Spaces:
Running
Running
docs: add qwen GEPA proposal graphs
Browse files
gepa-evalstate-qwen-overlay-c4-full-20260616T172947Z/final-report.html
CHANGED
|
@@ -43,6 +43,7 @@ li { margin:5px 0; }
|
|
| 43 |
<a href="#summary">Summary</a>
|
| 44 |
<a href="#heldout">Heldout</a>
|
| 45 |
<a href="#run">Run Config</a>
|
|
|
|
| 46 |
<a href="score_report.html">Iteration Graph</a>
|
| 47 |
<a href="prompt-diffs/index.html">Prompt Diffs</a>
|
| 48 |
<a href="candidate_tree.html">Candidate Tree</a>
|
|
@@ -104,6 +105,7 @@ li { margin:5px 0; }
|
|
| 104 |
<section id="links">
|
| 105 |
<h2>Artifacts</h2>
|
| 106 |
<p>
|
|
|
|
| 107 |
<a class="button" href="score_report.html">Score graph</a>
|
| 108 |
<a class="button" href="prompt-diffs/index.html">Prompt diff picker</a>
|
| 109 |
<a class="button" href="candidate_tree.html">Candidate tree</a>
|
|
|
|
| 43 |
<a href="#summary">Summary</a>
|
| 44 |
<a href="#heldout">Heldout</a>
|
| 45 |
<a href="#run">Run Config</a>
|
| 46 |
+
<a href="proposal-graphs.html">Proposal Graphs</a>
|
| 47 |
<a href="score_report.html">Iteration Graph</a>
|
| 48 |
<a href="prompt-diffs/index.html">Prompt Diffs</a>
|
| 49 |
<a href="candidate_tree.html">Candidate Tree</a>
|
|
|
|
| 105 |
<section id="links">
|
| 106 |
<h2>Artifacts</h2>
|
| 107 |
<p>
|
| 108 |
+
<a class="button" href="proposal-graphs.html">Proposal graphs</a>
|
| 109 |
<a class="button" href="score_report.html">Score graph</a>
|
| 110 |
<a class="button" href="prompt-diffs/index.html">Prompt diff picker</a>
|
| 111 |
<a class="button" href="candidate_tree.html">Candidate tree</a>
|
gepa-evalstate-qwen-overlay-c4-full-20260616T172947Z/proposal-graphs.html
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<!doctype html>
|
| 2 |
+
<html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1"><title>Evalstate Qwen GEPA Proposal Graphs</title><style>
|
| 3 |
+
:root{color-scheme:light;--bg:#f6f8fb;--panel:#fff;--ink:#172033;--muted:#667085;--line:#d8dee9;--green:#137333;--red:#b42318;--blue:#185abc;--amber:#ad5f00}*{box-sizing:border-box}body{margin:0;background:var(--bg);color:var(--ink);font-family:-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,Arial,sans-serif;line-height:1.45}header{background:#fff;border-bottom:1px solid var(--line);padding:28px 32px 20px;position:sticky;top:0;z-index:2}main{max-width:1280px;margin:0 auto;padding:24px 32px 52px}h1{margin:0 0 8px;font-size:28px}h2{margin:0 0 14px;font-size:20px}a{color:#0b57d0;text-decoration:none}.muted{color:var(--muted)}nav{display:flex;gap:10px;flex-wrap:wrap;margin-top:14px}nav a,.button{border:1px solid #c9dcff;background:#eef4ff;border-radius:7px;padding:7px 10px}section{background:var(--panel);border:1px solid var(--line);border-radius:8px;padding:20px;margin-bottom:20px}.gridcards{display:grid;grid-template-columns:repeat(auto-fit,minmax(170px,1fr));gap:12px}.card{border:1px solid var(--line);border-radius:8px;padding:14px;background:#fbfcfe;min-height:96px}.card .label{color:var(--muted);font-size:12px;text-transform:uppercase;letter-spacing:.04em}.card .value{margin-top:8px;font-size:26px;font-weight:750}.card .sub{margin-top:5px;color:var(--muted);font-size:13px}.good{color:var(--green);font-weight:700}.bad{color:var(--red);font-weight:700}.axis{stroke:#94a3b8;stroke-width:1.4}.grid{stroke:#e5eaf2}.tick{fill:#667085;font-size:12px}.axis-label{fill:#334155;font-size:13px}.chart-wrap{border:1px solid var(--line);border-radius:8px;background:#fff;overflow-x:auto}svg{min-width:980px;width:100%;height:auto;display:block}.legend{display:flex;gap:16px;flex-wrap:wrap;margin-top:10px;color:#334155;font-size:13px}.legend i{display:inline-block;width:10px;height:10px;border-radius:999px;margin-right:6px;vertical-align:-1px}.scroll{overflow:auto;border:1px solid var(--line);border-radius:8px}table{width:100%;border-collapse:collapse;font-size:13px}th,td{border-bottom:1px solid var(--line);padding:8px 9px;text-align:left;vertical-align:middle}th{background:#f0f3f8;color:#384152;font-weight:700;line-height:1.2;white-space:nowrap}.accepted{background:#f6fff8}.rejected{background:#fff8f8}.noop{background:#f8fafc;color:#64748b}code{font-family:ui-monospace,SFMono-Regular,Consolas,monospace;font-size:12px}.note{border-left:4px solid var(--amber);padding:10px 12px;background:#fff8eb;color:#4a2d00}@media(max-width:800px){header{position:static}main,header{padding-left:18px;padding-right:18px}}
|
| 4 |
+
</style></head>
|
| 5 |
+
<body><header><h1>Evalstate Qwen GEPA Proposal Graphs</h1><div class="muted">Run: <code>gepa-evalstate-qwen-overlay-c4-full-20260616T172947Z</code>. This page plots every proposal attempt, not only selected/full-eval candidates.</div><nav><a href="final-report.html">Final report</a><a href="score_report.html">Original score report</a><a href="prompt-diffs/index.html">Prompt diffs</a><a href="candidate_tree.html">Candidate tree</a></nav></header><main>
|
| 6 |
+
<section><h2>Proposal Accounting</h2><div class="gridcards">
|
| 7 |
+
<div class="card"><div class="label">Selected iterations</div><div class="value">32</div><div class="sub">GEPA loop iterations</div></div>
|
| 8 |
+
<div class="card"><div class="label">Actual proposals</div><div class="value">31</div><div class="sub">one iteration had no proposal</div></div>
|
| 9 |
+
<div class="card"><div class="label">Accepted proposals</div><div class="value good">19</div><div class="sub">became full-val candidates</div></div>
|
| 10 |
+
<div class="card"><div class="label">Rejected proposals</div><div class="value bad">12</div><div class="sub">subsample not better</div></div>
|
| 11 |
+
<div class="card"><div class="label">Best candidate</div><div class="value good">16</div><div class="sub">from proposal 27</div></div>
|
| 12 |
+
<div class="card"><div class="label">Best Pareto score</div><div class="value good">0.6979</div><div class="sub">seed 0.5742</div></div>
|
| 13 |
+
</div><p class="note">Proposal 29 is shown as a no-proposal iteration because GEPA selected rows that were already perfect and did not create a new candidate. The other 31 rows are the actual proposals.</p></section>
|
| 14 |
+
