Improvements

app.py

@@ -28,250 +28,6 @@ MODEL_TYPE_LABELS = {
     "random": "Random",
 }
 APP_CSS = """
-:root {
-  --povisle-bg: #f8f7f6;
-  --povisle-surface: #ffffff;
-  --povisle-surface-strong: #ffffff;
-  --povisle-ink: #15171c;
-  --povisle-muted: #5f6773;
-  --povisle-line: #e3dfdc;
-  --povisle-accent: #d7263d;
-  --povisle-accent-dark: #9f1239;
-  --povisle-green: #4f7f18;
-  --povisle-blue: #1f5d8c;
-  --povisle-shadow: 0 18px 46px rgba(39, 33, 31, 0.08);
-}
-body {
-  color-scheme: light;
-  background:
-    linear-gradient(180deg, rgba(255, 255, 255, 0.72), rgba(248, 247, 246, 0.96)),
-    var(--povisle-bg) !important;
-}
-.gradio-container {
-  max-width: 1240px !important;
-  margin: 0 auto !important;
-  padding: 24px 24px 42px !important;
-  background: transparent !important;
-  color: var(--povisle-ink) !important;
-  font-family: Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif !important;
-}
-.contain {
-  gap: 18px !important;
-}
-.povisle-hero {
-  padding: 34px 0 16px;
-}
-.povisle-kicker {
-  color: var(--povisle-accent-dark);
-  font-size: 0.78rem;
-  font-weight: 800;
-  letter-spacing: 0.12em;
-  margin: 0 0 10px;
-  text-transform: uppercase;
-}
-.povisle-hero h1 {
-  color: var(--povisle-ink);
-  font-size: clamp(2.4rem, 5vw, 5.3rem);
-  font-weight: 850;
-  letter-spacing: 0;
-  line-height: 0.94;
-  margin: 0;
-}
-.povisle-hero p {
-  color: var(--povisle-muted);
-  font-size: 1.04rem;
-  line-height: 1.65;
-  margin: 18px 0 0;
-  max-width: 760px;
-}
-.povisle-stat-row {
-  display: grid;
-  gap: 10px;
-  grid-template-columns: repeat(4, minmax(0, 1fr));
-  margin-top: 24px;
-  max-width: 900px;
-}
-.povisle-stat {
-  background: rgba(255, 255, 255, 0.72);
-  border: 1px solid var(--povisle-line);
-  border-radius: 8px;
-  padding: 13px 15px;
-}
-.povisle-stat strong {
-  color: var(--povisle-ink);
-  display: block;
-  font-size: 1.28rem;
-  line-height: 1.1;
-}
-.povisle-stat span {
-  color: var(--povisle-muted);
-  display: block;
-  font-size: 0.78rem;
-  margin-top: 5px;
-}
-.tabs {
-  border: 0 !important;
-}
-.tab-nav {
-  border-bottom: 1px solid var(--povisle-line) !important;
-}
-.tabitem {
-  background: transparent !important;
-  border: 0 !important;
-  padding-top: 18px !important;
-}
-#leaderboard-search textarea,
-#leaderboard-search input {
-  min-height: 48px !important;
-}
-#leaderboard-search,
-#category-view-select,
-#leaderboard-table,
-#examples-table {
-  border-radius: 8px !important;
-}
-#leaderboard-table,
-#examples-table {
-  box-shadow: var(--povisle-shadow);
-}
-#leaderboard-table table,
-#examples-table table {
-  border-collapse: separate !important;
-  border-spacing: 0 !important;
-}
-#leaderboard-table table th,
-#examples-table table th {
-  background: #efedeb !important;
-  color: #272a30 !important;
-  font-size: 0.78rem !important;
-  font-weight: 780 !important;
-}
-#leaderboard-table table td,
-#examples-table table td {
-  border-color: #e7e3e0 !important;
-}
-#leaderboard-table table tbody tr:nth-child(even) td,
-#examples-table table tbody tr:nth-child(even) td {
-  background: #fbfaf9;
-}
-#leaderboard-table table tbody tr:hover td,
-#examples-table table tbody tr:hover td {
-  background: #fff1f2 !important;
-}
-.povisle-section-title {
-  color: var(--povisle-ink);
-  font-size: 1.55rem;
-  font-weight: 800;
-  letter-spacing: 0;
-  margin: 28px 0 10px;
-}
-.povisle-dataset-card {
-  background: var(--povisle-surface);
-  border: 1px solid var(--povisle-line);
-  border-radius: 8px;
-  box-shadow: var(--povisle-shadow);
