diff --git a/.github/workflows/pages.yml b/.github/workflows/pages.yml
deleted file mode 100644
index 0c86d03..0000000
--- a/.github/workflows/pages.yml
+++ /dev/null
@@ -1,70 +0,0 @@
-# GitHub Pages deployment - Main website with README as homepage
-name: Deploy to GitHub Pages
-
-on:
-  push:
-    branches: ["main"]
-    paths:
-      - 'README.md'
-      - 'index.md'
-      - 'docs/leaderboard.html'
-      - 'docs/querygym-logo.png'
-      - '_config.yml'
-      - '_layouts/**'
-      - 'Gemfile'
-      - '.github/workflows/pages.yml'
-  workflow_dispatch:
-
-permissions:
-  contents: read
-  pages: write
-  id-token: write
-
-concurrency:
-  group: "pages"
-  cancel-in-progress: false
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Setup Pages
-        uses: actions/configure-pages@v4
-
-      - name: Setup Ruby
-        uses: ruby/setup-ruby@v1
-        with:
-          ruby-version: '3.2'
-          bundler-cache: true
-
-      - name: Install dependencies
-        run: bundle install
-
-      - name: Build with Jekyll
-        run: bundle exec jekyll build
-        env:
-          JEKYLL_ENV: production
-
-      - name: Copy additional files
-        run: |
-          # Copy leaderboard to _site
-          cp docs/leaderboard.html _site/leaderboard.html
-          # Copy logo for the site
-          cp docs/querygym-logo.png _site/querygym-logo.png 2>/dev/null || true
-
-      - name: Upload artifact
-        uses: actions/upload-pages-artifact@v3
-
-  deploy:
-    environment:
-      name: github-pages
-      url: ${{ steps.deployment.outputs.page_url }}
-    runs-on: ubuntu-latest
-    needs: build
-    steps:
-      - name: Deploy to GitHub Pages
-        id: deployment
-        uses: actions/deploy-pages@v4
diff --git a/Gemfile b/Gemfile
deleted file mode 100644
index 25637eb..0000000
--- a/Gemfile
+++ /dev/null
@@ -1,5 +0,0 @@
-source "https://rubygems.org"
-
-gem "jekyll", "~> 4.3"
-gem "kramdown-parser-gfm" # GitHub Flavored Markdown
-gem "webrick" # Required for Ruby 3.0+
diff --git a/README.md b/README.md
index a563260..44e5c43 100644
--- a/README.md
+++ b/README.md
@@ -15,8 +15,10 @@
 </p>
 
 <p align="center">
-  <a href="https://querygym.readthedocs.io/">📚 Documentation</a> •
-  <a href="https://ls3-lab.github.io/QueryGym/leaderboard.html">📊 Leaderboard</a> •
+  <a href="https://querygym.com">🌐 Website</a> •
+  <a href="https://leaderboard.querygym.com">📊 Leaderboard</a> •
+  <a href="https://dashboard.querygym.com">🚀 Dashboard</a> •
+  <a href="https://querygym.readthedocs.io/">📚 Docs</a> •
   <a href="https://pypi.org/project/querygym/">📦 PyPI</a> •
   <a href="https://arxiv.org/abs/2511.15996">📄 Paper</a>
 </p>
diff --git a/_config.yml b/_config.yml
deleted file mode 100644
index cefb360..0000000
--- a/_config.yml
+++ /dev/null
@@ -1,38 +0,0 @@
-# Jekyll configuration for GitHub Pages
-title: QueryGym
-description: A lightweight, reproducible toolkit for LLM-based query reformulation
-url: "https://ls3-lab.github.io"
-baseurl: "/QueryGym"
-
-# Markdown settings
-markdown: kramdown
-highlighter: rouge
-
-# Exclude files from build
-exclude:
-  - Gemfile
-  - Gemfile.lock
-  - node_modules
-  - vendor
-  - .git
-  - .github
-  - tests
-  - querygym
-  - examples
-  - scripts
-  - "*.py"
-  - "*.toml"
-  - Makefile
-  - Dockerfile
-  - Dockerfile.cpu
-  - docker-compose.yml
-  - .dockerignore
-  - .gitignore
-  - requirements*.txt
-  - docs/
-
-# Include specific files
-include:
-  - README.md
-  - index.md
-  - LICENSE
diff --git a/_layouts/default.html b/_layouts/default.html
deleted file mode 100644
index 7809d8f..0000000
--- a/_layouts/default.html
+++ /dev/null
@@ -1,281 +0,0 @@
-<!DOCTYPE html>
-<html lang="en-US">
-  <head>
-    <meta charset="UTF-8">
-    <meta http-equiv="X-UA-Compatible" content="IE=edge">
-    <meta name="viewport" content="width=device-width, initial-scale=1">
-    <title>{{ page.title | default: site.title }}</title>
-    <meta name="description" content="{{ page.description | default: site.description }}">
-    <link rel="preconnect" href="https://fonts.googleapis.com">
-    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
-    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap" rel="stylesheet">
-    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
-    <style>
-      :root {
-        --primary-color: #667eea;
-        --primary-dark: #764ba2;
-        --bg-body: #ffffff;
-        --bg-code: #f6f8fa;
-        --text-primary: #24292f;
-        --text-secondary: #57606a;
-        --border-color: #d0d7de;
-        --header-gradient: linear-gradient(to right, #667eea 0%, #764ba2 100%);
-        --link-color: #0969da;
-      }
-
-      [data-theme="dark"] {
-        --primary-color: #818cf8;
-        --primary-dark: #a78bfa;
-        --bg-body: #0d1117;
-        --bg-code: #161b22;
-        --text-primary: #c9d1d9;
-        --text-secondary: #8b949e;
-        --border-color: #30363d;
-        --header-gradient: linear-gradient(to right, #4338ca 0%, #6b21a8 100%);
-        --link-color: #58a6ff;
-      }
-
-      * {
-        box-sizing: border-box;
-      }
-
-      body {
-        font-family: 'Inter', -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif;
-        font-size: 16px;
-        line-height: 1.6;
-        color: var(--text-primary);
-        background-color: var(--bg-body);
-        margin: 0;
-        padding: 0;
-        transition: background-color 0.3s ease, color 0.3s ease;
-      }
-
-      a {
-        color: var(--link-color);
-        text-decoration: none;
-      }
-
-      a:hover {
-        text-decoration: underline;
-      }
-
-      .page-header {
-        background: var(--header-gradient);
-        padding: 2rem 1rem;
-        text-align: center;
-        color: #fff;
-        position: relative;
-      }
-
-      .header-controls {
-        position: absolute;
-        top: 1rem;
-        right: 1rem;
-        display: flex;
-        gap: 0.5rem;
-      }
-
-      .header-btn {
-        display: inline-flex;
-        align-items: center;
-        justify-content: center;
-        width: 40px;
-        height: 40px;
-        background: rgba(255, 255, 255, 0.15);
-        border: 1px solid rgba(255, 255, 255, 0.3);
-        border-radius: 6px;
-        color: white;
-        cursor: pointer;
-        transition: all 0.2s ease;
-      }
-
-      .header-btn:hover {
-        background: rgba(255, 255, 255, 0.25);
-        text-decoration: none;
-      }
-
-      .project-name {
-        margin: 0;
-        font-size: 2rem;
-        font-weight: 700;
-      }
-
-      .project-tagline {
-        margin: 0.5rem 0 0;
-        opacity: 0.9;
-        font-size: 1.1rem;
-        font-weight: 400;
-      }
-
-      .main-content {
-        max-width: 900px;
-        margin: 0 auto;
-        padding: 2rem 1rem;
-      }
-
-      .main-content h1,
-      .main-content h2,
-      .main-content h3,
-      .main-content h4,
-      .main-content h5,
-      .main-content h6 {
-        color: var(--text-primary);
-        margin-top: 2rem;
-        margin-bottom: 1rem;
-        font-weight: 600;
-      }
-
-      .main-content h1 { font-size: 2rem; border-bottom: 1px solid var(--border-color); padding-bottom: 0.5rem; }
-      .main-content h2 { font-size: 1.5rem; border-bottom: 1px solid var(--border-color); padding-bottom: 0.3rem; }
-      .main-content h3 { font-size: 1.25rem; }
-
-      .main-content p {
-        margin-bottom: 1rem;
-      }
-
-      .main-content ul,
-      .main-content ol {
-        margin-bottom: 1rem;
-        padding-left: 2rem;
-      }
-
-      .main-content li {
-        margin-bottom: 0.5rem;
-      }
-
-      .main-content code {
-        background: var(--bg-code);
-        padding: 0.2rem 0.4rem;
-        border-radius: 4px;
-        font-size: 0.9em;
-        font-family: 'SFMono-Regular', Consolas, 'Liberation Mono', Menlo, monospace;
-      }
-
-      .main-content pre {
-        background: var(--bg-code);
-        padding: 1rem;
-        border-radius: 6px;
-        overflow-x: auto;
-        margin-bottom: 1rem;
-        border: 1px solid var(--border-color);
-      }
-
-      .main-content pre code {
-        background: transparent;
-        padding: 0;
-      }
-
-      .main-content img {
-        max-width: 100%;
-        height: auto;
-      }
-
-      .main-content blockquote {
-        margin: 1rem 0;
-        padding: 0.5rem 1rem;
-        border-left: 4px solid var(--primary-color);
-        background: var(--bg-code);
-        color: var(--text-secondary);
-      }
-
-      .main-content hr {
-        border: none;
-        border-top: 1px solid var(--border-color);
-        margin: 2rem 0;
-      }
-
-      .main-content table {
-        width: 100%;
-        border-collapse: collapse;
-        margin-bottom: 1rem;
-      }
-
-      .main-content th,
-      .main-content td {
-        padding: 0.75rem;
-        border: 1px solid var(--border-color);
-        text-align: left;
-      }
-
-      .main-content th {
-        background: var(--bg-code);
-        font-weight: 600;
-      }
-
-      .site-footer {
-        border-top: 1px solid var(--border-color);
-        margin-top: 2rem;
-        padding: 2rem 1rem;
-        text-align: center;
-        color: var(--text-secondary);
-        font-size: 0.875rem;
-      }
-
-      @media screen and (min-width: 64em) {
-        .page-header {
-          padding: 3rem 2rem;
-        }
-        .project-name {
-          font-size: 2.5rem;
-        }
-        .main-content {
-          padding: 2rem;
-        }
-      }
-    </style>
-  </head>
-  <body>
-    <header class="page-header">
-      <div class="header-controls">
-        <a href="https://github.com/ls3-lab/QueryGym" class="header-btn" title="View on GitHub">
-          <i class="fab fa-github"></i>
-        </a>
-        <button class="header-btn" id="themeToggle" title="Toggle dark mode">
-          <i class="fas fa-moon"></i>
-        </button>
-      </div>
-      <h1 class="project-name">{{ site.title | default: "QueryGym" }}</h1>
-      <h2 class="project-tagline">{{ site.description | default: "A lightweight, reproducible toolkit for LLM-based query reformulation" }}</h2>
-    </header>
-
-    <main class="main-content">
-      {{ content }}
-    </main>
-
-    <footer class="site-footer">
-      <span>Made with ❤️ by the QueryGym Team</span>
-      <br>
-      <span style="font-size: 0.8rem; margin-top: 0.5rem; display: inline-block;">© 2024-2025 QueryGym Contributors · <a href="https://github.com/ls3-lab/QueryGym">GitHub</a> · <a href="https://opensource.org/licenses/Apache-2.0">Apache 2.0</a></span>
-    </footer>
-
-    <script>
-      // Dark mode toggle
-      const themeToggle = document.getElementById('themeToggle');
-      const themeIcon = themeToggle.querySelector('i');
-      
-      // Check for saved theme preference or default to light
-      const savedTheme = localStorage.getItem('querygym-theme') || 'light';
-      if (savedTheme === 'dark') {
-        document.documentElement.setAttribute('data-theme', 'dark');