<section><h2>Old vs New Subsample Score, Every Proposal</h2><div class="chart-wrap"><svg viewBox="0 0 1160 370" role="img" aria-label="old and new subsample score per proposal"><rect width="100%" height="100%" fill="#fff"/><line x1="58" y1="312.0" x2="1138" y2="312.0" class="grid"/><text x="48" y="316.0" text-anchor="end" class="tick">0.0</text><line x1="58" y1="240.0" x2="1138" y2="240.0" class="grid"/><text x="48" y="244.0" text-anchor="end" class="tick">1.0</text><line x1="58" y1="168.0" x2="1138" y2="168.0" class="grid"/><text x="48" y="172.0" text-anchor="end" class="tick">2.0</text><line x1="58" y1="96.0" x2="1138" y2="96.0" class="grid"/><text x="48" y="100.0" text-anchor="end" class="tick">3.0</text><line x1="58" y1="24.0" x2="1138" y2="24.0" class="grid"/><text x="48" y="28.0" text-anchor="end" class="tick">4.0</text><line x1="58" y1="312" x2="1138" y2="312" class="axis"/><line x1="58" y1="24" x2="58" y2="312" class="axis"/><rect x="63.4" y="178.6" width="10.5" height="133.4" rx="2" fill="#64748b"><title>proposal 1 old_sum: 1.8533</title></rect><rect x="75.8" y="64.8" width="10.5" height="247.2" rx="2" fill="#2563eb"><title>proposal 1 new_sum: 3.4333</title></rect><circle cx="74.9" cy="322" r="3" fill="#16a34a"><title>proposal 1: accepted</title></circle><text x="74.9" y="346" text-anchor="middle" class="tick">1</text><rect x="97.1" y="164.2" width="10.5" height="147.8" rx="2" fill="#64748b"><title>proposal 2 old_sum: 2.0533</title></rect><rect x="109.6" y="64.8" width="10.5" height="247.2" rx="2" fill="#2563eb"><title>proposal 2 new_sum: 3.4333</title></rect><circle cx="108.6" cy="322" r="3" fill="#16a34a"><title>proposal 2: accepted</title></circle><rect x="130.9" y="312.0" width="10.5" height="0.0" rx="2" fill="#64748b"><title>proposal 3 old_sum: 0.0000</title></rect><rect x="143.3" y="312.0" width="10.5" height="0.0" rx="2" fill="#2563eb"><title>proposal 3 new_sum: 0.0000</title></rect><circle cx="142.4" cy="322" r="3" fill="#dc2626"><title>proposal 3: rejected</title></circle><rect x="164.6" y="312.0" width="10.5" height="0.0" rx="2" fill="#64748b"><title>proposal 4 old_sum: 0.0000</title></rect><rect x="177.1" y="312.0" width="10.5" height="0.0" rx="2" fill="#2563eb"><title>proposal 4 new_sum: 0.0000</title></rect><circle cx="176.1" cy="322" r="3" fill="#dc2626"><title>proposal 4: rejected</title></circle><text x="176.1" y="346" text-anchor="middle" class="tick">4</text><rect x="198.4" y="312.0" width="10.5" height="0.0" rx="2" fill="#64748b"><title>proposal 5 old_sum: 0.0000</title></rect><rect x="210.8" y="312.0" width="10.5" height="0.0" rx="2" fill="#2563eb"><title>proposal 5 new_sum: 0.0000</title></rect><circle cx="209.9" cy="322" r="3" fill="#dc2626"><title>proposal 5: rejected</title></circle><rect x="232.1" y="312.0" width="10.5" height="0.0" rx="2" fill="#64748b"><title>proposal 6 old_sum: 0.0000</title></rect><rect x="244.6" y="312.0" width="10.5" height="0.0" rx="2" fill="#2563eb"><title>proposal 6 new_sum: 0.0000</title></rect><circle cx="243.6" cy="322" r="3" fill="#dc2626"><title>proposal 6: rejected</title></circle><rect x="265.9" y="312.0" width="10.5" height="0.0" rx="2" fill="#64748b"><title>proposal 7 old_sum: 0.0000</title></rect><rect x="278.3" y="312.0" width="10.5" height="0.0" rx="2" fill="#2563eb"><title>proposal 7 new_sum: 0.0000</title></rect><circle cx="277.4" cy="322" r="3" fill="#dc2626"><title>proposal 7: rejected</title></circle><rect x="299.6" y="312.0" width="10.5" height="0.0" rx="2" fill="#64748b"><title>proposal 8 old_sum: 