egor-bogomolov's picture
Add 28 benchmark datasets with rich visualization views
9a8a9c5
.problem-header {
display: flex;
justify-content: space-between;
align-items: center;
margin-bottom: 15px;
}
.problem-meta {
margin-bottom: 20px;
}
.meta-item {
display: inline-block;
margin-right: 15px;
margin-bottom: 10px;
}
.meta-label {
font-weight: 600;
color: #7f8c8d;
margin-right: 5px;
}
.meta-value {
color: #2c3e50;
}
.task-selector {
margin: 20px 0;
display: flex;
gap: 10px;
flex-wrap: wrap;
}
.task-btn {
padding: 10px 20px;
background: #ecf0f1;
border: 2px solid transparent;
border-radius: 4px;
cursor: pointer;
transition: all 0.3s;
font-size: 0.95rem;
}
.task-btn:hover {
background: #bdc3c7;
}
.task-btn.active {
background: #3498db;
color: white;
border-color: #2980b9;
}
.task-details {
margin-top: 20px;
}
.task-section {
margin-bottom: 25px;
padding: 15px;
background: #f8f9fa;
border-left: 4px solid #3498db;
border-radius: 4px;
}
.task-section h3 {
margin-bottom: 10px;
color: #2c3e50;
font-size: 1.1rem;
}
.code-block {
background: #f8f9fa;
padding: 15px;
border-radius: 4px;
overflow-x: auto;
font-family: 'Monaco', 'Menlo', 'Ubuntu Mono', monospace;
font-size: 0.9rem;
border: 1px solid #e1e4e8;
}
.task-items-list {
list-style: none;
}
.task-items-list li {
padding: 10px;
margin-bottom: 8px;
background: white;
border-radius: 4px;
border: 1px solid #e1e4e8;
}
.line-ref {
display: inline-block;
padding: 2px 8px;
background: #3498db;
color: white;
border-radius: 3px;
font-family: monospace;
font-size: 0.85rem;
margin-right: 8px;
}
.var-name {
display: inline-block;
padding: 2px 8px;
background: #9b59b6;
color: white;
border-radius: 3px;
font-family: monospace;
font-size: 0.85rem;
}
.io-section {
display: grid;
grid-template-columns: 1fr 1fr;
gap: 15px;
}
@media (max-width: 768px) {
.io-section {
grid-template-columns: 1fr;
}
}
.navigation-hint {
margin-top: 20px;
padding: 15px;
background: #e8f4f8;
border-radius: 4px;
color: #2c3e50;
font-size: 0.9rem;
}
.test-code-section {
margin-top: 20px;
}
/* Inline task visualization */
.code-with-tasks {
position: relative;
}
.task-marker {
display: inline-block;
margin-left: 10px;
padding: 2px 8px;
background: #9b59b6;
color: white;
border-radius: 3px;
font-size: 0.75rem;
font-weight: 600;
cursor: crosshair;
}
/* Coverage coloring on lineno spans */
td.linenos .normal.line-executed {
background-color: #d4edda !important;
color: #155724 !important;
}
td.linenos .normal.line-not-executed {
background-color: #f8d7da !important;
color: #721c24 !important;
}
/* Coverage legend */
.coverage-legend {
margin: 10px 0;
padding: 10px 15px;
background: #f8f9fa;
border-left: 4px solid #28a745;
border-radius: 4px;
font-size: 0.85rem;
display: none;
}
.coverage-legend-item {
display: inline-block;
margin-right: 18px;
}
.coverage-swatch {
display: inline-block;
width: 12px;
height: 12px;
border-radius: 2px;
margin-right: 4px;
vertical-align: middle;
}
/* Ground truth answer badge */
.gt-answer {
display: inline-block;
margin-left: 10px;
padding: 2px 8px;
background: #17a2b8;
color: white;
border-radius: 3px;
font-family: monospace;