-        themeIcon.classList.remove('fa-moon');
-        themeIcon.classList.add('fa-sun');
-      }
-      
-      themeToggle.addEventListener('click', () => {
-        const currentTheme = document.documentElement.getAttribute('data-theme');
-        const newTheme = currentTheme === 'dark' ? 'light' : 'dark';
-        
-        document.documentElement.setAttribute('data-theme', newTheme);
-        localStorage.setItem('querygym-theme', newTheme);
-        
-        if (newTheme === 'dark') {
-          themeIcon.classList.remove('fa-moon');
-          themeIcon.classList.add('fa-sun');
-        } else {
-          themeIcon.classList.remove('fa-sun');
-          themeIcon.classList.add('fa-moon');
-        }
-      });
-    </script>
-  </body>
-</html>
diff --git a/docs/index.md b/docs/index.md
index d1d96a7..0a90ca6 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -89,7 +89,7 @@ pip install querygym[dev]
 - [CLI Usage](user-guide/cli.md)
 - [API Reference](api/core.md)
 
-> 📊 **Looking for benchmarks?** Visit the [Leaderboard](https://ls3-lab.github.io/QueryGym/leaderboard.html) on our main site.
+> 📊 **Looking for benchmarks?** Visit the [Leaderboard](https://leaderboard.querygym.com).
 
 ## Citation
 
diff --git a/docs/leaderboard.html b/docs/leaderboard.html
deleted file mode 100644
index 6f24445..0000000
--- a/docs/leaderboard.html
+++ /dev/null
@@ -1,1512 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
-    <meta charset="UTF-8" />
-    <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no" />
-    <meta http-equiv="x-ua-compatible" content="ie=edge" />
-    <title>QueryGym: Query Reformulation Methods Leaderboard</title>
-    <!-- Google Fonts -->
-    <link rel="preconnect" href="https://fonts.googleapis.com">
-    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
-    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet">
-    <!-- Font Awesome -->
-    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css" />
-    <!-- Bootstrap -->
-    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet" />
-    
-    <style>
-        * {
-            margin: 0;
-            padding: 0;
-            box-sizing: border-box;
-        }
-
-        :root {
-            --primary-color: #2563eb;
-            --primary-dark: #1e40af;
-            --bg-light: #f8fafc;
-            --bg-white: #ffffff;
-            --bg-body: #f0f4f8;
-            --text-primary: #1e293b;
-            --text-secondary: #64748b;
-            --border-color: #e2e8f0;
-            --border-light: #f1f5f9;
-            --shadow-sm: 0 1px 2px 0 rgba(0, 0, 0, 0.05);
-            --shadow-md: 0 4px 6px -1px rgba(0, 0, 0, 0.1), 0 2px 4px -1px rgba(0, 0, 0, 0.06);
-            --shadow-lg: 0 10px 15px -3px rgba(0, 0, 0, 0.1), 0 4px 6px -2px rgba(0, 0, 0, 0.05);
-            --code-bg: #f8fafc;
-            --table-row-hover: #f8fafc;
-            --header-gradient: linear-gradient(to right, #667eea 0%, #764ba2 100%);
-        }
-
-        [data-theme="dark"] {
-            --primary-color: #60a5fa;
-            --primary-dark: #3b82f6;
-            --bg-light: #1e293b;
-            --bg-white: #0f172a;
-            --bg-body: #020617;
-            --text-primary: #f1f5f9;
-            --text-secondary: #94a3b8;
-            --border-color: #334155;
-            --border-light: #1e293b;
-            --code-bg: #1e293b;
-            --table-row-hover: #1e293b;
-            --header-gradient: linear-gradient(to right, #4338ca 0%, #6b21a8 100%);
-        }
-
-        body {
-            font-family: 'Inter', -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
-            background: var(--bg-body);
-            color: var(--text-primary);
-            line-height: 1.6;
-            min-height: 100vh;
-            transition: background-color 0.3s ease, color 0.3s ease;
-        }
-
-        .header-section {
-            background: var(--header-gradient);
-            padding: 3rem 0;
-            color: white;
-            box-shadow: var(--shadow-lg);
-            position: relative;
-        }
-
-        .header-controls {
-            position: absolute;
-            top: 1rem;
-            right: 1rem;
-            display: flex;
-            gap: 0.75rem;
-            align-items: center;
-        }
-
-        .header-btn {
-            display: inline-flex;
-            align-items: center;
-            gap: 0.5rem;
-            padding: 0.5rem 1rem;
-            background: rgba(255, 255, 255, 0.15);
-            border: 1px solid rgba(255, 255, 255, 0.3);
-            border-radius: 6px;
-            color: white;
-            font-size: 0.875rem;
-            font-weight: 500;
-            cursor: pointer;
-            transition: all 0.2s ease;
-            text-decoration: none;
-        }
-
-        .header-btn:hover {
-            background: rgba(255, 255, 255, 0.25);
-            color: white;
-            text-decoration: none;
-        }
-
-        .theme-toggle {
-            padding: 0.5rem;
-            width: 40px;
-            height: 40px;
-            justify-content: center;
-        }
-
-        .theme-toggle i {
-            font-size: 1.1rem;
-        }
-
-        .header-section h1 {
-            font-size: 2.5rem;
-            font-weight: 700;
-            margin-bottom: 0.5rem;
-        }
-
-        .header-section .subtitle {
-            font-size: 1.1rem;
-            opacity: 0.9;
-            font-weight: 400;
-        }
-
-        .header-section .fa-trophy {
-            color: #ffd700;
-            text-shadow: 0 0 10px rgba(255, 215, 0, 0.5), 0 2px 4px rgba(0, 0, 0, 0.3);
-        }
-
-        .main-container {
-            max-width: 1440px;
-            margin: -2rem auto 3rem;
-            padding: 0 2rem;
-            position: relative;
-            z-index: 10;
-        }
-
-        .intro-card {
-            background: var(--bg-white);
-            border-radius: 8px;
-            padding: 2rem;
-            margin-bottom: 2rem;
-            box-shadow: var(--shadow-sm);
-            border: 1px solid var(--border-color);
-        }
-
-        .intro-card p {
-            color: var(--text-secondary);
-            font-size: 1rem;
-            margin: 0;
-        }
-
-        .leaderboard-card {
-            background: var(--bg-white);
-            border-radius: 8px;
-            box-shadow: var(--shadow-sm);
-            border: 1px solid var(--border-color);
-            overflow: hidden;
-        }
-
-        .table-header {
-            background: var(--bg-light);
-            padding: 1.5rem;
-            border-bottom: 2px solid var(--border-color);
-        }
-
-        .table-header h2 {
-            font-size: 1.5rem;
-            font-weight: 600;
-            color: var(--text-primary);
-            margin: 0;
-        }
-
-        .leaderboard-table {
-            width: 100%;
-            border-collapse: collapse;
-        }
-
-        .leaderboard-table thead {
-            background: var(--bg-light);
-        }
-
-        .leaderboard-table thead th {
-            padding: 1rem;
-            font-weight: 600;
-            font-size: 0.75rem;
-            text-transform: uppercase;
-            letter-spacing: 0.5px;
-            color: var(--text-secondary);
-            border-bottom: 2px solid var(--border-color);
-            text-align: center;
-            vertical-align: middle;
-        }
-
-        .leaderboard-table thead th.config-col {
-            text-align: left;
-            width: 1%;
-            background: var(--border-light);
-        }
-
-        .leaderboard-table thead th.method-col {
-            text-align: left;
-            min-width: 160px;
-            width: 160px;
-            background: var(--border-light);
-        }
-
-        .leaderboard-table thead th.metric-col {
-            min-width: 70px;
-            width: 70px;
-            background: var(--bg-light);
-            color: var(--text-secondary);
-            padding: 1rem 0.5rem;
-        }
-
-        .leaderboard-table thead th.sortable {
-            cursor: pointer;
-            user-select: none;
-            position: relative;
-            transition: background-color 0.2s ease;
-        }
-
-        .leaderboard-table thead th.sortable:hover {
-            background: var(--border-color);
-        }
-
-        .leaderboard-table thead th.sortable .sort-indicator {
-            display: inline-block;
-            margin-left: 0.5rem;
-            opacity: 0.5;
-            font-size: 0.7rem;
-        }
-
-        .leaderboard-table thead th.sortable.sort-asc .sort-indicator,
-        .leaderboard-table thead th.sortable.sort-desc .sort-indicator {
-            opacity: 1;
-        }
-
-        .leaderboard-table thead th.sortable.sort-asc .sort-indicator::after {
-            content: ' ▲';
-        }
-
-        .leaderboard-table thead th.sortable.sort-desc .sort-indicator::after {
-            content: ' ▼';
-        }
-
-        .leaderboard-table thead th.sortable {
-            position: relative;
-        }
-
-        .leaderboard-table thead th.sortable::after {
-            content: '⇅';
-            display: inline-block;
-            margin-left: 0.25rem;
-            opacity: 0.4;
-            font-size: 0.7rem;
-            font-weight: normal;
-            transition: opacity 0.2s ease, transform 0.2s ease;
-            vertical-align: middle;
-        }
-
-        .leaderboard-table thead th.sortable:hover::after {
-            opacity: 0.8;
-            transform: scale(1.1);
-        }
-
-        .leaderboard-table thead th.sortable.sort-asc::after,
-        .leaderboard-table thead th.sortable.sort-desc::after {
-            opacity: 0;
-        }
-
-        .leaderboard-table thead th.separator-col + th {
-            border-left: 1px solid rgba(203, 213, 225, 0.4);
-        }
-
-        .leaderboard-table thead th.dataset-header.metric-col {
-            background: linear-gradient(to right, #dde4fc 0%, #d4dcfa 50%, #ccd5f8 100%) !important;
-            color: #3b4a9a !important;
-            font-weight: 700;
-            font-size: 0.85rem;
-            padding: 1rem 0.75rem;
-            border-top: 1px solid rgba(255, 255, 255, 0.6);
-            border-bottom: 1px solid rgba(255, 255, 255, 0.6);
-        }
-
-        .leaderboard-table thead tr:first-child th.dataset-header.metric-col:nth-child(5),
-        .leaderboard-table thead tr:first-child th.dataset-header.metric-col:nth-child(7) {
-            border-left: 1px solid rgba(203, 213, 225, 0.4);
-        }
-
-        .leaderboard-table thead th.dataset-header {
-            background: linear-gradient(to right, #dde4fc 0%, #d4dcfa 50%, #ccd5f8 100%) !important;
-            color: #3b4a9a !important;
-            font-weight: 700;
-            font-size: 0.8rem;
-            padding: 1rem 0.75rem;
-            border-top: 1px solid rgba(255, 255, 255, 0.5);
-            border-bottom: 1px solid rgba(255, 255, 255, 0.5);
-        }
-
-        .leaderboard-table tbody tr {
-            transition: background-color 0.15s ease;
