evalstate's picture
download
raw
17.3 kB
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Numeric-data stability analysis — rendering checker</title>
<style data-birch-system>
:root {
color-scheme: light;
--color-ivory: #FAF9F5;
--color-slate: #141413;
--color-clay: #D97757;
--color-clay-dark: #B85C3E;
--color-oat: #E3DACC;
--color-olive: #788C5D;
--color-rust: #B04A3F;
--color-sky: #6A8CAF;
--color-white: #FFFFFF;
--color-gray-50: #F7F5EE;
--color-gray-100: #F0EEE6;
--color-gray-150: #E8E4DA;
--color-gray-200: #DED9CD;
--color-gray-300: #D1CFC5;
--color-gray-500: #87867F;
--color-gray-700: #3D3D3A;
--color-gray-800: #242421;
--bg: var(--color-ivory);
--surface: var(--color-white);
--surface-tint: var(--color-gray-100);
--surface-warm: var(--color-oat);
--text: var(--color-slate);
--text-muted: var(--color-gray-500);
--text-soft: var(--color-gray-700);
--muted: var(--text-muted);
--border-color: var(--color-gray-300);
--accent: var(--color-clay);
--accent-strong: var(--color-clay-dark);
--success: var(--color-olive);
--warning: #C78E3F;
--danger: var(--color-rust);
--info: var(--color-sky);
--font-serif: ui-serif, Georgia, "Times New Roman", serif;
--font-sans: system-ui, -apple-system, "Segoe UI", Roboto, sans-serif;
--font-mono: ui-monospace, "SF Mono", Menlo, Consolas, monospace;
--text-xs: 11px;
--text-sm: 12px;
--text-md: 14px;
--text-base: 15px;
--text-lg: 17px;
--text-xl: 21px;
--text-2xl: 26px;
--text-3xl: 36px;
--text-4xl: 44px;
--leading-tight: 1.15;
--leading-title: 1.25;
--leading-body: 1.55;
--space-1: 4px;
--space-2: 8px;
--space-3: 12px;
--space-4: 16px;
--space-5: 24px;
--space-6: 32px;
--space-7: 48px;
--space-8: 64px;
--space-9: 96px;
--radius-xs: 4px;
--radius-sm: 8px;
--radius-md: 12px;
--radius-lg: 16px;
--radius-pill: 999px;
--border: 1.5px solid var(--border-color);
--border-thin: 1px solid var(--border-color);
--dur-fast: 120ms;
--dur: 180ms;
--hover-y: -2px;
--page-max: 1100px;
--page-pad: 28px;
--page-pad-block: 48px;
--panel-pad: var(--space-5);
--card-pad: var(--space-5);
}
*, *::before, *::after {
box-sizing: border-box;
}
html {
background: var(--bg);
color: var(--text);
font-family: var(--font-sans);
-webkit-text-size-adjust: 100%;
}
body {
margin: 0;
background: var(--bg);
color: var(--text);
font-size: var(--text-base);
line-height: 1.55;
font-family: var(--font-sans);
}
h1, h2, h3 {
margin: 0;
font-family: var(--font-serif);
line-height: 1.2;
}
h1 { font-size: clamp(28px, 4.8vw, var(--text-4xl)); }
h2 { font-size: var(--text-2xl); }
p { margin: 0; }
code { font-family: var(--font-mono); }
a { color: inherit; }
.page {
width: min(100% - (var(--page-pad) * 2), var(--page-max));
margin-inline: auto;
padding-block: var(--page-pad-block) var(--space-9);
}
.stack {
display: flex;
flex-direction: column;
gap: var(--stack-gap, var(--space-4));
}
.stack[data-gap="xs"] { --stack-gap: var(--space-2); }
.stack[data-gap="sm"] { --stack-gap: var(--space-3); }
.stack[data-gap="md"] { --stack-gap: var(--space-4); }
.stack[data-gap="lg"] { --stack-gap: var(--space-6); }
.stack[data-gap="xl"] { --stack-gap: var(--space-8); }
.section {
margin-block: var(--section-gap, var(--space-5));
}
.section-head .eyebrow { margin-block-end: var(--space-2); }
.auto-grid {
display: grid;
gap: var(--space-5);
grid-template-columns: repeat(auto-fit, minmax(min(100%, var(--grid-min, 210px)), 1fr));
}
.section-rail {
display: grid;
grid-template-columns: minmax(0, 1fr) minmax(260px, 360px);
gap: var(--space-6);
align-items: start;
}
.section-rail > .section-head {
grid-column: 1 / -1;
}
.eyebrow {
display: inline-flex;
align-items: center;
gap: 8px;
color: var(--accent);
font-family: var(--font-mono);
font-size: var(--text-xs);
font-weight: 700;
letter-spacing: 0.08em;
text-transform: uppercase;
}
.lede {
max-width: 72ch;
color: var(--text-soft);