0.0000</title></rect><rect x="312.1" y="312.0" width="10.5" height="0.0" rx="2" fill="#2563eb"><title>proposal 8 new_sum: 0.0000</title></rect><circle cx="311.1" cy="322" r="3" fill="#dc2626"><title>proposal 8: rejected</title></circle><text x="311.1" y="346" text-anchor="middle" class="tick">8</text><rect x="333.4" y="312.0" width="10.5" height="0.0" rx="2" fill="#64748b"><title>proposal 9 old_sum: 0.0000</title></rect><rect x="345.8" y="312.0" width="10.5" height="0.0" rx="2" fill="#2563eb"><title>proposal 9 new_sum: 0.0000</title></rect><circle cx="344.9" cy="322" r="3" fill="#dc2626"><title>proposal 9: rejected</title></circle><rect x="367.1" y="312.0" width="10.5" height="0.0" rx="2" fill="#64748b"><title>proposal 10 old_sum: 0.0000</title></rect><rect x="379.6" y="168.0" width="10.5" height="144.0" rx="2" fill="#2563eb"><title>proposal 10 new_sum: 2.0000</title></rect><circle cx="378.6" cy="322" r="3" fill="#16a34a"><title>proposal 10: accepted</title></circle><rect x="400.9" y="64.8" width="10.5" height="247.2" rx="2" fill="#64748b"><title>proposal 11 old_sum: 3.4333</title></rect><rect x="413.3" y="115.2" width="10.5" height="196.8" rx="2" fill="#2563eb"><title>proposal 11 new_sum: 2.7333</title></rect><circle cx="412.4" cy="322" r="3" fill="#dc2626"><title>proposal 11: rejected</title></circle><rect x="434.6" y="128.2" width="10.5" height="183.8" rx="2" fill="#64748b"><title>proposal 12 old_sum: 2.5533</title></rect><rect x="447.1" y="96.5" width="10.5" height="215.5" rx="2" fill="#2563eb"><title>proposal 12 new_sum: 2.9933</title></rect><circle cx="446.1" cy="322" r="3" fill="#16a34a"><title>proposal 12: accepted</title></circle><text x="446.1" y="346" text-anchor="middle" class="tick">12</text><rect x="468.4" y="96.5" width="10.5" height="215.5" rx="2" fill="#64748b"><title>proposal 13 old_sum: 2.9933</title></rect><rect x="480.8" y="87.4" width="10.5" height="224.6" rx="2" fill="#2563eb"><title>proposal 13 new_sum: 3.1200</title></rect><circle cx="479.9" cy="322" r="3" fill="#16a34a"><title>proposal 13: accepted</title></circle><rect x="502.1" y="74.4" width="10.5" height="237.6" rx="2" fill="#64748b"><title>proposal 14 old_sum: 3.3000</title></rect><rect x="514.6" y="24.0" width="10.5" height="288.0" rx="2" fill="#2563eb"><title>proposal 14 new_sum: 4.0000</title></rect><circle cx="513.6" cy="322" r="3" fill="#16a34a"><title>proposal 14: accepted</title></circle><rect x="535.9" y="64.8" width="10.5" height="247.2" rx="2" fill="#64748b"><title>proposal 15 old_sum: 3.4333</title></rect><rect x="548.3" y="64.8" width="10.5" height="247.2" rx="2" fill="#2563eb"><title>proposal 15 new_sum: 3.4333</title></rect><circle cx="547.4" cy="322" r="3" fill="#dc2626"><title>proposal 15: rejected</title></circle><rect x="569.6" y="55.7" width="10.5" height="256.3" rx="2" fill="#64748b"><title>proposal 16 old_sum: 3.5600</title></rect><rect x="582.1" y="127.7" width="10.5" height="184.3" rx="2" fill="#2563eb"><title>proposal 16 new_sum: 2.5600</title></rect><circle cx="581.1" cy="322" r="3" fill="#dc2626"><title>proposal 16: rejected</title></circle><text x="581.1" y="346" text-anchor="middle" class="tick">16</text><rect x="603.4" y="137.3" width="10.5" height="174.7" rx="2" fill="#64748b"><title>proposal 