-            border-bottom: 1px solid var(--border-light);
-        }
-
-        .leaderboard-table tbody tr:hover {
-            background-color: var(--table-row-hover);
-        }
-
-        .leaderboard-table tbody tr.expanded-row {
-            background-color: var(--table-row-hover);
-        }
-
-        .leaderboard-table tbody td {
-            padding: 1rem;
-            vertical-align: middle;
-            text-align: center;
-            font-size: 0.875rem;
-        }
-
-        .leaderboard-table tbody tr:not(.expandable-content) td.separator-col + td {
-            border-left: 1px solid rgba(203, 213, 225, 0.4);
-        }
-
-        .leaderboard-table tbody td.config-cell {
-            text-align: left;
-            font-weight: 500;
-            color: var(--text-primary);
-            border-right: 1px solid var(--border-light);
-        }
-
-        .leaderboard-table tbody td.method-name {
-            text-align: left;
-            font-weight: 600;
-            color: var(--text-primary);
-            font-size: 0.85rem;
-        }
-
-        .config-badges {
-            display: flex;
-            flex-direction: column;
-            gap: 0.4rem;
-            width: fit-content;
-        }
-
-        .config-badge {
-            display: inline-flex;
-            align-items: center;
-            flex-direction: column;
-            padding: 0.5rem 0.8rem;
-            border-radius: 20px;
-            font-size: 0.85rem;
-            font-weight: 500;
-            width: fit-content;
-            min-width: 170px;
-            box-shadow: 0 1px 3px rgba(0, 0, 0, 0.1);
-            text-align: center;
-        }
-        
-        .config-badge small {
-            display: block;
-            margin-top: 0.2rem;
-            line-height: 1.2;
-        }
-
-        .badge-llm {
-            background: linear-gradient(135deg, #dbeafe 0%, #bfdbfe 100%);
-            color: #1e40af;
-            border: 1px solid #93c5fd;
-        }
-
-        .badge-llm i {
-            margin-right: 0.4rem;
-            font-size: 0.85rem;
-            color: #1e40af;
-        }
-        
-        .config-badge span[style*="display: flex"] i {
-            margin-right: 0.4rem;
-        }
-
-        .badge-retrieval {
-            background: linear-gradient(135deg, #fce7f3 0%, #fbcfe8 100%);
-            color: #9f1239;
-            border: 1px solid #f9a8d4;
-        }
-
-        .badge-retrieval i {
-            margin-right: 0.4rem;
-            font-size: 0.85rem;
-            color: #9f1239;
-        }
-
-        .metric-value {
-            font-family: 'JetBrains Mono', 'Courier New', monospace;
-            font-size: 0.8rem;
-            font-weight: 400;
-            color: var(--text-secondary);
-            padding: 0.2rem 0.3rem;
-            border-radius: 4px;
-            display: inline-block;
-            min-width: 60px;
-        }
-
-        .expand-icon {
-            width: 28px;
-            height: 28px;
-            display: flex;
-            align-items: center;
-            justify-content: center;
-            background: var(--border-light);
-            color: var(--text-secondary);
-            border-radius: 4px;
-            cursor: pointer;
-            transition: all 0.2s ease;
-            font-size: 0.75rem;
-            border: 1px solid var(--border-color);
-        }
-
-        .expand-icon:hover {
-            background: var(--border-color);
-            color: var(--text-primary);
-        }
-
-        .expand-icon.expanded {
-            background: var(--primary-color);
-            color: white;
-            border-color: var(--primary-color);
-        }
-
-        .expandable-content {
-            background: var(--bg-light);
-            border-top: 2px solid var(--border-color);
-            padding: 0;
-            overflow-x: auto;
-            max-width: 100%;
-            box-sizing: border-box;
-        }
-
-        .content-tabs {
-            border-bottom: 1px solid var(--border-color);
-            background: var(--bg-white);
-            padding: 0 1.5rem;
-            display: flex;
-            gap: 0;
-        }
-
-        .content-tab {
-            padding: 1rem 1.5rem;
-            background: transparent;
-            border: none;
-            border-bottom: 2px solid transparent;
-            color: var(--text-secondary);
-            font-weight: 500;
-            font-size: 0.875rem;
-            cursor: pointer;
-            transition: all 0.2s ease;
-        }
-
-        .content-tab:hover {
-            color: var(--text-primary);
-            background: var(--bg-light);
-        }
-
-        .content-tab.active {
-            color: var(--primary-color);
-            border-bottom-color: var(--primary-color);
-            background: var(--bg-light);
-        }
-
-        .tab-content {
-            padding: 2rem;
-            background: var(--bg-white);
-            overflow-x: auto;
-            max-width: 100%;
-            box-sizing: border-box;
-        }
-
-        .tab-pane {
-            display: none;
-        }
-
-        .tab-pane.active {
-            display: block;
-        }
-
-        blockquote.mycode {
-            border-left: 3px solid var(--border-color);
-            margin-left: 0;
-            margin-top: 1rem;
-            margin-bottom: 1rem;
-            padding-left: 1.25rem;
-            background: var(--code-bg);
-            padding: 1rem 1.25rem;
-            border-radius: 4px;
-            text-align: left;
-            overflow-x: auto;
-            max-width: 100%;
-            box-sizing: border-box;
-        }
-
-        blockquote.mycode pre {
-            margin: 0;
-            color: var(--text-primary);
-            font-family: 'JetBrains Mono', 'Courier New', monospace;
-            font-size: 0.875rem;
-            line-height: 1.6;
-            overflow-x: auto;
-            white-space: pre-wrap;
-            word-wrap: break-word;
-            overflow-wrap: break-word;
-            max-width: 100%;
-        }
-
-        blockquote.mycode code {
-            color: var(--text-primary);
-            background: transparent;
-            padding: 0;
-        }
-
-        .command-label {
-            color: var(--text-primary);
-            font-size: 0.875rem;
-            font-weight: 600;
-            margin-bottom: 0.5rem;
-        }
-
-        .copy-code-button {
-            border-radius: 4px;
-            min-width: 50px;
-            background: var(--text-secondary);
-            color: white;
-            cursor: pointer;
-            border: none;
-            font-family: 'Inter', sans-serif;
-            font-size: 0.75rem;
-            font-weight: 500;
-            text-align: center;
-            padding: 0.4rem 0.75rem;
-            position: absolute;
-            top: 0.5rem;
-            right: 0.5rem;
-            transition: all 0.2s ease;
-        }
-
-        .copy-code-button:hover {
-            background: var(--primary-color);
-        }
-
-        blockquote.mycode {
-            position: relative;
-        }
-
-        .notes-section {
-            background: var(--bg-white);
-            border-radius: 8px;
-            padding: 2rem;
-            margin-top: 2rem;
-            box-shadow: var(--shadow-sm);
-            border: 1px solid var(--border-color);
-        }
-
-        .notes-section h3 {
-            font-size: 1.25rem;
-            font-weight: 600;
-            color: var(--text-primary);
-            margin-bottom: 1.25rem;
-            padding-bottom: 1rem;
-            border-bottom: 1px solid var(--border-color);
-        }
-
-        .notes-section ul {
-            list-style: none;
-            padding: 0;
-        }
-
-        .notes-section li {
-            padding: 0.75rem 0;
-            color: var(--text-secondary);
-            border-bottom: 1px solid var(--border-light);
-            font-size: 0.9rem;
-        }
-
-        .notes-section li:last-child {
-            border-bottom: none;
-        }
-
-        .notes-section li strong {
-            color: var(--text-primary);
-            font-weight: 600;
-        }
-
-        .highlight-box {
-            display: inline-block;
-            background: #dcfce7;
-            padding: 0.2rem 0.5rem;
-            border-radius: 3px;
-            font-weight: 500;
-            color: #166534;
-            font-size: 0.875rem;
-        }
-
-        .programmatic-section {
-            background: var(--bg-white);
-            border-radius: 8px;
-            padding: 2rem;
-            margin-top: 2rem;
-            box-shadow: var(--shadow-sm);
-            border: 1px solid var(--border-color);
-        }
-
-        .programmatic-section h3 {
-            font-size: 1.25rem;
-            font-weight: 600;
-            color: var(--text-primary);
-            margin-bottom: 1.25rem;
-            padding-bottom: 1rem;
-            border-bottom: 1px solid var(--border-color);
-        }
-
-        .separator-col {
-            display: none;
-        }
-
-        @media (max-width: 1400px) {
-            .leaderboard-table {
-                font-size: 0.8rem;
-            }
-            
-            .leaderboard-table tbody td {
-                padding: 0.75rem 0.5rem;
-            }
-        }
-    </style>
-</head>
-<body>
-
-    <!-- Header Section -->
-    <div class="header-section">
-        <div class="header-controls">
-            <a href="./" class="header-btn">
-                <i class="fas fa-home"></i>
-                <span>Home</span>
-            </a>
-            <button class="header-btn theme-toggle" id="themeToggle" title="Toggle dark mode">
-                <i class="fas fa-moon"></i>
-            </button>
-        </div>
-        <div class="container text-center">
-            <h1><i class="fas fa-trophy me-2"></i>QueryGym Leaderboard</h1>
-            <p class="subtitle">Query Reformulation Methods Performance Evaluation</p>
-        </div>
-    </div>
-
-    <!-- Main Container -->
-    <div class="main-container">
-        <!-- Introduction Card -->
-        <div class="intro-card">
-            <p>
-                The leaderboard below provides comprehensive performance metrics for QueryGym query reformulation methods 
-                across different LLM configurations and retrieval backends. Each row represents a unique method configuration. 
-                <strong>Click on any metric column header (⇅) to sort methods by that metric.</strong> Click on any row to expand 
-                and view detailed commands for reproducing the results.
-            </p>
-        </div>
-
-        <!-- Leaderboard Card -->
-        <div class="leaderboard-card">
-            <div class="table-header">
-                <h2><i class="fas fa-chart-line me-2"></i>Performance Metrics</h2>
-            </div>
-            
-            <div class="table-responsive">
-                <table class="leaderboard-table">
-                    <thead>
-                        <tr>