-  margin-top: 24px;
-  padding: 24px;
-}
-.povisle-dataset-card p {
-  color: var(--povisle-muted);
-  font-size: 0.98rem;
-  line-height: 1.62;
-  margin: 0;
-  max-width: 920px;
-}
-.block label span,
-.block .label-wrap span {
-  color: #3c4149 !important;
-  font-weight: 680 !important;
-}
-footer {
-  display: none !important;
-}
-#examples-table table td,
-#examples-table table th,
-#examples-table table td *,
-#examples-table table th *,
-#examples-table [role="gridcell"],
-#examples-table [role="columnheader"],
-#examples-table [role="gridcell"] *,
-#examples-table [role="columnheader"] *,
-#examples-table * {
-  white-space: pre-wrap !important;
-  word-break: break-word;
-  overflow-wrap: anywhere;
-}
-#examples-table table td:nth-child(1),
-#examples-table table th:nth-child(1) {
-  min-width: 7rem;
-  width: 7rem;
-}
-#examples-table table td:nth-child(2),
-#examples-table table th:nth-child(2) {
-  min-width: 10rem;
-  width: 10rem;
-}
-#examples-table table td:nth-child(3),
-#examples-table table th:nth-child(3) {
-  min-width: 10rem;
-  width: 10rem;
-}
-#examples-table table td:nth-child(4),
-#examples-table table th:nth-child(4) {
-  min-width: 10rem;
-  width: 10rem;
-  text-align: center;
-  vertical-align: middle;
-}
-#examples-table table td:nth-child(4) img.example-image {
-  display: block;
-  margin: 0 auto;
-  max-width: 9rem;
-  max-height: 9rem;
-  object-fit: contain;
-}
-#examples-table table td:nth-child(5),
-#examples-table table th:nth-child(5) {
-  max-width: 24rem;
-  width: 24rem;
-}
-#examples-table table td:nth-child(6),
-#examples-table table th:nth-child(6) {
-  min-width: 20rem;
-  width: 20rem;
-}
-#examples-table table td:nth-child(7),
-#examples-table table th:nth-child(7) {
-  min-width: 14rem;
-  width: 14rem;
-}
-#examples-table table td:nth-child(8),
-#examples-table table th:nth-child(8) {
-  min-width: 14rem;
-  width: 14rem;
-}
-#examples-table table td:nth-child(9),
-#examples-table table th:nth-child(9),
-#examples-table table td:nth-child(10),
-#examples-table table th:nth-child(10) {
-  min-width: 8rem;
-  width: 8rem;
-}
-@media (max-width: 760px) {
-  .gradio-container {
-    padding: 18px 14px 32px !important;
-  }
-  .povisle-hero {
-    padding-top: 22px;
-  }
-  .povisle-stat-row {
-    grid-template-columns: 1fr;
-  }
-  .povisle-dataset-card {
-    padding: 18px;
-  }
-}
-
 :root {
   --povisle-bg: #f8f7f6;
   --povisle-surface: #ffffff;
@@ -292,19 +48,26 @@ footer {
   --povisle-mono: "JetBrains Mono", ui-monospace, SFMono-Regular, Menlo, monospace;
 }
 body {
+  color-scheme: light;
   background: var(--povisle-bg) !important;
   color: var(--povisle-ink) !important;
   font-family: var(--povisle-sans) !important;
   line-height: 1.7;
 }
 .gradio-container {
-  max-width: 1180px !important;
-  padding: 0 24px 42px !important;
+  max-width: 1480px !important;
+  margin: 0 auto !important;
+  padding: 0 14px 42px !important;
+  background: transparent !important;
+  color: var(--povisle-ink) !important;
   font-family: var(--povisle-sans) !important;
 }
 .contain {
   gap: 0 !important;
 }
+footer {
+  display: none !important;
+}
 .povisle-hero {
   background: transparent;
   border: 0;
@@ -346,6 +109,10 @@ body {
 .povisle-title-accent {
   color: var(--povisle-accent) !important;
 }
+.povisle-hero em {
+  color: var(--povisle-ink);
+  font-style: italic;
+}
 .povisle-hero p {
   color: var(--povisle-muted);
   font-size: 0.98rem;
@@ -436,26 +203,33 @@ body {
   transform: translateY(-1px);
 }
 .povisle-stat-row {
+  display: grid;
   gap: 16px;
