Align cross-judge layout and remove full-set label

index.html

@@ -204,16 +204,16 @@
             robustness and expose judge-specific gaps.
           </p>
         </div>
+        <div class="text-content result-copy result-copy-wide">
+          <p>
+            Across both judges, <strong>WildToM-Reasoner</strong> ranks first. On Gemini grading,
+            its lead widens, while rank correlation remains high
+            (<strong>Spearman &rho; = 0.867</strong>), indicating that the OE ranking trend is
+            robust to judge replacement.
+          </p>
+        </div>
         <div class="analysis-grid">
           <div class="analysis-main">
-            <div class="text-content result-copy">
-              <p>
-                Across both judges, <strong>WildToM-Reasoner</strong> ranks first. On Gemini
-                common-exam grading, its lead widens, while rank correlation remains high
-                (<strong>Spearman &rho; = 0.867</strong>), indicating that the OE ranking trend is
-                robust to judge replacement.
-              </p>
-            </div>
             <section class="cross-judge-card" aria-label="Cross-judge model ranking comparison">
               <div class="cross-toolbar">
                 <div class="toolbar-row">
@@ -224,10 +224,6 @@
                   <span class="toolbar-label">Judge</span>
                   <div class="toggle-group" id="judge-toggle"></div>
                 </div>
-                <div class="toolbar-row">
-                  <span class="toolbar-label">Metric</span>
-                  <div class="toggle-group metric" id="metric-toggle"></div>
-                </div>
               </div>
               <div class="results-caption" id="results-caption"></div>
               <div class="results-panel" id="results-table"></div>

script.js

@@ -161,7 +161,7 @@ const filters = ["Belief", "Desire", "Intention", "Emotion", "Knowledge"];
 
 const judgeResults = {
   gpt4o: {
-    label: "GPT-4o (full set)",
+    label: "GPT-4o",
     deltaLabel: "Gemini",
     rows: [
       { model: "WildToM-Reasoner", rank: 1, oeAcc: 32.7, oeScr: 2.6, isOurs: true },
@@ -211,7 +211,6 @@ const showcaseRoot = document.getElementById("showcase-browser");
 const resultsRoot = document.getElementById("results-table");
 const taskToggleRoot = document.getElementById("task-toggle");
 const judgeToggleRoot = document.getElementById("judge-toggle");
-const metricToggleRoot = document.getElementById("metric-toggle");
 const resultsCaptionRoot = document.getElementById("results-caption");
 const carouselState = {
   activeDimension: "Belief",
@@ -385,7 +384,6 @@ function renderControls() {
     return;
   }
   const judgeToggleRow = judgeToggleRoot.closest(".toolbar-row");
-  const metricToggleRow = metricToggleRoot ? metricToggleRoot.closest(".toolbar-row") : null;
 
   const taskItems = [
     { key: "oe", label: "OE" },
@@ -404,21 +402,15 @@ function renderControls() {
   });
 
   judgeToggleRoot.innerHTML = "";
-  if (metricToggleRoot) {
-    metricToggleRoot.innerHTML = "";
-  }
 
   if (crossJudgeState.activeTask === "oe") {
     judgeToggleRoot.classList.remove("is-hidden");
     if (judgeToggleRow) {
       judgeToggleRow.classList.remove("is-hidden");
     }
-    if (metricToggleRow) {
-      metricToggleRow.classList.add("is-hidden");
-    }
 
     const judgeItems = [
-      { key: "gpt4o", label: "GPT-4o (full set)" },
+      { key: "gpt4o", label: "GPT-4o" },
       { key: "gemini", label: "Gemini-2.5-Flash" }
     ];
     judgeItems.forEach((item) => {
@@ -434,9 +426,6 @@ function renderControls() {
   if (judgeToggleRow) {
     judgeToggleRow.classList.add("is-hidden");
   }
-  if (metricToggleRow) {
-    metricToggleRow.classList.add("is-hidden");
-  }
 }
 
 function renderOeResults(activeJudge) {

styles.css

@@ -358,13 +358,14 @@ code {
   display: grid;
   grid-template-columns: minmax(0, 1fr) minmax(0, 1fr);
   gap: 14px;
-  align-items: start;
+  align-items: stretch;
 }
 
 .stats-left-stack {
   display: grid;
   gap: 10px;
   align-content: start;
+  height: 100%;
 }
 
 .distribution-figure {
@@ -383,6 +384,7 @@ code {
 .table-stack {
   display: grid;
   gap: 10px;
+  height: 100%;
 }
 
 .dimension-grid {
@@ -416,6 +418,8 @@ code {
   display: grid;
   grid-template-columns: repeat(2, minmax(0, 1fr));
   gap: 10px;
+  height: 100%;
+  align-items: stretch;
 }
 
 .table-card {
@@ -423,6 +427,7 @@ code {
   border-radius: 12px;
   background: #ffffff;
   padding: 12px 12px 8px;
+  height: 100%;
 }
 
 .table-card h3 {
@@ -463,19 +468,16 @@ code {
   display: grid;
   grid-template-columns: minmax(0, 1.15fr) minmax(320px, 0.85fr);
   gap: 16px;
-  align-items: stretch;
+  align-items: start;
 }
 
 .analysis-main {
-  display: grid;
-  grid-template-rows: auto 1fr;
   min-height: 100%;
 }
 
 .analysis-side {
   display: grid;
   gap: 12px;
-  margin-top: 92px;
 }
 
 .text-content {
@@ -490,6 +492,16 @@ code {
   margin-bottom: 12px;
 }
 
+.result-copy-wide {
+  margin-bottom: 14px;
+}
+
+.result-copy-wide p {
+  text-align: justify;
+  text-justify: inter-word;
+  max-width: none;
+}
+
 .cross-judge-card {
   border: 1px solid var(--line);
   border-radius: 14px;