-                            <th class="config-col">Configuration</th>
-                            <th class="method-col">Method</th>
-                            <th class="dataset-header metric-col" colspan="3">TREC DL 2019</th>
-                            <th class="separator-col"></th>
-                            <th class="dataset-header metric-col" colspan="3">TREC DL 2020</th>
-                            <th class="separator-col"></th>
-                            <th class="dataset-header metric-col" colspan="3">DL HARD</th>
-                        </tr>
-                        <tr>
-                            <th></th>
-                            <th></th>
-                            <th class="metric-col sortable" data-sort="dl19-ap" title="Click to sort by AP (TREC DL 2019)">AP<span class="sort-indicator"></span></th>
-                            <th class="metric-col sortable" data-sort="dl19-ndcg" title="Click to sort by nDCG@10 (TREC DL 2019)">nDCG@10<span class="sort-indicator"></span></th>
-                            <th class="metric-col sortable" data-sort="dl19-recall" title="Click to sort by R@1K (TREC DL 2019)">R@1K<span class="sort-indicator"></span></th>
-                            <th class="separator-col"></th>
-                            <th class="metric-col sortable" data-sort="dl20-ap" title="Click to sort by AP (TREC DL 2020)">AP<span class="sort-indicator"></span></th>
-                            <th class="metric-col sortable" data-sort="dl20-ndcg" title="Click to sort by nDCG@10 (TREC DL 2020)">nDCG@10<span class="sort-indicator"></span></th>
-                            <th class="metric-col sortable" data-sort="dl20-recall" title="Click to sort by R@1K (TREC DL 2020)">R@1K<span class="sort-indicator"></span></th>
-                            <th class="separator-col"></th>
-                            <th class="metric-col sortable" data-sort="dlhard-ap" title="Click to sort by AP (DL HARD)">AP<span class="sort-indicator"></span></th>
-                            <th class="metric-col sortable" data-sort="dlhard-ndcg" title="Click to sort by nDCG@10 (DL HARD)">nDCG@10<span class="sort-indicator"></span></th>
-                            <th class="metric-col sortable" data-sort="dlhard-recall" title="Click to sort by R@1K (DL HARD)">R@1K<span class="sort-indicator"></span></th>
-                        </tr>
-                    </thead>
-                    <tbody>
-                        <!-- BM25 Baseline -->
-                        <tr>
-                            <td class="config-cell">
-                                <div class="config-badges">
-                                    <span class="config-badge badge-retrieval">
-                                        <span style="display: flex; align-items: center; justify-content: center;">
-                                            <i class="fas fa-search"></i>BM25
-                                        </span>
-                                        <small style="font-size: 0.65rem; opacity: 0.85;">k1=0.9, b=0.4</small>
-                                    </span>
-                                </div>
-                            </td>
-                            <td class="method-name">
-                                BM25 (Baseline)
-                            </td>
-                            <td><span class="metric-value">0.3013</span></td>
-                            <td><span class="metric-value">0.5058</span></td>
-                            <td><span class="metric-value">0.7501</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.2856</span></td>
-                            <td><span class="metric-value">0.4796</span></td>
-                            <td><span class="metric-value">0.7863</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.1595</span></td>
-                            <td><span class="metric-value">0.2850</span></td>
-                            <td><span class="metric-value">0.6806</span></td>
-                        </tr>
-                        <!-- Configuration: GPT-4.1-mini + BM25 -->
-                        <tr class="accordion-row" data-target="row1">
-                            <td class="config-cell" rowspan="7">
-                                <div class="config-badges">
-                                    <span class="config-badge badge-llm">
-                                        <span style="display: flex; align-items: center; justify-content: center;">
-                                            <i class="fas fa-brain"></i>GPT-4.1-mini
-                                        </span>
-                                        <small style="font-size: 0.65rem; opacity: 0.85;">temp=1.0, max_tokens=128</small>
-                                    </span>
-                                    <span class="config-badge badge-retrieval">
-                                        <span style="display: flex; align-items: center; justify-content: center;">
-                                            <i class="fas fa-search"></i>BM25
-                                        </span>
-                                        <small style="font-size: 0.65rem; opacity: 0.85;">k1=0.9, b=0.4</small>
-                                    </span>
-                                </div>
-                            </td>
-                            <td class="method-name">
-                                <div class="expand-icon" data-row="row1" style="display: inline-flex; margin-right: 0.5rem;">
-                                    <i class="fas fa-chevron-down"></i>
-                                </div>
-                                Query2Doc (ZS)
-                            </td>
-                            <td><span class="metric-value">0.4508</span></td>
-                            <td><span class="metric-value">0.6709</span></td>
-                            <td><span class="metric-value">0.8746</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.4325</span></td>
-                            <td><span class="metric-value">0.6323</span></td>
-                            <td><span class="metric-value">0.8864</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.2276</span></td>
-                            <td><span class="metric-value">0.3303</span></td>
-                            <td><span class="metric-value">0.7704</span></td>
-                        </tr>
-                        <tr class="accordion-row" data-target="row2">
-                            <td class="method-name">
-                                <div class="expand-icon" data-row="row2" style="display: inline-flex; margin-right: 0.5rem;">
-                                    <i class="fas fa-chevron-down"></i>
-                                </div>
-                                Query2Doc (FS)
-                            </td>
-                            <td><span class="metric-value">0.4418</span></td>
-                            <td><span class="metric-value">0.6532</span></td>
-                            <td><span class="metric-value">0.8521</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.4051</span></td>
-                            <td><span class="metric-value">0.6111</span></td>
-                            <td><span class="metric-value">0.8869</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.2260</span></td>
-                            <td><span class="metric-value">0.3388</span></td>
-                            <td><span class="metric-value">0.7842</span></td>
-                        </tr>
-                        <tr class="accordion-row" data-target="row3">
-                            <td class="method-name">
-                                <div class="expand-icon" data-row="row3" style="display: inline-flex; margin-right: 0.5rem;">
-                                    <i class="fas fa-chevron-down"></i>
-                                </div>
-                                Query2Doc (CoT)
-                            </td>
-                            <td><span class="metric-value">0.4145</span></td>
-                            <td><span class="metric-value">0.6128</span></td>
-                            <td><span class="metric-value">0.8495</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.3801</span></td>
-                            <td><span class="metric-value">0.5894</span></td>
-                            <td><span class="metric-value">0.8846</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.2225</span></td>
-                            <td><span class="metric-value">0.3191</span></td>
-                            <td><span class="metric-value">0.7524</span></td>
-                        </tr>
-                        <tr class="expandable-content" id="row1-content" style="display: none;">
-                            <td colspan="13">
-                                <div class="content-tabs">
-                                    <button class="content-tab active" data-tab="row1-tab1">TREC DL 2019</button>
-                                    <button class="content-tab" data-tab="row1-tab2">TREC DL 2020</button>
-                                    <button class="content-tab" data-tab="row1-tab3">DL HARD</button>
-                                </div>
-                                <div class="tab-content">
-                                    <div class="tab-pane active" id="row1-tab1">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2019:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row1-tab1-cmd">Copy</button>
-                                            <pre id="row1-tab1-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --dataset msmarco-v1-passage.trecdl2019 \
-    --method query2doc \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --output-dir outputs/dl19_query2doc_zs</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row1-tab2">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2020:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row1-tab2-cmd">Copy</button>
-                                            <pre id="row1-tab2-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --dataset msmarco-v1-passage.trecdl2020 \
-    --method query2doc \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --output-dir outputs/dl20_query2doc_zs</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row1-tab3">
-                                        <div class="command-label">Command to reproduce results on DL HARD:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row1-tab3-cmd">Copy</button>
-                                            <pre id="row1-tab3-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --queries-file path/to/queries.tsv \
-    --qrels-file path/to/qrels.trec \
-    --index-name msmarco-v1-passage \
-    --method query2doc \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --output-dir outputs/dlhard_query2doc_zs</code></pre>
-                                        </blockquote>
-                                    </div>
-                                </div>