font-size: var(--text-lg);
}
.caption {
color: var(--text-muted);
font-family: var(--font-mono);
font-size: var(--text-sm);
}
.panel,
.card {
background: var(--surface);
border: var(--border);
border-radius: var(--radius-md);
padding: var(--panel-pad);
}
.stat-card {
gap: 4px;
}
.stat-value {
display: block;
color: var(--text);
font-family: var(--font-serif);
font-size: clamp(28px, 3.2vw, 42px);
font-variant-numeric: tabular-nums;
line-height: 1;
letter-spacing: -0.025em;
font-weight: 550;
}
.metric-list {
--metric-label: 132px;
--metric-value: 150px;
display: grid;
gap: var(--space-3);
}
.metric-row {
display: grid;
grid-template-columns: var(--metric-label) minmax(140px, 1fr) var(--metric-value);
gap: var(--space-3);
align-items: center;
}
.metric-row > :first-child { min-width: 0; }
.metric-row > :last-child {
justify-self: end;
min-width: var(--metric-value);
font-size: var(--text-sm);
font-family: var(--font-mono);
color: var(--text-muted);
white-space: nowrap;
}
.meter {
height: 9px;
border-radius: var(--radius-pill);
background: var(--surface-tint);
overflow: hidden;
}
.meter span {
display: block;
width: var(--value);
height: 100%;
background: var(--accent);
}
.chart-panel { max-width: 100%; min-width: 0; overflow: hidden; }
.chart-panel svg,
.chart-svg {
width: 100%;
height: auto;
display: block;
}
.chart-caption {
color: var(--text-muted);
font-size: var(--text-sm);
}
.numeric-table-wrap {
overflow-x: auto;
background: var(--surface);
border: var(--border);
border-radius: var(--radius-md);
}
.numeric-table {
width: 100%;
border-collapse: collapse;
}
.numeric-table th,
.numeric-table td {
padding: var(--space-3);
border-bottom: 1px solid var(--color-gray-200);
vertical-align: middle;
}
.numeric-table th {
text-align: left;
color: var(--text-muted);
background: var(--surface-tint);
font-family: var(--font-mono);
font-size: 11px;
letter-spacing: 0.08em;
text-transform: uppercase;
}
.numeric-table .metric,
.numeric-table .num {
text-align: right;
font-variant-numeric: tabular-nums;
}
.callout {
border-inline-start: 4px solid var(--info);
background: color-mix(in srgb, var(--info) 12%, transparent);
border-radius: var(--radius-md);
padding: var(--space-4);
border: var(--border);
}
.callout-label {
display: block;
color: var(--text-muted);
font-family: var(--font-mono);
font-size: var(--text-xs);
text-transform: uppercase;
font-weight: 700;
letter-spacing: 0.08em;
margin-block-end: var(--space-2);
}
@media (max-width: 860px) {
:root {
--page-pad: 20px;
--page-pad-block: 40px;
}
.section-rail {
grid-template-columns: 1fr;
}
}
@media (max-width: 620px) {
.metric-row {
grid-template-columns: 1fr max-content;
}
.metric-row .meter {
grid-column: 1 / -1;
}
.metric-row > :last-child {
grid-column: 2;
}
.numeric-table th,
.numeric-table td {
padding: 10px 8px;
font-size: 12px;
}
}
</style>
</head>
<body>
<main class="page stack" data-gap="lg">
<header class="stack" data-gap="sm">
<div class="eyebrow">Numeric-data stability check</div>
<h1>Rendering checker trend is strong enough to advance toward adoption.</h1>
<p class="lede">From <code>evals/numeric-data/source.csv</code>, pass rose from <strong>85.67%</strong> to <strong>97.67%</strong> over 4 prior weeks while overflow fell <strong>20 → 1</strong>. Latest week (2026-05-18): <strong>97.67%</strong> avg static pass and <strong>1</strong> overflow across three artifacts.</p>
</header>
<section class="section stack" data-gap="lg">
<div class="section-head">
<span class="eyebrow">Evidence strip</span>
<h2>Week-over-week progress</h2>
</div>
<div class="auto-grid" style="--grid-min: 180px;">
<article class="card panel stat-card stack" data-gap="xs">
<div class="eyebrow">Latest weekly pass</div>
<strong class="stat-value">97.67%</strong>
<p class="caption">2026-05-18: mean across 3 artifacts</p>
</article>