font-size: 0.82rem;
font-weight: 600;
}
.gt-answer.loading {
background: #6c757d;
}
/* SVG arrow overlay */
#arrow-overlay {
position: absolute;
top: 0;
left: 0;
width: 100%;
height: 100%;
pointer-events: none;
overflow: visible;
z-index: 10;
}
.exec-arrow {
fill: none;
stroke: #e67e22;
stroke-width: 2.5;
stroke-dasharray: none;
opacity: 0.9;
}
.exec-arrow-head {
fill: #e67e22;
opacity: 0.9;
}
/* CRUXEval answer highlight */
.crux-answer {
border-left: 4px solid #17a2b8 !important;
background: #e8f6f8 !important;
}
/* Before/after diff view */
.diff-container {
display: grid;
grid-template-columns: 1fr 1fr;
gap: 20px;
}
@media (max-width: 1024px) {
.diff-container {
grid-template-columns: 1fr;
}
}
.diff-panel {
overflow-x: auto;
}
.diff-panel h3 {
margin-bottom: 10px;
font-size: 1.1rem;
}
.diff-panel h3 .diff-label-buggy {
color: #e74c3c;
}
.diff-panel h3 .diff-label-fixed {
color: #27ae60;
}
.bug-info {
margin-bottom: 15px;
padding: 12px 15px;
border-left: 4px solid #e74c3c;
background: #fdf2f2;
border-radius: 4px;
}
.bug-info .bug-category {
display: inline-block;
padding: 2px 8px;
background: #e74c3c;
color: white;
border-radius: 3px;
font-size: 0.82rem;
font-weight: 600;
margin-right: 8px;
}
.bug-info .bug-subtype {
display: inline-block;
padding: 2px 8px;
background: #c0392b;
color: white;
border-radius: 3px;
font-size: 0.82rem;
font-weight: 600;
}
/* Multi-language view */
.lang-tabs {
display: flex;
gap: 0;
border-bottom: 2px solid #e1e4e8;
margin-bottom: 0;
}
.lang-tab {
padding: 10px 20px;
background: #f8f9fa;
border: 1px solid #e1e4e8;
border-bottom: none;
cursor: pointer;
font-size: 0.95rem;
font-weight: 500;
transition: all 0.2s;
border-radius: 4px 4px 0 0;
margin-right: 2px;
}
.lang-tab:hover {
background: #e8f4f8;
}
.lang-tab.active {
background: white;
border-bottom: 2px solid white;
margin-bottom: -2px;
color: #3498db;
font-weight: 600;
}
.lang-code-panel {
display: none;
}
.lang-code-panel.active {
display: block;
}
/* BigOBench complexity display */
.complexity-badges {
display: flex;
gap: 20px;
flex-wrap: wrap;
}
.complexity-item {
display: flex;
align-items: center;
gap: 10px;
}
.complexity-label {
font-weight: 600;
color: #7f8c8d;
font-size: 0.95rem;
}
.complexity-value {
display: inline-block;
padding: 6px 16px;
background: #2c3e50;
color: #f1c40f;
border-radius: 4px;
font-family: 'Monaco', 'Menlo', 'Ubuntu Mono', monospace;
font-size: 1.1rem;
font-weight: 600;
}
/* Diff view (GitHub-style table with line numbers) */
.diff-view {
font-family: 'Monaco', 'Menlo', 'Ubuntu Mono', monospace;
font-size: 0.85rem;
line-height: 1.5;
overflow-x: auto;
border: 1px solid #e1e4e8;
border-radius: 4px;
}
.diff-table {
border-collapse: collapse;
width: 100%;
}
.diff-table td {
padding: 0 8px;
white-space: pre;
vertical-align: top;
}
.diff-ln {
width: 1%;
min-width: 40px;
color: #959da5;
text-align: right;
user-select: none;
font-size: 0.8rem;
padding: 0 6px !important;
border-right: 1px solid #e1e4e8;
}
.diff-tr-add td { background: #e6ffec; }
.diff-td-add { color: #24292e; }
.diff-tr-add .diff-ln { background: #ccffd8; color: #22863a; }