-                            </td>
-                        </tr>
-                        <tr class="expandable-content" id="row2-content" style="display: none;">
-                            <td colspan="13">
-                                <div class="content-tabs">
-                                    <button class="content-tab active" data-tab="row2-tab1">TREC DL 2019</button>
-                                    <button class="content-tab" data-tab="row2-tab2">TREC DL 2020</button>
-                                    <button class="content-tab" data-tab="row2-tab3">DL HARD</button>
-                                </div>
-                                <div class="tab-content">
-                                    <div class="tab-pane active" id="row2-tab1">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2019:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row2-tab1-cmd">Copy</button>
-                                            <pre id="row2-tab1-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --dataset msmarco-v1-passage.trecdl2019 \
-    --method query2doc \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"mode":"fs","num_examples":4,"dataset_type":"msmarco",' \
-    '"collection_path":"path/to/collection.tsv",' \
-    '"train_queries_path":"path/to/queries.train.tsv","train_qrels_path":"path/to/qrels.train.tsv"}' \
-    --output-dir outputs/dl19_query2doc</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row2-tab2">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2020:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row2-tab2-cmd">Copy</button>
-                                            <pre id="row2-tab2-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --dataset msmarco-v1-passage.trecdl2020 \
-    --method query2doc \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"mode":"fs","num_examples":4,"dataset_type":"msmarco",' \
-    '"collection_path":"path/to/collection.tsv",' \
-    '"train_queries_path":"path/to/queries.train.tsv","train_qrels_path":"path/to/qrels.train.tsv"}' \
-    --output-dir outputs/dl20_query2doc</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row2-tab3">
-                                        <div class="command-label">Command to reproduce results on DL HARD:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row2-tab3-cmd">Copy</button>
-                                            <pre id="row2-tab3-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --queries-file path/to/queries.tsv \
-    --qrels-file path/to/qrels.trec \
-    --index-name msmarco-v1-passage \
-    --method query2doc \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"mode":"fs","num_examples":4,"dataset_type":"msmarco",' \
-    '"collection_path":"path/to/collection.tsv",' \
-    '"train_queries_path":"path/to/queries.train.tsv","train_qrels_path":"path/to/qrels.train.tsv"}' \
-    --output-dir outputs/dlhard_query2doc</code></pre>
-                                        </blockquote>
-                                    </div>
-                                </div>
-                            </td>
-                        </tr>
-                        <tr class="expandable-content" id="row3-content" style="display: none;">
-                            <td colspan="13">
-                                <div class="content-tabs">
-                                    <button class="content-tab active" data-tab="row3-tab1">TREC DL 2019</button>
-                                    <button class="content-tab" data-tab="row3-tab2">TREC DL 2020</button>
-                                    <button class="content-tab" data-tab="row3-tab3">DL HARD</button>
-                                </div>
-                                <div class="tab-content">
-                                    <div class="tab-pane active" id="row3-tab1">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2019:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row3-tab1-cmd">Copy</button>
-                                            <pre id="row3-tab1-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --dataset msmarco-v1-passage.trecdl2019 \
-    --method query2doc \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"mode":"cot"}' \
-    --output-dir outputs/dl19_query2doc_cot</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row3-tab2">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2020:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row3-tab2-cmd">Copy</button>
-                                            <pre id="row3-tab2-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --dataset msmarco-v1-passage.trecdl2020 \
-    --method query2doc \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"mode":"cot"}' \
-    --output-dir outputs/dl20_query2doc_cot</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row3-tab3">
-                                        <div class="command-label">Command to reproduce results on DL HARD:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row3-tab3-cmd">Copy</button>
-                                            <pre id="row3-tab3-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --queries-file path/to/queries.tsv \
-    --qrels-file path/to/qrels.trec \
-    --index-name msmarco-v1-passage \
-    --method query2doc \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"mode":"cot"}' \
-    --output-dir outputs/dlhard_query2doc_cot</code></pre>
-                                        </blockquote>
-                                    </div>
-                                </div>
-                            </td>
-                        </tr>
-                        <tr class="accordion-row" data-target="row4">
-                            <td class="method-name">
-                                <div class="expand-icon" data-row="row4" style="display: inline-flex; margin-right: 0.5rem;">
-                                    <i class="fas fa-chevron-down"></i>
-                                </div>
-                                Query2E (ZS)
-                            </td>
-                            <td><span class="metric-value">0.3709</span></td>
-                            <td><span class="metric-value">0.5679</span></td>
-                            <td><span class="metric-value">0.8384</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.3436</span></td>
-                            <td><span class="metric-value">0.5624</span></td>
-                            <td><span class="metric-value">0.8373</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.1845</span></td>
-                            <td><span class="metric-value">0.3179</span></td>
-                            <td><span class="metric-value">0.7642</span></td>
-                        </tr>
-                        <tr class="expandable-content" id="row4-content" style="display: none;">
-                            <td colspan="13">
-                                <div class="content-tabs">
-                                    <button class="content-tab active" data-tab="row4-tab1">TREC DL 2019</button>
-                                    <button class="content-tab" data-tab="row4-tab2">TREC DL 2020</button>
-                                    <button class="content-tab" data-tab="row4-tab3">DL HARD</button>
-                                </div>
-                                <div class="tab-content">
-                                    <div class="tab-pane active" id="row4-tab1">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2019:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row4-tab1-cmd">Copy</button>
-                                            <pre id="row4-tab1-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --queries-file path/to/original_queries.tsv \
-    --qrels-file path/to/qrels.trec \
-    --index-name msmarco-v1-passage \
-    --method query2e \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"mode":"zs"}' \
-    --output-dir outputs/dl19_query2e_zs</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row4-tab2">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2020:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row4-tab2-cmd">Copy</button>
-                                            <pre id="row4-tab2-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --queries-file path/to/original_queries.tsv \
-    --qrels-file path/to/qrels.trec \
-    --index-name msmarco-v1-passage \
-    --method query2e \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"mode":"zs"}' \
-    --output-dir outputs/dl20_query2e_zs</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row4-tab3">
-                                        <div class="command-label">Command to reproduce results on DL HARD:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row4-tab3-cmd">Copy</button>
-                                            <pre id="row4-tab3-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --queries-file path/to/original_queries.tsv \
-    --qrels-file path/to/qrels.trec \
-    --index-name msmarco-v1-passage \
-    --method query2e \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"mode":"zs"}' \
-    --output-dir outputs/dlhard_query2e_zs</code></pre>
-                                        </blockquote>
-                                    </div>
-                                </div>
-                            </td>
-                        </tr>
-                        <tr class="accordion-row" data-target="row5">
-                            <td class="method-name">
-                                <div class="expand-icon" data-row="row5" style="display: inline-flex; margin-right: 0.5rem;">
-                                    <i class="fas fa-chevron-down"></i>
-                                </div>
-                                CSQE
-                            </td>
-                            <td><span class="metric-value">0.4007</span></td>
-                            <td><span class="metric-value">0.5962</span></td>
-                            <td><span class="metric-value">0.8506</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.3542</span></td>
-                            <td><span class="metric-value">0.5298</span></td>
-                            <td><span class="metric-value">0.8431</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.2170</span></td>
-                            <td><span class="metric-value">0.3194</span></td>
-                            <td><span class="metric-value">0.7276</span></td>
-                        </tr>
-                        <tr class="expandable-content" id="row5-content" style="display: none;">
-                            <td colspan="13">
-                                <div class="content-tabs">
-                                    <button class="content-tab active" data-tab="row5-tab1">TREC DL 2019</button>
-                                    <button class="content-tab" data-tab="row5-tab2">TREC DL 2020</button>