<article class="card panel stat-card stack" data-gap="xs">
<div class="eyebrow">Latest overflow total</div>
<strong class="stat-value">1</strong>
<p class="caption">Last week: 3 → 1 (-2)</p>
</article>
<article class="card panel stat-card stack" data-gap="xs">
<div class="eyebrow">Pass delta vs prior week</div>
<strong class="stat-value">+1.33 pts</strong>
<p class="caption">2026-05-11 → 2026-05-18</p>
</article>
<article class="card panel stat-card stack" data-gap="xs">
<div class="eyebrow">Best vs worst this week</div>
<strong class="stat-value">timeline • component-variants</strong>
<p class="caption">99.0% vs 96.0%</p>
</article>
</div>
</section>
<section class="section stack" data-gap="lg">
<div class="section-head">
<span class="eyebrow">Trend and exact values</span>
<h2>Weekly pass-rate trajectory is monotonic and near target</h2>
</div>
<div class="section-rail">
<div class="stack" data-gap="lg">
<article class="panel chart-panel stack" data-gap="sm">
<svg class="chart-svg" viewBox="0 0 760 300" role="img" aria-label="Weekly average static pass rate across all artifacts">
<title>Average static pass by week</title>
<desc>Line chart showing the weekly mean static pass over 2026-04-20 through 2026-05-18.</desc>
<rect x="0" y="0" width="760" height="300" fill="var(--surface)" />
<line x1="64" y1="230" x2="732" y2="230" stroke="var(--border-color)" stroke-width="1" />
<line x1="64" y1="28" x2="64" y2="230" stroke="var(--border-color)" stroke-width="1" />
<line x1="64" y1="252.4" x2="732" y2="252.4" stroke="var(--border-color)" stroke-width="1" stroke-dasharray="4 6" /><line x1="64" y1="196.3" x2="732" y2="196.3" stroke="var(--border-color)" stroke-width="1" stroke-dasharray="4 6" /><line x1="64" y1="140.2" x2="732" y2="140.2" stroke="var(--border-color)" stroke-width="1" stroke-dasharray="4 6" /><line x1="64" y1="84.1" x2="732" y2="84.1" stroke="var(--border-color)" stroke-width="1" stroke-dasharray="4 6" /><line x1="64" y1="28.0" x2="732" y2="28.0" stroke="var(--border-color)" stroke-width="1" stroke-dasharray="4 6" />
<text x="54" y="256.4" text-anchor="end" fill="var(--text-soft)" font-size="11">80%</text><text x="54" y="200.3" text-anchor="end" fill="var(--text-soft)" font-size="11">85%</text><text x="54" y="144.2" text-anchor="end" fill="var(--text-soft)" font-size="11">90%</text><text x="54" y="88.1" text-anchor="end" fill="var(--text-soft)" font-size="11">95%</text><text x="54" y="32.0" text-anchor="end" fill="var(--text-soft)" font-size="11">100%</text>
<path d="M 64.0 188.9 L 231.0 136.5 L 398.0 99.1 L 565.0 69.1 L 732.0 54.2" fill="none" stroke="var(--accent)" stroke-width="4" stroke-linecap="round" stroke-linejoin="round" />
<circle cx="64.0" cy="188.9" r="5.5" fill="var(--surface)" stroke="var(--accent)" stroke-width="3" /><circle cx="231.0" cy="136.5" r="5.5" fill="var(--surface)" stroke="var(--accent)" stroke-width="3" /><circle cx="398.0" cy="99.1" r="5.5" fill="var(--surface)" stroke="var(--accent)" stroke-width="3" /><circle cx="565.0" cy="69.1" r="5.5" fill="var(--surface)" stroke="var(--accent)" stroke-width="3" /><circle cx="732.0" cy="54.2" r="5.5" fill="var(--surface)" stroke="var(--accent)" stroke-width="3" />
<text x="64.0" y="180.9" text-anchor="middle" fill="var(--text)" font-size="11">85.67%</text><text x="231.0" y="128.5" text-anchor="middle" fill="var(--text)" font-size="11">90.33%</text><text x="398.0" y="91.1" text-anchor="middle" fill="var(--text)" font-size="11">93.67%</text><text x="565.0" y="61.1" text-anchor="middle" fill="var(--text)" font-size="11">96.33%</text><text x="732.0" y="46.2" text-anchor="middle" fill="var(--text)" font-size="11">97.67%</text>