.diff-tr-del td { background: #ffebe9; }
.diff-td-del { color: #24292e; }
.diff-tr-del .diff-ln { background: #ffd7d5; color: #cb2431; }
.diff-tr-ctx td { background: white; }
.diff-td-ctx { color: #586069; }
.diff-tr-hunk td {
background: #f1f8ff;
color: #0366d6;
font-weight: 600;
padding: 4px 8px;
}
.diff-tr-header td {
background: #fafbfc;
color: #6a737d;
font-weight: 600;
padding: 4px 8px;
border-bottom: 1px solid #e1e4e8;
}
/* Diff file sections (GitHub-style per-file headers) */
.diff-file-section {
margin-bottom: 16px;
border: 1px solid #d0d7de;
border-radius: 6px;
overflow: hidden;
}
.diff-file-section .diff-view {
border: none;
border-radius: 0;
}
.diff-file-header {
display: flex;
justify-content: space-between;
align-items: center;
padding: 8px 12px;
background: #f6f8fa;
border-bottom: 1px solid #d0d7de;
font-family: 'Monaco', 'Menlo', 'Ubuntu Mono', monospace;
font-size: 0.85rem;
}
.diff-file-path {
color: #24292f;
font-weight: 600;
word-break: break-all;
}
.diff-file-stats {
white-space: nowrap;
margin-left: 12px;
font-size: 0.8rem;
}
.diff-stat-add { color: #1a7f37; font-weight: 600; }
.diff-stat-del { color: #cf222e; font-weight: 600; margin-left: 6px; }
/* GitHub links bar */
.gh-links-bar {
display: flex;
gap: 12px;
align-items: center;
flex-wrap: wrap;
}
.gh-link {
display: inline-block;
padding: 6px 14px;
background: #f6f8fa;
border: 1px solid #d0d7de;
border-radius: 6px;
color: #0969da;
text-decoration: none;
font-size: 0.9rem;
font-weight: 500;
transition: background 0.15s, border-color 0.15s;
}
.gh-link:hover {
background: #ddf4ff;
border-color: #0969da;
}
/* Issue / problem statement */
.issue-statement {
line-height: 1.7;
padding: 10px;
white-space: pre-wrap;
word-wrap: break-word;
max-height: 500px;
overflow-y: auto;
background: #f8f9fa;
border: 1px solid #e1e4e8;
border-radius: 4px;
font-size: 0.9rem;
}
.test-id-list {
list-style: none;
padding: 0;
}
.test-id-list li {
padding: 4px 8px;
margin-bottom: 4px;
background: #f8f9fa;
border-radius: 3px;
font-family: monospace;
font-size: 0.82rem;
border-left: 3px solid #e74c3c;
}
.test-id-list li.pass-to-pass {
border-left-color: #27ae60;
}
/* Fill-in-the-Middle (SAFIM) view */
.fim-hole-marker {
display: inline-block;
padding: 4px 16px;
background: #e74c3c;
color: white;
border-radius: 4px;
font-family: monospace;
font-weight: 600;
font-size: 0.9rem;
margin: 4px 0;
}
.fim-answer {
padding: 15px;
background: #e8f6e8;
border-left: 4px solid #27ae60;
border-radius: 4px;
font-family: monospace;
font-size: 0.9rem;
}
.fim-merged-legend {
margin: 8px 0;
padding: 6px 12px;
background: #f8f9fa;
border-radius: 4px;
font-size: 0.85rem;
color: #555;
}
/* Vulnerability view */
.vuln-status {
display: inline-block;
padding: 4px 12px;
border-radius: 4px;
font-size: 0.85rem;
font-weight: 600;
}
.vuln-status-vulnerable {
background: #e74c3c;
color: white;
}
.vuln-status-patched {
background: #27ae60;
color: white;
}
.cwe-badge {
display: inline-block;
padding: 4px 12px;
background: #2c3e50;
color: #e74c3c;
border-radius: 4px;
font-family: monospace;
font-size: 0.85rem;
font-weight: 600;
}