-                                    <button class="content-tab" data-tab="row5-tab3">DL HARD</button>
-                                </div>
-                                <div class="tab-content">
-                                    <div class="tab-pane active" id="row5-tab1">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2019:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row5-tab1-cmd">Copy</button>
-                                            <pre id="row5-tab1-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --dataset msmarco-v1-passage.trecdl2019 \
-    --method csqe \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 1024 \
-    --method-params '{"retrieval_k":10,"gen_num":2}' \
-    --output-dir outputs/dl19_csqe</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row5-tab2">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2020:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row5-tab2-cmd">Copy</button>
-                                            <pre id="row5-tab2-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --dataset msmarco-v1-passage.trecdl2020 \
-    --method csqe \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 1024 \
-    --method-params '{"retrieval_k":10,"gen_num":2}' \
-    --output-dir outputs/dl20_csqe</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row5-tab3">
-                                        <div class="command-label">Command to reproduce results on DL HARD:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row5-tab3-cmd">Copy</button>
-                                            <pre id="row5-tab3-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --queries-file path/to/original_queries.tsv \
-    --qrels-file path/to/qrels.trec \
-    --index-name msmarco-v1-passage \
-    --method csqe \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 1024 \
-    --method-params '{"retrieval_k":10,"gen_num":2}' \
-    --output-dir outputs/dlhard_csqe</code></pre>
-                                        </blockquote>
-                                    </div>
-                                </div>
-                            </td>
-                        </tr>
-                        <tr class="accordion-row" data-target="row6">
-                            <td class="method-name">
-                                <div class="expand-icon" data-row="row6" style="display: inline-flex; margin-right: 0.5rem;">
-                                    <i class="fas fa-chevron-down"></i>
-                                </div>
-                                LameR
-                            </td>
-                            <td><span class="metric-value">0.4185</span></td>
-                            <td><span class="metric-value">0.6587</span></td>
-                            <td><span class="metric-value">0.8611</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.4432</span></td>
-                            <td><span class="metric-value">0.6353</span></td>
-                            <td><span class="metric-value">0.8839</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.2562</span></td>
-                            <td><span class="metric-value">0.3623</span></td>
-                            <td><span class="metric-value">0.7887</span></td>
-                        </tr>
-                        <tr class="expandable-content" id="row6-content" style="display: none;">
-                            <td colspan="13">
-                                <div class="content-tabs">
-                                    <button class="content-tab active" data-tab="row6-tab1">TREC DL 2019</button>
-                                    <button class="content-tab" data-tab="row6-tab2">TREC DL 2020</button>
-                                    <button class="content-tab" data-tab="row6-tab3">DL HARD</button>
-                                </div>
-                                <div class="tab-content">
-                                    <div class="tab-pane active" id="row6-tab1">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2019:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row6-tab1-cmd">Copy</button>
-                                            <pre id="row6-tab1-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --dataset msmarco-v1-passage.trecdl2019 \
-    --method lamer \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"retrieval_k":10,"gen_passages":5}' \
-    --output-dir outputs/dl19_lamer</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row6-tab2">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2020:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row6-tab2-cmd">Copy</button>
-                                            <pre id="row6-tab2-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --dataset msmarco-v1-passage.trecdl2020 \
-    --method lamer \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"retrieval_k":10,"gen_passages":5}' \
-    --output-dir outputs/dl20_lamer</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row6-tab3">
-                                        <div class="command-label">Command to reproduce results on DL HARD:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row6-tab3-cmd">Copy</button>
-                                            <pre id="row6-tab3-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --queries-file path/to/original_queries.tsv \
-    --qrels-file path/to/qrels.trec \
-    --index-name msmarco-v1-passage \
-    --method lamer \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"retrieval_k":10,"gen_passages":5}' \
-    --output-dir outputs/dlhard_lamer</code></pre>
-                                        </blockquote>
-                                    </div>
-                                </div>
-                            </td>
-                        </tr>
-                        <tr class="accordion-row" data-target="row7">
-                            <td class="method-name">
-                                <div class="expand-icon" data-row="row7" style="display: inline-flex; margin-right: 0.5rem;">
-                                    <i class="fas fa-chevron-down"></i>
-                                </div>
-                                MuGI
-                            </td>
-                            <td><span class="metric-value">0.4766</span></td>
-                            <td><span class="metric-value">0.6903</span></td>
-                            <td><span class="metric-value">0.8822</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.4353</span></td>
-                            <td><span class="metric-value">0.6300</span></td>
-                            <td><span class="metric-value">0.8985</span></td>
-                            <td class="separator-col"></td>
-                            <td><span class="metric-value">0.2393</span></td>
-                            <td><span class="metric-value">0.3515</span></td>
-                            <td><span class="metric-value">0.7974</span></td>
-                        </tr>
-                        <tr class="expandable-content" id="row7-content" style="display: none;">
-                            <td colspan="13">
-                                <div class="content-tabs">
-                                    <button class="content-tab active" data-tab="row7-tab1">TREC DL 2019</button>
-                                    <button class="content-tab" data-tab="row7-tab2">TREC DL 2020</button>
-                                    <button class="content-tab" data-tab="row7-tab3">DL HARD</button>
-                                </div>
-                                <div class="tab-content">
-                                    <div class="tab-pane active" id="row7-tab1">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2019:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row7-tab1-cmd">Copy</button>
-                                            <pre id="row7-tab1-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --dataset msmarco-v1-passage.trecdl2019 \
-    --method mugi \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"num_docs":5,"parallel":true,"mode":"zs"}' \
-    --output-dir outputs/dl19_mugi_zs</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row7-tab2">
-                                        <div class="command-label">Command to reproduce results on TREC DL 2020:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row7-tab2-cmd">Copy</button>
-                                            <pre id="row7-tab2-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --dataset msmarco-v1-passage.trecdl2020 \
-    --method mugi \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"num_docs":5,"parallel":true,"mode":"zs"}' \
-    --output-dir outputs/dl20_mugi_zs</code></pre>
-                                        </blockquote>
-                                    </div>
-                                    <div class="tab-pane" id="row7-tab3">
-                                        <div class="command-label">Command to reproduce results on DL HARD:</div>
-                                        <blockquote class="mycode">
-                                            <button class="copy-code-button" data-copy="row7-tab3-cmd">Copy</button>
-                                            <pre id="row7-tab3-cmd"><code>python examples/querygym_pyserini/pipeline.py \
-    --queries-file path/to/original_queries.tsv \
-    --qrels-file path/to/qrels.trec \
-    --index-name msmarco-v1-passage \
-    --method mugi \
-    --model gpt-4.1-mini \
-    --temperature 1.0 \
-    --max-tokens 128 \
-    --method-params '{"num_docs":5,"parallel":true,"mode":"zs"}' \
-    --output-dir outputs/dlhard_mugi_zs</code></pre>
-                                        </blockquote>
-                                    </div>
-                                </div>
-                            </td>
-                        </tr>
-                    </tbody>
-                </table>
-            </div>
-        </div>
-
-        <!-- Notes Section -->
-        <div class="notes-section">
-            <h3><i class="fas fa-info-circle me-2"></i>Notes</h3>
-            <ul>
-                <li><strong>AP</strong>: Average Precision (AP@100)</li>
-                <li><strong>nDCG@10</strong>: Normalized Discounted Cumulative Gain at rank 10</li>
-                <li><strong>R@1K</strong>: Recall at rank 1000</li>
-                <li>All results are reproducible using the commands shown in the expanded rows</li>
-                <li>Configuration column shows the LLM and retrieval backend used for all methods in that group</li>
-            </ul>
-        </div>
-
-        <!-- Programmatic Execution Section -->
-        <div class="programmatic-section">
-            <h3><i class="fas fa-code me-2"></i>Programmatic Execution</h3>
-            <p style="color: var(--text-secondary); margin-bottom: 1.5rem;">
-                All experimental runs shown in the above table can be programmatically executed using the QueryGym pipeline scripts.