+  grid-template-columns: repeat(auto-fit, minmax(150px, 1fr));
   margin: 30px auto 0;
   max-width: 760px;
 }
 .povisle-stat {
   background: var(--povisle-bg);
-  border-color: var(--povisle-line);
+  border: 1px solid var(--povisle-line);
   border-radius: 10px;
   padding: 18px 14px;
   text-align: center;
 }
 .povisle-stat strong {
   color: var(--povisle-accent) !important;
+  display: block;
   font-family: var(--povisle-serif);
   font-size: 1.7rem;
   font-weight: 600;
+  line-height: 1.1;
 }
 .povisle-stat span {
   color: var(--povisle-faint);
+  display: block;
+  font-size: 0.78rem;
   font-weight: 500;
+  margin-top: 5px;
 }
 .tab-nav {
   justify-content: center !important;
@@ -673,7 +447,7 @@ body {
   border-radius: 0;
   box-shadow: none;
   margin: 30px auto 8px;
-  max-width: 1120px;
+  max-width: 1440px;
   padding: 12px 0 4px;
 }
 .povisle-dataset-card p {
@@ -700,22 +474,22 @@ body {
   margin-top: 0;
 }
 .povisle-category-layout {
-  align-items: center;
+  align-items: start;
   display: grid;
   gap: 24px;
-  grid-template-columns: minmax(0, 2fr) minmax(0, 3fr);
+  grid-template-columns: repeat(2, minmax(0, 1fr));
 }
 .povisle-task-layout {
   align-items: start;
   display: grid;
   gap: 24px;
-  grid-template-columns: minmax(0, 1fr) minmax(260px, 0.9fr);
+  grid-template-columns: repeat(2, minmax(0, 1fr));
 }
 .povisle-creation-layout {
-  align-items: center;
+  align-items: start;
   display: grid;
   gap: 24px;
-  grid-template-columns: minmax(0, 1fr) minmax(0, 1.25fr);
+  grid-template-columns: repeat(2, minmax(0, 1fr));
 }
 .povisle-creation-figure {
   background: var(--povisle-surface);
@@ -760,11 +534,11 @@ body {
 }
 .povisle-examples-heading {
   margin: 38px auto 18px;
-  max-width: 1120px;
+  max-width: 1440px;
 }
 .povisle-leaderboard-heading {
   margin: 26px auto 18px;
-  max-width: 1120px;
+  max-width: 1440px;
 }
 .povisle-leaderboard-heading .povisle-section-title {
   margin-bottom: 10px;
@@ -774,7 +548,7 @@ body {
   font-size: 0.97rem;
   line-height: 1.7;
   margin: 0;
-  max-width: 760px;
+  max-width: 100%;
 }
 .povisle-examples-heading p {
   color: var(--povisle-muted);
@@ -785,7 +559,7 @@ body {
 .povisle-acknowledgement {
   border-top: 1px solid var(--povisle-line);
   margin: 46px auto 0;
-  max-width: 1120px;
+  max-width: 1440px;
   padding: 24px 0 0;
 }
 .povisle-acknowledgement .povisle-section-title {
@@ -797,17 +571,40 @@ body {
   font-size: 0.94rem;
   line-height: 1.7;
   margin: 0;
-  max-width: 820px;
+  max-width: 100%;
+}
+.povisle-citation {
+  border-top: 1px solid var(--povisle-line);
+  margin: 30px auto 0;
+  max-width: 1440px;
+  padding: 24px 0 0;
+}
+.povisle-citation .povisle-section-title {
+  font-size: 1.15rem;
+  margin-bottom: 8px;
+}
+.povisle-citation pre {
+  background: var(--povisle-surface);
+  border: 1px solid var(--povisle-line);
+  border-radius: 8px;
+  color: var(--povisle-ink);
+  font-family: var(--povisle-mono);
+  font-size: 0.82rem;
+  line-height: 1.55;
+  margin: 0;
+  overflow-x: auto;
+  padding: 14px;
+  white-space: pre;
 }
 #examples-filter-row {
   background: var(--povisle-surface) !important;
   border: 1px solid var(--povisle-line) !important;
   border-radius: 10px !important;
   gap: 0 !important;
-  margin: 0 12px 16px !important;
+  margin: 0 0 16px !important;
   overflow: hidden !important;
   padding: 0 !important;
-  width: calc(100% - 24px) !important;
+  width: 100% !important;
 }
 #examples-filter-row > * {
   background: transparent !important;
@@ -978,22 +775,44 @@ body {
   border-radius: 8px;
   padding: 16px;
 }
