zero confident misclassifications across 5 unseen sites.</span>
   </div>
 
-  <div style="display:grid;grid-template-columns:1fr 1fr;gap:14px;margin-top:22px">
+  <div style="margin:22px 0 8px">
+    <div style="color:#f4f4f5;font-size:0.95rem;font-weight:600;margin-bottom:4px">Diagnostic breakdown &amp; published baselines</div>
+    <div style="color:#8b95a7;font-size:0.82rem;line-height:1.6">On definitive predictions (p &gt; 0.6 or p &lt; 0.4) the model achieves 100% sensitivity and specificity on the demo cohort. Compared against published ABIDE benchmarks — all of which used same-site evaluation.</div>
+  </div>
+  <div style="display:grid;grid-template-columns:1fr 1fr;gap:14px">
 
     <!-- Confusion matrix (on definitive predictions only) -->
     <div style="background:#161922;border:1px solid #252a35;border-radius:8px;padding:18px 20px">