-                The pipeline command runs the complete workflow: reformulation, retrieval, and evaluation.
-            </p>
-            
-            <div class="command-label">Example pipeline command:</div>
-            <blockquote class="mycode">
-                <pre><code>python scripts/querygym_pyserini/pipeline.py \
-  --dataset msmarco-v1-passage.dev \
-  --method query2doc \
-  --model gpt-4 \
-  --base-url https://api.openai.com/v1 \
-  --api-key YOUR_API_KEY \
-  --output-dir runs/query2doc-gpt4-bm25</code></pre>
-            </blockquote>
-
-            <p style="color: var(--text-secondary); margin-top: 1.5rem;">
-                For more information, see the <a href="https://github.com/ls3-lab/QueryGym/blob/main/examples/querygym_pyserini/README.md" style="color: var(--primary-color); text-decoration: none; font-weight: 600;">QueryGym Pyserini Pipeline documentation</a>.
-            </p>
-        </div>
-    </div>
-
-    <!-- Bootstrap JS -->
-    <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"></script>
-
-    <script>
-        // Expand/Collapse functionality
-        document.querySelectorAll('.expand-icon').forEach(icon => {
-            icon.addEventListener('click', function() {
-                const rowId = this.getAttribute('data-row');
-                const contentRow = document.getElementById(rowId + '-content');
-                const parentRow = this.closest('tr');
-                
-                if (contentRow.style.display === 'none') {
-                    contentRow.style.display = 'table-row';
-                    parentRow.classList.add('expanded-row');
-                    this.classList.add('expanded');
-                    this.innerHTML = '<i class="fas fa-chevron-up"></i>';
-                } else {
-                    contentRow.style.display = 'none';
-                    parentRow.classList.remove('expanded-row');
-                    this.classList.remove('expanded');
-                    this.innerHTML = '<i class="fas fa-chevron-down"></i>';
-                }
-            });
-        });
-
-        // Tab switching functionality
-        document.querySelectorAll('.content-tab').forEach(tab => {
-            tab.addEventListener('click', function() {
-                const tabId = this.getAttribute('data-tab');
-                const tabContainer = this.closest('.expandable-content');
-                
-                // Update active tab
-                tabContainer.querySelectorAll('.content-tab').forEach(t => t.classList.remove('active'));
-                this.classList.add('active');
-                
-                // Update active pane
-                const tabContent = tabContainer.querySelector('.tab-content');
-                tabContent.querySelectorAll('.tab-pane').forEach(p => p.classList.remove('active'));
-                tabContent.querySelector('#' + tabId).classList.add('active');
-            });
-        });
-
-        // Copy button functionality
-        document.querySelectorAll('.copy-code-button').forEach(button => {
-            button.addEventListener('click', function() {
-                const targetId = this.getAttribute('data-copy');
-                const codeElement = document.getElementById(targetId);
-                const text = codeElement.textContent;
-                
-                navigator.clipboard.writeText(text).then(() => {
-                    const originalText = this.textContent;
-                    this.textContent = 'Copied!';
-                    this.style.background = '#10b981';
-                    
-                    setTimeout(() => {
-                        this.textContent = originalText;
-                        this.style.background = '';
-                    }, 2000);
-                }).catch(err => {
-                    console.error('Failed to copy:', err);
-                    this.textContent = 'Error';
-                    setTimeout(() => {
-                        this.textContent = 'Copy';
-                    }, 2000);
-                });
-            });
-        });
-
-        // Sorting functionality
-        const sortMap = {
-            'dl19-ap': 2,
-            'dl19-ndcg': 3,
-            'dl19-recall': 4,
-            'dl20-ap': 6,
-            'dl20-ndcg': 7,
-            'dl20-recall': 8,
-            'dlhard-ap': 10,
-            'dlhard-ndcg': 11,
-            'dlhard-recall': 12
-        };
-
-        let currentSort = { column: null, direction: 'desc' };
-
-        document.querySelectorAll('.sortable').forEach(header => {
-            header.addEventListener('click', function() {
-                const sortKey = this.getAttribute('data-sort');
-                const columnIndex = sortMap[sortKey];
-                const tbody = document.querySelector('.leaderboard-table tbody');
-                
-                // Get all accordion rows (main data rows)
-                const accordionRows = Array.from(tbody.querySelectorAll('tr.accordion-row'));
-                
-                // Find the row with config cell and extract it
-                let configCell = null;
-                let rowspan = null;
-                accordionRows.forEach(row => {
-                    const cell = row.querySelector('td.config-cell');
-                    if (cell) {
-                        configCell = cell.cloneNode(true);
-                        rowspan = parseInt(cell.getAttribute('rowspan') || '1');
-                        // Remove config cell from original row temporarily
-                        cell.remove();
-                    }
-                });
-                
-                // Determine sort direction
-                if (currentSort.column === sortKey) {
-                    currentSort.direction = currentSort.direction === 'asc' ? 'desc' : 'asc';
-                } else {
-                    currentSort.column = sortKey;
-                    currentSort.direction = 'desc';
-                }
-
-                // Remove sort indicators from all headers
-                document.querySelectorAll('.sortable').forEach(h => {
-                    h.classList.remove('sort-asc', 'sort-desc');
-                });
-
-                // Add sort indicator to current header
-                this.classList.add('sort-' + currentSort.direction);
-
-                // Create pairs of accordion row and its expandable content
-                // After removing config cell, all rows have same structure, so use columnIndex - 1
-                const rowPairs = accordionRows.map(row => {
-                    const target = row.getAttribute('data-target');
-                    const expandable = document.getElementById(target + '-content');
-                    // After config cell removal, metrics are at columnIndex - 1
-                    const valueCell = row.cells[columnIndex - 1];
-                    return {
-                        accordion: row,
-                        expandable: expandable || null,
-                        value: parseFloat(valueCell?.querySelector('.metric-value')?.textContent || 0)
-                    };
-                });
-
-                // Sort pairs by metric value
-                rowPairs.sort((a, b) => {
-                    if (currentSort.direction === 'asc') {
-                        return a.value - b.value;
-                    } else {
-                        return b.value - a.value;
-                    }
-                });
-
-                // Remove all rows from tbody
-                const allRows = Array.from(tbody.querySelectorAll('tr'));
-                allRows.forEach(row => row.remove());
-
-                // Re-insert sorted pairs with config cell in first row
-                rowPairs.forEach((pair, index) => {
-                    if (index === 0 && configCell && rowspan) {
-                        // Insert config cell as first cell in first row
-                        const newConfigCell = configCell.cloneNode(true);
-                        newConfigCell.setAttribute('rowspan', rowspan);
-                        pair.accordion.insertBefore(newConfigCell, pair.accordion.cells[0]);
-                    }
-                    
-                    tbody.appendChild(pair.accordion);
-                    if (pair.expandable) {
-                        tbody.appendChild(pair.expandable);
-                    }
-                });
-            });
-        });
-
-        // Dark mode toggle
-        const themeToggle = document.getElementById('themeToggle');
-        const themeIcon = themeToggle.querySelector('i');
-        
-        // Check for saved theme preference or default to light
-        const savedTheme = localStorage.getItem('querygym-theme') || 'light';
-        if (savedTheme === 'dark') {
-            document.documentElement.setAttribute('data-theme', 'dark');
-            themeIcon.classList.remove('fa-moon');
-            themeIcon.classList.add('fa-sun');
-        }
-        
-        themeToggle.addEventListener('click', () => {
-            const currentTheme = document.documentElement.getAttribute('data-theme');