-.povisle-task-chart-row {
+.povisle-task-chart-legend {
+  display: flex;
+  flex-wrap: wrap;
+  gap: 10px 14px;
+  margin-bottom: 16px;
+}
+.povisle-task-chart-legend span {
   align-items: center;
-  display: grid;
-  gap: 10px;
-  grid-template-columns: minmax(92px, 0.8fr) minmax(120px, 1.4fr) 44px;
-  min-height: 28px;
+  color: var(--povisle-muted);
+  display: inline-flex;
+  font-size: 0.78rem;
+  gap: 6px;
+  line-height: 1.2;
+}
+.povisle-task-chart-legend span::before {
+  background: var(--segment-color);
+  border-radius: 999px;
+  content: "";
+  display: inline-block;
+  height: 8px;
+  width: 8px;
+}
+.povisle-task-split + .povisle-task-split {
+  margin-top: 18px;
 }
-.povisle-task-chart-row + .povisle-task-chart-row {
-  margin-top: 10px;
+.povisle-task-split-header {
+  align-items: baseline;
+  display: flex;
+  justify-content: space-between;
+  gap: 12px;
+  margin-bottom: 8px;
 }
-.povisle-task-chart-row span {
+.povisle-task-split-header span {
   color: var(--povisle-muted);
   font-size: 0.82rem;
   line-height: 1.25;
 }
-.povisle-task-chart-row strong {
+.povisle-task-split-header strong {
   color: var(--povisle-ink);
   font-family: var(--povisle-mono);
   font-size: 0.82rem;
@@ -1003,13 +822,25 @@ body {
 .povisle-task-chart-track {
   background: var(--povisle-soft);
   border-radius: 999px;
-  height: 8px;
+  display: flex;
+  height: 24px;
   overflow: hidden;
 }
-.povisle-task-chart-track div {
-  background: var(--povisle-accent);
-  border-radius: inherit;
+.povisle-task-chart-segment {
+  align-items: center;
+  background: var(--segment-color);
+  color: #ffffff;
+  display: flex;
+  font-family: var(--povisle-mono);
+  font-size: 0.72rem;
+  font-weight: 650;
   height: 100%;
+  justify-content: center;
+  line-height: 1;
+  min-width: 28px;
+}
+.povisle-task-chart-segment + .povisle-task-chart-segment {
+  border-left: 1px solid rgba(255, 255, 255, 0.75);
 }
 .block label span,
 .block .label-wrap span {
@@ -1336,40 +1167,40 @@ APP_HEAD = """
 <link href="https://fonts.googleapis.com/css2?family=Source+Serif+4:ital,opsz,wght@0,8..60,300;0,8..60,400;0,8..60,600;0,8..60,700;1,8..60,300;1,8..60,400&family=DM+Sans:ital,wght@0,300;0,400;0,500;0,600;1,300&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet">
 """
 HERO_HTML = """
-<section class="povisle-hero" style="background: transparent; border: 0; box-shadow: none; margin: 0 auto 34px; max-width: 1120px; padding: 84px 28px 48px; text-align: center;">
-  <h1 style="color: #181416; display: block; font-family: 'Source Serif 4', Georgia, serif; font-size: clamp(1.7rem, 3.2vw, 3rem); font-weight: 600; letter-spacing: 0; line-height: 1.08; margin: 0 auto 12px; max-width: 980px; white-space: nowrap;">
-    <em style="color: #181416; font-style: italic;">Jako Tako</em> or Fluent? Presenting <span class="povisle-title-accent" style="color: #d7263d;">PoVisLE</span>
+<section class="povisle-hero">
+  <h1>
+    <em>Jako Tako</em> or Fluent? Presenting <span class="povisle-title-accent">PoVisLE</span>
   </h1>
-  <p style="color: #5f585b; font-family: 'DM Sans', system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif; font-size: 0.98rem; line-height: 1.8; margin: 18px auto 0; max-width: 720px;">
+  <p>
     We introduce PoVisLE, a monocultural vision-language benchmark for Polish designed to evaluate
     culturally grounded multimodal understanding under a grounded evaluation paradigm, where language
     is interpreted in interaction with visual context. The dataset contains 1,117 images and 2,366
     manually annotated VQA pairs.