<text x="64.0" y="254" text-anchor="middle" fill="var(--text-muted)" font-size="11">Apr 20</text><text x="231.0" y="254" text-anchor="middle" fill="var(--text-muted)" font-size="11">Apr 27</text><text x="398.0" y="254" text-anchor="middle" fill="var(--text-muted)" font-size="11">May 04</text><text x="565.0" y="254" text-anchor="middle" fill="var(--text-muted)" font-size="11">May 11</text><text x="732.0" y="254" text-anchor="middle" fill="var(--text-muted)" font-size="11">May 18</text>
</svg>
<p class="chart-caption">Each point is the unweighted mean static pass for that week across design-system, component-variants, and timeline.</p>
</article>
<article class="panel stack" data-gap="sm">
<div class="section-head">
<span class="eyebrow">Exact numeric table</span>
<h2>Weekly aggregates used in the chart</h2>
</div>
<div class="numeric-table-wrap">
<table class="numeric-table">
<thead>
<tr>
<th scope="col">Week</th>
<th scope="col" class="metric">Avg static pass</th>
<th scope="col" class="metric">Δ pass vs prior</th>
<th scope="col" class="metric">Overflow total</th>
<th scope="col" class="metric">Avg palette_close</th>
<th scope="col" class="metric">Avg mean_rgb_delta</th>
<th scope="col" class="metric">Avg vision_score</th>
</tr>
</thead>
<tbody>
<tr><th scope="row">2026-04-20</th><td class="metric num">85.6667%</td><td class="metric num"></td><td class="metric num">20</td><td class="metric num">0.9033</td><td class="metric num">19.7000</td><td class="metric num">3.0333</td></tr><tr><th scope="row">2026-04-27</th><td class="metric num">90.3333%</td><td class="metric num">+4.67 pp</td><td class="metric num">13</td><td class="metric num">0.9333</td><td class="metric num">15.9667</td><td class="metric num">3.4000</td></tr><tr><th scope="row">2026-05-04</th><td class="metric num">93.6667%</td><td class="metric num">+3.33 pp</td><td class="metric num">8</td><td class="metric num">0.9533</td><td class="metric num">13.2667</td><td class="metric num">3.7667</td></tr><tr><th scope="row">2026-05-11</th><td class="metric num">96.3333%</td><td class="metric num">+2.67 pp</td><td class="metric num">3</td><td class="metric num">0.9700</td><td class="metric num">9.1667</td><td class="metric num">4.1333</td></tr><tr><th scope="row">2026-05-18</th><td class="metric num">97.6667%</td><td class="metric num">+1.33 pp</td><td class="metric num">1</td><td class="metric num">0.9767</td><td class="metric num">7.6667</td><td class="metric num">4.3667</td></tr>
</tbody>
</table>
</div>
</article>
</div>
<aside class="panel stack" data-gap="sm">
<span class="eyebrow">Latest-week ranking</span>
<h2>Artifact ranking with progress bars</h2>
<div class="metric-list">
<div class="metric-row"><span class="caption">timeline</span><div class="meter"><span style="--value:99.0%"></span></div><code>99.0% · 0 overflows</code></div><div class="metric-row"><span class="caption">design-system</span><div class="meter"><span style="--value:98.0%"></span></div><code>98.0% · 0 overflows</code></div><div class="metric-row"><span class="caption">component-variants</span><div class="meter"><span style="--value:96.0%"></span></div><code>96.0% · 1 overflow</code></div>
</div>
<p class="caption">Best: <strong>timeline</strong> at 99.0% with 0 overflow. Worst: <strong>component-variants</strong> at 96.0% with 1 overflow.</p>
</aside>
</div>
</section>
<section class="section">
<article class="callout" role="note">
<span class="callout-label">Source / caveat</span>
<p class="caption">Source-grounded on local file <code>evals/numeric-data/source.csv</code> with <strong>15 rows</strong> (3 artifacts × 5 weeks). No external validation or statistical intervals were applied, so conclusions are trend-level operational signals rather than a formal significance test.</p>
</article>
</section>
</main>
</body>
</html>

Xet Storage Details

Size:
17.3 kB
·
Xet hash:
f0516b709f4d9d0bf8bd622c8e7b75dbc9350f155b8884f2b473c7f5f491fd36

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.