-            const newTheme = currentTheme === 'dark' ? 'light' : 'dark';
-            
-            document.documentElement.setAttribute('data-theme', newTheme);
-            localStorage.setItem('querygym-theme', newTheme);
-            
-            if (newTheme === 'dark') {
-                themeIcon.classList.remove('fa-moon');
-                themeIcon.classList.add('fa-sun');
-            } else {
-                themeIcon.classList.remove('fa-sun');
-                themeIcon.classList.add('fa-moon');
-            }
-        });
-    </script>
-
-</body>
-</html>
-
diff --git a/index.md b/index.md
deleted file mode 100644
index 4243dc6..0000000
--- a/index.md
+++ /dev/null
@@ -1,6 +0,0 @@
----
-layout: default
-title: Home
----
-
-{% include_relative README.md %}

Configuration	Method	TREC DL 2019				TREC DL 2020				DL HARD
		AP	nDCG@10	R@1K		AP	nDCG@10	R@1K		AP	nDCG@10	R@1K
- - - - BM25 - - k1=0.9, b=0.4 - - -	- BM25 (Baseline) -	0.3013	0.5058	0.7501		0.2856	0.4796	0.7863		0.1595	0.2850	0.6806
- - - - GPT-4.1-mini - - temp=1.0, max_tokens=128 - - - - BM25 - - k1=0.9, b=0.4 - - -	- - - - Query2Doc (ZS) -	0.4508	0.6709	0.8746		0.4325	0.6323	0.8864		0.2276	0.3303	0.7704
	- - - - Query2Doc (FS) -	0.4418	0.6532	0.8521		0.4051	0.6111	0.8869		0.2260	0.3388	0.7842
	- - - - Query2Doc (CoT) -	0.4145	0.6128	0.8495		0.3801	0.5894	0.8846		0.2225	0.3191	0.7524
	- - - - - - - - Command to reproduce results on TREC DL 2019: - - - `python examples/querygym_pyserini/pipeline.py \ - --dataset msmarco-v1-passage.trecdl2019 \ - --method query2doc \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --output-dir outputs/dl19_query2doc_zs` - - - - Command to reproduce results on TREC DL 2020: - - - `python examples/querygym_pyserini/pipeline.py \ - --dataset msmarco-v1-passage.trecdl2020 \ - --method query2doc \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --output-dir outputs/dl20_query2doc_zs` - - - - Command to reproduce results on DL HARD: - - - `python examples/querygym_pyserini/pipeline.py \ - --queries-file path/to/queries.tsv \ - --qrels-file path/to/qrels.trec \ - --index-name msmarco-v1-passage \ - --method query2doc \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --output-dir outputs/dlhard_query2doc_zs` - - - -
	- - - - - - - - Command to reproduce results on TREC DL 2019: - - - `python examples/querygym_pyserini/pipeline.py \ - --dataset msmarco-v1-passage.trecdl2019 \ - --method query2doc \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"mode":"fs","num_examples":4,"dataset_type":"msmarco",' \ - '"collection_path":"path/to/collection.tsv",' \ - '"train_queries_path":"path/to/queries.train.tsv","train_qrels_path":"path/to/qrels.train.tsv"}' \ - --output-dir outputs/dl19_query2doc` - - - - Command to reproduce results on TREC DL 2020: - - - `python examples/querygym_pyserini/pipeline.py \ - --dataset msmarco-v1-passage.trecdl2020 \ - --method query2doc \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"mode":"fs","num_examples":4,"dataset_type":"msmarco",' \ - '"collection_path":"path/to/collection.tsv",' \ - '"train_queries_path":"path/to/queries.train.tsv","train_qrels_path":"path/to/qrels.train.tsv"}' \ - --output-dir outputs/dl20_query2doc` - - - - Command to reproduce results on DL HARD: - - - python examples/querygym_pyserini/pipeline.py \ - --queries-file path/to/queries.tsv \ - --qrels-file path/to/qrels.trec \ - --index-name msmarco-v1-passage \ - --method query2doc \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"mode":"fs","num_examples":4,"dataset_type":"msmarco",' \ - '"collection_path":"path/to/collection.tsv",' \ - '"train_queries_path":"path/to/queries.train.tsv","train_qrels_path":"path/to/qrels.train.tsv"}' \ - --output-dir outputs/dlhard_query2doc - - - -
	- - - - - - - - Command to reproduce results on TREC DL 2019: - - - `python examples/querygym_pyserini/pipeline.py \ - --dataset msmarco-v1-passage.trecdl2019 \ - --method query2doc \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"mode":"cot"}' \ - --output-dir outputs/dl19_query2doc_cot` - - - - Command to reproduce results on TREC DL 2020: - - - `python examples/querygym_pyserini/pipeline.py \ - --dataset msmarco-v1-passage.trecdl2020 \ - --method query2doc \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"mode":"cot"}' \ - --output-dir outputs/dl20_query2doc_cot` - - - - Command to reproduce results on DL HARD: - - - `python examples/querygym_pyserini/pipeline.py \ - --queries-file path/to/queries.tsv \ - --qrels-file path/to/qrels.trec \ - --index-name msmarco-v1-passage \ - --method query2doc \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"mode":"cot"}' \ - --output-dir outputs/dlhard_query2doc_cot` - - - -
	- - - - Query2E (ZS) -	0.3709	0.5679	0.8384		0.3436	0.5624	0.8373		0.1845	0.3179	0.7642
- - - - - - - - Command to reproduce results on TREC DL 2019: - - - `python examples/querygym_pyserini/pipeline.py \ - --queries-file path/to/original_queries.tsv \ - --qrels-file path/to/qrels.trec \ - --index-name msmarco-v1-passage \ - --method query2e \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"mode":"zs"}' \ - --output-dir outputs/dl19_query2e_zs` - - - - Command to reproduce results on TREC DL 2020: - - - `python examples/querygym_pyserini/pipeline.py \ - --queries-file path/to/original_queries.tsv \ - --qrels-file path/to/qrels.trec \ - --index-name msmarco-v1-passage \ - --method query2e \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"mode":"zs"}' \ - --output-dir outputs/dl20_query2e_zs` - - - - Command to reproduce results on DL HARD: - - - `python examples/querygym_pyserini/pipeline.py \ - --queries-file path/to/original_queries.tsv \ - --qrels-file path/to/qrels.trec \ - --index-name msmarco-v1-passage \ - --method query2e \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"mode":"zs"}' \ - --output-dir outputs/dlhard_query2e_zs` - - - -
- - - - CSQE -	0.4007	0.5962	0.8506		0.3542	0.5298	0.8431		0.2170	0.3194	0.7276
- - - - - - - - Command to reproduce results on TREC DL 2019: - - - `python examples/querygym_pyserini/pipeline.py \ - --dataset msmarco-v1-passage.trecdl2019 \ - --method csqe \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 1024 \ - --method-params '{"retrieval_k":10,"gen_num":2}' \ - --output-dir outputs/dl19_csqe` - - - - Command to reproduce results on TREC DL 2020: - - - `python examples/querygym_pyserini/pipeline.py \ - --dataset msmarco-v1-passage.trecdl2020 \ - --method csqe \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 1024 \ - --method-params '{"retrieval_k":10,"gen_num":2}' \ - --output-dir outputs/dl20_csqe` - - - - Command to reproduce results on DL HARD: - - - `python examples/querygym_pyserini/pipeline.py \ - --queries-file path/to/original_queries.tsv \ - --qrels-file path/to/qrels.trec \ - --index-name msmarco-v1-passage \ - --method csqe \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 1024 \ - --method-params '{"retrieval_k":10,"gen_num":2}' \ - --output-dir outputs/dlhard_csqe` - - - -
- - - - LameR -	0.4185	0.6587	0.8611		0.4432	0.6353	0.8839		0.2562	0.3623	0.7887
- - - - - - - - Command to reproduce results on TREC DL 2019: - - - `python examples/querygym_pyserini/pipeline.py \ - --dataset msmarco-v1-passage.trecdl2019 \ - --method lamer \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"retrieval_k":10,"gen_passages":5}' \ - --output-dir outputs/dl19_lamer` - - - - Command to reproduce results on TREC DL 2020: - - - `python examples/querygym_pyserini/pipeline.py \ - --dataset msmarco-v1-passage.trecdl2020 \ - --method lamer \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"retrieval_k":10,"gen_passages":5}' \ - --output-dir outputs/dl20_lamer` - - - - Command to reproduce results on DL HARD: - - - `python examples/querygym_pyserini/pipeline.py \ - --queries-file path/to/original_queries.tsv \ - --qrels-file path/to/qrels.trec \ - --index-name msmarco-v1-passage \ - --method lamer \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"retrieval_k":10,"gen_passages":5}' \ - --output-dir outputs/dlhard_lamer` - - - -
- - - - MuGI -	0.4766	0.6903	0.8822		0.4353	0.6300	0.8985		0.2393	0.3515	0.7974
- - - - - - - - Command to reproduce results on TREC DL 2019: - - - `python examples/querygym_pyserini/pipeline.py \ - --dataset msmarco-v1-passage.trecdl2019 \ - --method mugi \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"num_docs":5,"parallel":true,"mode":"zs"}' \ - --output-dir outputs/dl19_mugi_zs` - - - - Command to reproduce results on TREC DL 2020: - - - `python examples/querygym_pyserini/pipeline.py \ - --dataset msmarco-v1-passage.trecdl2020 \ - --method mugi \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"num_docs":5,"parallel":true,"mode":"zs"}' \ - --output-dir outputs/dl20_mugi_zs` - - - - Command to reproduce results on DL HARD: - - - `python examples/querygym_pyserini/pipeline.py \ - --queries-file path/to/original_queries.tsv \ - --qrels-file path/to/qrels.trec \ - --index-name msmarco-v1-passage \ - --method mugi \ - --model gpt-4.1-mini \ - --temperature 1.0 \ - --max-tokens 128 \ - --method-params '{"num_docs":5,"parallel":true,"mode":"zs"}' \ - --output-dir outputs/dlhard_mugi_zs` - - - -