   </p>
-  <div class="povisle-authors" style="color: #5f585b; font-family: 'DM Sans', system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif; font-size: 0.9rem; line-height: 1.65; margin: 24px auto 0; max-width: 760px;">
+  <div class="povisle-authors">
     <strong>Anna Ko&#322;os</strong> &middot; <strong>Grzegorz Statkiewicz</strong> &middot; <strong>Karolina Seweryn</strong> &middot;
     <strong>Katarzyna Kowol</strong> &middot; <strong>Karolina Piosek</strong> &middot; <strong>Wojciech Kusa</strong><br>
     NASK National Research Institute, Warsaw, Poland
   </div>
-  <div class="povisle-links-row" style="display: flex; flex-wrap: wrap; gap: 10px; justify-content: center; margin-top: 30px;">
-    <a href="https://huggingface.co/collections/NASK-PIB/povisle" class="povisle-btn povisle-btn-dataset" target="_blank" style="align-items: center; background: #edf3f9; border: 1px solid rgba(44, 95, 138, 0.2); border-radius: 6px; color: #2c5f8a; display: inline-flex; font-family: 'DM Sans', system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif; font-size: 0.84rem; font-weight: 500; gap: 7px; line-height: 1; padding: 10px 18px; text-decoration: none;">
+  <div class="povisle-links-row">
+    <a href="https://huggingface.co/collections/NASK-PIB/povisle" class="povisle-btn povisle-btn-dataset" target="_blank">
       <svg width="15" height="15" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" aria-hidden="true"><ellipse cx="12" cy="5" rx="9" ry="3"/><path d="M21 12c0 1.66-4 3-9 3s-9-1.34-9-3"/><path d="M3 5v14c0 1.66 4 3 9 3s9-1.34 9-3V5"/></svg>
-      Dataset
+      Dataset (Validation)
     </a>
-    <a href="https://github.com/NASK-NLP/PoVisLE" class="povisle-btn povisle-btn-outline" target="_blank" style="align-items: center; background: #ffffff; border: 1px solid #e3dfdc; border-radius: 6px; color: #181416; display: inline-flex; font-family: 'DM Sans', system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif; font-size: 0.84rem; font-weight: 500; gap: 7px; line-height: 1; padding: 10px 18px; text-decoration: none;">
+    <a href="https://github.com/NASK-NLP/PoVisLE" class="povisle-btn povisle-btn-outline" target="_blank">
       <svg width="15" height="15" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" aria-hidden="true"><path d="M9 19c-5 1.5-5-2.5-7-3m14 6v-3.87a3.37 3.37 0 0 0-.94-2.61c3.14-.35 6.44-1.54 6.44-7A5.44 5.44 0 0 0 20 4.77 5.07 5.07 0 0 0 19.91 1S18.73.65 16 2.48a13.38 13.38 0 0 0-7 0C6.27.65 5.09 1 5.09 1A5.07 5.07 0 0 0 5 4.77a5.44 5.44 0 0 0-1.5 3.78c0 5.42 3.3 6.61 6.44 7A3.37 3.37 0 0 0 9 18.13V22"/></svg>
       Code
     </a>
-    <a href="https://arxiv.org/" class="povisle-btn povisle-btn-outline" target="_blank" style="align-items: center; background: #ffffff; border: 1px solid #e3dfdc; border-radius: 6px; color: #181416; display: inline-flex; font-family: 'DM Sans', system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif; font-size: 0.84rem; font-weight: 500; gap: 7px; line-height: 1; padding: 10px 18px; text-decoration: none;">
+    <a href="https://arxiv.org/" class="povisle-btn povisle-btn-outline" target="_blank">
       <svg class="arxiv-icon" width="23" height="23" viewBox="0 0 448 512" aria-hidden="true"><path fill="currentColor" d="m 119.65,351.996 c -5.84961,0.13477 -11.1943,-3.29883 -13.502,-8.67578 -2.19629,-5.27051 -0.61914,-8.9668 4.19727,-15.8652 7.05469,-10.3799 78.8242,-96.5625 78.8242,-96.5625 l -15.8828,-14.8633 c -13.3809,-13.3779 -13.9561,-31.333 -1.50977,-43.7754 l 18.4922,-17.6133 -51.5977,-63.377 c -4.00586,-4.26758 -6.48535,-11.7559 -4.24805,-17.1309 2.27832,-5.53613 7.69727,-9.12891 13.6836,-9.07031 3.83398,0.0957 7.43262,1.87402 9.83789,4.86133 l 61.3691,57.0566 94.5762,-90.0703 c 3.19434,-3.08398 7.44336,-4.83984 11.8828,-4.91016 1.60449,0.0039 3.19824,0.245117 4.73242,0.714844 5.7793,1.80566 10.249,6.41797 11.8711,12.252 1.2998,5.47363 -0.27637,11.2334 -4.18164,15.2832 l -83.0859,100.011996 14.8789,13.834 c 11.0957,10.0029 11.1543,27.3906 0.12695,37.4688 l -16.2949,15.6309 56.2559,66.4434 0.0742,0.0859 0.0664,0.0899 c 5.02734,6.53125 7.43164,11.5615 4.83984,17.9395 -3.13379,5.96875 -8.69727,10.29 -15.2559,11.8516 -0.67676,0.0908 -1.35938,0.13574 -2.04297,0.13671 l -0.004,-0.0117 c -4.42871,-0.27051 -8.61035,-2.13086 -11.7754,-5.24023 l -0.13086,-0.10743 -0.12304,-0.11132 -65.207,-59.127 -89.8965,86.2402 c 0,0 -5.33398,6.47754 -10.9707,6.61133 z m 178.104,-33.041 c 0.47852,-0.002 0.95703,-0.0332 1.43164,-0.0957 4.84277,-1.33301 8.95605,-4.54004 11.4316,-8.91016 1.44922,-3.5625 1.00293,-6.45703 -4.19727,-13.2148 l -56.0586,-66.2188 -26.375,25.3027 64.9551,58.9062 c 2.33887,2.41504 5.46484,3.91113 8.8125,4.2168 v 0.0137 z M 192.436,227.402 334.446,57.244 c 2.78711,-3.48926 4.5293,-6.97949 3.3418,-10.9121 -1.16113,-4.30273 -4.43457,-7.71777 -8.68555,-9.05664 -1.08105,-0.333984 -2.20508,-0.503906 -3.33594,-0.505859 -3.20801,0.07617 -6.26953,1.35645 -8.57617,3.58789 l -142.033,135.284999 c -11.1719,11.1719 -9.48242,26.0195 1.39258,36.8945 z"/></svg>
       Paper
     </a>
   </div>
-  <div class="povisle-stat-row" aria-label="Dataset summary" style="display: grid; gap: 16px; grid-template-columns: repeat(auto-fit, minmax(150px, 1fr)); margin: 30px auto 0; max-width: 760px;">
-    <div class="povisle-stat" style="background: #f8f7f6; border: 1px solid #e3dfdc; border-radius: 10px; padding: 18px 14px; text-align: center;"><strong style="color: #d7263d; display: block; font-family: 'Source Serif 4', Georgia, serif; font-size: 1.7rem; font-weight: 600; line-height: 1.1;">1,117</strong><span style="color: #8b8588; display: block; font-family: 'DM Sans', system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif; font-size: 0.78rem; font-weight: 500; margin-top: 5px;">images</span></div>
-    <div class="povisle-stat" style="background: #f8f7f6; border: 1px solid #e3dfdc; border-radius: 10px; padding: 18px 14px; text-align: center;"><strong style="color: #d7263d; display: block; font-family: 'Source Serif 4', Georgia, serif; font-size: 1.7rem; font-weight: 600; line-height: 1.1;">2,366</strong><span style="color: #8b8588; display: block; font-family: 'DM Sans', system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif; font-size: 0.78rem; font-weight: 500; margin-top: 5px;">questions</span></div>
-    <div class="povisle-stat" style="background: #f8f7f6; border: 1px solid #e3dfdc; border-radius: 10px; padding: 18px 14px; text-align: center;"><strong style="color: #d7263d; display: block; font-family: 'Source Serif 4', Georgia, serif; font-size: 1.7rem; font-weight: 600; line-height: 1.1;">7</strong><span style="color: #8b8588; display: block; font-family: 'DM Sans', system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif; font-size: 0.78rem; font-weight: 500; margin-top: 5px;">main categories</span></div>
-    <div class="povisle-stat" style="background: #f8f7f6; border: 1px solid #e3dfdc; border-radius: 10px; padding: 18px 14px; text-align: center;"><strong style="color: #d7263d; display: block; font-family: 'Source Serif 4', Georgia, serif; font-size: 1.7rem; font-weight: 600; line-height: 1.1;">3</strong><span style="color: #8b8588; display: block; font-family: 'DM Sans', system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif; font-size: 0.78rem; font-weight: 500; margin-top: 5px;">task formats</span></div>
+  <div class="povisle-stat-row" aria-label="Dataset summary">
+    <div class="povisle-stat"><strong>1,117</strong><span>images</span></div>
+    <div class="povisle-stat"><strong>2,366</strong><span>questions</span></div>
+    <div class="povisle-stat"><strong>7</strong><span>main categories</span></div>
+    <div class="povisle-stat"><strong>3</strong><span>task formats</span></div>
   </div>
 </section>
 """
@@ -1389,49 +1220,61 @@ DATASET_DESCRIPTION_HTML = f"""
   <div class="povisle-about-grid">
     <div class="povisle-about-copy">
       <h3>Tasks</h3>
-      <p>
-        During annotation, each VQA pair is assigned one of three task types. These
-        are multiple-choice, binary yes/no, and open-ended questions. All questions
-        are designed to require image understanding, and the answer should not be
-        obtainable from textual knowledge alone without reference to the image.
