docs(eval): add human evaluation report for fixed_size ±3
Why: - Manager deliverable for human evaluation across 10 benchmark documents. Changes: - Report markdown, scored CSV, chart generator, and SVG assets - Linked from docs/README.md Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
37
docs/assets/human-eval/mean-human-by-document.svg
Normal file
37
docs/assets/human-eval/mean-human-by-document.svg
Normal file
@@ -0,0 +1,37 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<svg xmlns="http://www.w3.org/2000/svg" width="720" height="380" viewBox="0 0 720 380" role="img" aria-label="Mean human score by document">
|
||||
<title>Mean human score by document</title>
|
||||
<rect width="720" height="380" fill="#ffffff"/>
|
||||
<text x="20" y="28" font-family="Inter, system-ui, sans-serif" font-size="16" font-weight="700" fill="#111827">Mean human score by document (1–5)</text>
|
||||
<text x="20" y="48" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#6b7280">fixed_size ±3 · stratified sample · higher is better</text>
|
||||
<rect x="120" y="61.4" width="429.3" height="17.6" rx="4" fill="#14b8a6"/>
|
||||
<text x="112" y="73.4" text-anchor="end" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#111827">havades-ind</text>
|
||||
<text x="555.3" y="73.4" font-family="Inter, system-ui, sans-serif" font-size="12" font-weight="600" fill="#111827">3.83</text>
|
||||
<rect x="120" y="89.8" width="448.0" height="17.6" rx="4" fill="#14b8a6"/>
|
||||
<text x="112" y="101.8" text-anchor="end" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#111827">customer1</text>
|
||||
<text x="574.0" y="101.8" font-family="Inter, system-ui, sans-serif" font-size="12" font-weight="600" fill="#111827">4.00</text>
|
||||
<rect x="120" y="118.2" width="448.0" height="17.6" rx="4" fill="#14b8a6"/>
|
||||
<text x="112" y="130.2" text-anchor="end" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#111827">havades</text>
|
||||
<text x="574.0" y="130.2" font-family="Inter, system-ui, sans-serif" font-size="12" font-weight="600" fill="#111827">4.00</text>
|
||||
<rect x="120" y="146.6" width="466.7" height="17.6" rx="4" fill="#14b8a6"/>
|
||||
<text x="112" y="158.6" text-anchor="end" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#111827">website</text>
|
||||
<text x="592.7" y="158.6" font-family="Inter, system-ui, sans-serif" font-size="12" font-weight="600" fill="#111827">4.17</text>
|
||||
<rect x="120" y="175.0" width="485.3" height="17.6" rx="4" fill="#14b8a6"/>
|
||||
<text x="112" y="187.0" text-anchor="end" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#111827">bazresi</text>
|
||||
<text x="611.3" y="187.0" font-family="Inter, system-ui, sans-serif" font-size="12" font-weight="600" fill="#111827">4.33</text>
|
||||
<rect x="120" y="203.4" width="485.3" height="17.6" rx="4" fill="#14b8a6"/>
|
||||
<text x="112" y="215.4" text-anchor="end" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#111827">lifetime-ind</text>
|
||||
<text x="611.3" y="215.4" font-family="Inter, system-ui, sans-serif" font-size="12" font-weight="600" fill="#111827">4.33</text>
|
||||
<rect x="120" y="231.8" width="485.3" height="17.6" rx="4" fill="#14b8a6"/>
|
||||
<text x="112" y="243.8" text-anchor="end" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#111827">lifetime-comp</text>
|
||||
<text x="611.3" y="243.8" font-family="Inter, system-ui, sans-serif" font-size="12" font-weight="600" fill="#111827">4.33</text>
|
||||
<rect x="120" y="260.2" width="504.0" height="17.6" rx="4" fill="#14b8a6"/>
|
||||
<text x="112" y="272.2" text-anchor="end" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#111827">fire</text>
|
||||
<text x="630.0" y="272.2" font-family="Inter, system-ui, sans-serif" font-size="12" font-weight="600" fill="#111827">4.50</text>
|
||||
<rect x="120" y="288.6" width="522.7" height="17.6" rx="4" fill="#14b8a6"/>
|
||||
<text x="112" y="300.6" text-anchor="end" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#111827">Refah</text>
|
||||
<text x="648.7" y="300.6" font-family="Inter, system-ui, sans-serif" font-size="12" font-weight="600" fill="#111827">4.67</text>
|
||||
<rect x="120" y="317.0" width="541.3" height="17.6" rx="4" fill="#14b8a6"/>
|
||||
<text x="112" y="329.0" text-anchor="end" font-family="Inter, system-ui, sans-serif" font-size="12" fill="#111827">moavenin</text>
|
||||
<text x="667.3" y="329.0" font-family="Inter, system-ui, sans-serif" font-size="12" font-weight="600" fill="#111827">4.83</text>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 3.9 KiB |
Reference in New Issue
Block a user