Update index.html

index.html

@@ -212,10 +212,10 @@
       </ul>
       <details class="card" style="margin-top:1rem">
         <summary><strong>Method (short)</strong></summary>
-        <ol>
-          <li>For each clip, run models on A, V, and AV variants with the same instruction‑style prompt.</li>
+        <ol> 
+          <li>For each clip, run models on A, V, and AV variants with the same instruction-style prompt.</li>
           <li>Decode model outputs into <code>{object, material, outcome}</code> and compare against labels.</li>
-          <li>Compute accuracy per task and cross‑modal gain per clip and on average.</li>
+          <li>Compute per-task Top-1 and Top-5 accuracy and cross-modal gain per clip and in aggregate; additionally report calibration/confidence metrics (ECE, Brier, margin, entropy, Top-1 probability) and probing-based audio reliance via fixed cue selection and A/V/AV consistency; all metrics computed on the paired clip set (A&cap;V&cap;AV) with 95% confidence intervals.</li>
         </ol>
       </details>
     </section>