-      </p>
       <div class="povisle-task-layout">
         <div>
+          <p>
+            During annotation, each VQA pair is assigned one of three task types. These
+            are multiple-choice, binary yes/no, and open-ended questions. All questions
+            are designed to require image understanding, and the answer should not be
+            obtainable from textual knowledge alone without reference to the image.
+          </p>
           <ul class="povisle-task-list">
             <li><strong>Multiple-choice questions</strong> include answer options appended below the question with letter labels.</li>
             <li><strong>Yes/no questions</strong> use the raw question as the prompt and are evaluated as binary answers.</li>
             <li><strong>Open-ended questions</strong> also use the raw question as the prompt, without appended answer options.</li>
           </ul>
         </div>
-        <div class="povisle-task-chart" aria-label="Question distribution by task format">
-          <div class="povisle-task-chart-row">
-            <span>Multiple choice</span>
-            <div class="povisle-task-chart-track"><div style="width: 36.1%;"></div></div>
-            <strong>855</strong>
+        <div class="povisle-task-chart" aria-label="Question distribution by task format and split">
+          <div class="povisle-task-chart-legend" aria-hidden="true">
+            <span style="--segment-color: #d7263d;">Multiple choice</span>
+            <span style="--segment-color: #2c5f8a;">Yes/no</span>
+            <span style="--segment-color: #2a7a4e;">Open-ended</span>
           </div>
-          <div class="povisle-task-chart-row">
-            <span>Yes/no</span>
-            <div class="povisle-task-chart-track"><div style="width: 36.7%;"></div></div>
-            <strong>868</strong>
+          <div class="povisle-task-split">
+            <div class="povisle-task-split-header">
+              <span>Test split</span>
+              <strong>1,960</strong>
+            </div>
+            <div class="povisle-task-chart-track" title="Test: 643 multiple-choice, 714 yes/no, 603 open-ended">
+              <div class="povisle-task-chart-segment" style="--segment-color: #d7263d; width: 32.8%;" aria-label="Multiple choice: 643, 32.8%">643</div>
+              <div class="povisle-task-chart-segment" style="--segment-color: #2c5f8a; width: 36.4%;" aria-label="Yes/no: 714, 36.4%">714</div>
+              <div class="povisle-task-chart-segment" style="--segment-color: #2a7a4e; width: 30.8%;" aria-label="Open-ended: 603, 30.8%">603</div>
+            </div>
           </div>
-          <div class="povisle-task-chart-row">
-            <span>Open-ended</span>
-            <div class="povisle-task-chart-track"><div style="width: 27.2%;"></div></div>
-            <strong>643</strong>
+          <div class="povisle-task-split">
+            <div class="povisle-task-split-header">
+              <span>Validation split</span>
+              <strong>406</strong>
+            </div>
+            <div class="povisle-task-chart-track" title="Validation: 212 multiple-choice, 154 yes/no, 40 open-ended">
+              <div class="povisle-task-chart-segment" style="--segment-color: #d7263d; width: 52.2%;" aria-label="Multiple choice: 212, 52.2%">212</div>
+              <div class="povisle-task-chart-segment" style="--segment-color: #2c5f8a; width: 37.9%;" aria-label="Yes/no: 154, 37.9%">154</div>
+              <div class="povisle-task-chart-segment" style="--segment-color: #2a7a4e; width: 9.9%;" aria-label="Open-ended: 40, 9.9%">40</div>
+            </div>
           </div>
         </div>
       </div>
     </div>
     <div class="povisle-about-copy">
       <h3>Categories</h3>
-      <p class="povisle-category-intro">
-        The taxonomy is adapted from PLCC and refined for the VQA setting. Grammar
-        and vocabulary are merged into a unified Language category, while the hierarchy
-        supports fine-grained diagnostics across cultural, linguistic, and visual
-        reasoning domains. The dataset is organized into the following main categories.
-      </p>
       <div class="povisle-category-layout">
         <div>
+          <p class="povisle-category-intro">
+            The taxonomy is adapted from PLCC and refined for the VQA setting. Grammar
+            and vocabulary are merged into a unified Language category, while the hierarchy
+            supports fine-grained diagnostics across cultural, linguistic, and visual
+            reasoning domains. The dataset is organized into the following main categories.
+          </p>
           <ul class="povisle-category-list">
             <li><strong>Art and Entertainment</strong> covers Polish and Poland-related artistic, media, and cultural references, including architecture, film, literature, music, paintings, sculpture, sport, and media.</li>
             <li><strong>Culture and Tradition</strong> covers shared customs, practices, symbols, cuisine, religion, traditions, pop culture, and regional or ethnic cultural variation.</li>
@@ -1477,6 +1320,13 @@ DATASET_DESCRIPTION_HTML = f"""
           grounded, unambiguous, linguistically natural, and suitable for deterministic
           evaluation.
         </p>
+        <p>
+          The benchmark is divided into a held-out test split for final evaluation and
+          a public validation split. The validation split is intended mainly to
+          illustrate the range of question types, so it is not sampled from the same
+          distribution as the test set. In particular, it contains fewer open-ended
+          questions, which are largely retained in the held-out test split.
+        </p>
       </div>
       <div class="povisle-creation-figure">
         <img src="{DATASET_CREATION_IMAGE_URL}" alt="Overview of the PoVisLE dataset construction process">
@@ -1486,17 +1336,18 @@ DATASET_DESCRIPTION_HTML = f"""
   <div class="povisle-about-copy">
     <h3>Evaluation Protocol</h3>
     <p>
-      Models receive the image and a Polish prompt specifying the expected answer format. Accuracy
-      is the main metric. Multiple-choice questions use circular evaluation: answer options are
-      cyclically rotated, and a prediction is counted as correct only if the model selects the gold
-      answer under every rotation. This reduces option-position bias while keeping evaluation
-      efficient.
+      Models receive the image and a Polish prompt specifying the expected answer format, length,
+      word order, and, where relevant, grammatical form. Macro accuracy is the main metric.
+      Multiple-choice questions use circular evaluation: answer options are cyclically rotated, and
+      a prediction is counted as correct only if the model selects the gold answer under every
+      rotation. This reduces option-position bias while keeping evaluation efficient.
     </p>
     <p>
-      Yes/no items are evaluated as single-pass binary answers in Polish. Open-ended predictions are
-      compared with the gold answer after normalization, including lowercasing, diacritic removal,
-      and alphanumeric/whitespace normalization. A response is correct when it exactly matches the
-      normalized gold answer or contains it as a substring.
+      Yes/no and open-ended questions are evaluated in a single pass. Yes/no questions require a
+      binary answer in Polish. Open-ended predictions are compared against the gold answers, with
+      correct diacritics required in all cases and correct capitalization required where relevant.
+      For selected questions, multiple answer variants are accepted through predefined inclusion
+      patterns developed through iterative human validation.
     </p>
   </div>
 </section>
@@ -2000,7 +1851,7 @@ with gr.Blocks(
             <section class="povisle-leaderboard-heading">
               <div class="povisle-section-label">Results</div>
               <h2 class="povisle-section-title">Leaderboard</h2>
-              <p>Compare model performance by category or task type across the test and validation splits.</p>
+              <p>Compare model performance by category or task type across the test and validation splits. Overall and category scores report <strong>macro accuracy</strong>, while task columns report task-level accuracy.</p>
             </section>
             """
         )
@@ -2030,7 +1881,16 @@ with gr.Blocks(
         """
         <section class="povisle-acknowledgement">
           <h2 class="povisle-section-title">Acknowledgement</h2>
-          <p>This work was supported by the Ministry of Digital Affairs (subsidy no. 4/WII/DBI/2026).</p>
+          <p>This work was supported by the Polish Ministry of Digital Affairs (subsidy no. 4/WII/DBI/2026). The computational resources were provided by the Polish high-performance computing infrastructure PLGrid (HPC Center: ACK Cyfronet AGH) under computational grant no. PLG/2026/019138.</p>
+        </section>
+        <section class="povisle-citation">
+          <h2 class="povisle-section-title">Citation</h2>
+          <pre>@article{kolos2026povisle,
+  title   = {Jako Tako or Fluent? Presenting PoVisLE: A Polish Vision-Language Evaluation},
+  author  = {Ko{\\l}os, Anna and Statkiewicz, Grzegorz and Seweryn, Karolina and Kowol, Katarzyna and Piosek, Karolina and Kusa, Wojciech},
+  journal = {arXiv preprint},
+  year    = {2026}
+}</pre>
         </section>
         """
     )