17 old_sum: 2.4267</title></rect><rect x="615.8" y="24.0" width="10.5" height="288.0" rx="2" fill="#2563eb"><title>proposal 17 new_sum: 4.0000</title></rect><circle cx="614.9" cy="322" r="3" fill="#16a34a"><title>proposal 17: accepted</title></circle><rect x="637.1" y="183.6" width="10.5" height="128.4" rx="2" fill="#64748b"><title>proposal 18 old_sum: 1.7833</title></rect><rect x="649.6" y="96.5" width="10.5" height="215.5" rx="2" fill="#2563eb"><title>proposal 18 new_sum: 2.9933</title></rect><circle cx="648.6" cy="322" r="3" fill="#16a34a"><title>proposal 18: accepted</title></circle><rect x="670.9" y="175.7" width="10.5" height="136.3" rx="2" fill="#64748b"><title>proposal 19 old_sum: 1.8933</title></rect><rect x="683.3" y="24.0" width="10.5" height="288.0" rx="2" fill="#2563eb"><title>proposal 19 new_sum: 4.0000</title></rect><circle cx="682.4" cy="322" r="3" fill="#16a34a"><title>proposal 19: accepted</title></circle><rect x="704.6" y="115.2" width="10.5" height="196.8" rx="2" fill="#64748b"><title>proposal 20 old_sum: 2.7333</title></rect><rect x="717.1" y="96.0" width="10.5" height="216.0" rx="2" fill="#2563eb"><title>proposal 20 new_sum: 3.0000</title></rect><circle cx="716.1" cy="322" r="3" fill="#16a34a"><title>proposal 20: accepted</title></circle><text x="716.1" y="346" text-anchor="middle" class="tick">20</text><rect x="738.4" y="206.4" width="10.5" height="105.6" rx="2" fill="#64748b"><title>proposal 21 old_sum: 1.4667</title></rect><rect x="750.8" y="24.0" width="10.5" height="288.0" rx="2" fill="#2563eb"><title>proposal 21 new_sum: 4.0000</title></rect><circle cx="749.9" cy="322" r="3" fill="#16a34a"><title>proposal 21: accepted</title></circle><rect x="772.1" y="200.2" width="10.5" height="111.8" rx="2" fill="#64748b"><title>proposal 22 old_sum: 1.5533</title></rect><rect x="784.6" y="24.0" width="10.5" height="288.0" rx="2" fill="#2563eb"><title>proposal 22 new_sum: 4.0000</title></rect><circle cx="783.6" cy="322" r="3" fill="#16a34a"><title>proposal 22: accepted</title></circle><rect x="805.9" y="128.2" width="10.5" height="183.8" rx="2" fill="#64748b"><title>proposal 23 old_sum: 2.5533</title></rect><rect x="818.3" y="24.0" width="10.5" height="288.0" rx="2" fill="#2563eb"><title>proposal 23 new_sum: 4.0000</title></rect><circle cx="817.4" cy="322" r="3" fill="#16a34a"><title>proposal 23: accepted</title></circle><rect x="839.6" y="137.3" width="10.5" height="174.7" rx="2" fill="#64748b"><title>proposal 24 old_sum: 2.4267</title></rect><rect x="852.1" y="24.0" width="10.5" height="288.0" rx="2" fill="#2563eb"><title>proposal 24 new_sum: 4.0000</title></rect><circle cx="851.1" cy="322" r="3" fill="#16a34a"><title>proposal 24: accepted</title></circle><text x="851.1" y="346" text-anchor="middle" class="tick">24</text><rect x="873.4" y="79.4" width="10.5" height="232.6" rx="2" fill="#64748b"><title>proposal 25 old_sum: 3.2300</title></rect><rect x="885.8" y="105.6" width="10.5" height="206.4" rx="2" fill="#2563eb"><title>proposal 25 new_sum: 2.8667</title></rect><circle cx="884.9" cy="322" r="3" fill="#dc2626"><title>proposal 25: rejected</title></circle><rect x="907.1" y="137.3" width="10.5" height="174.7" rx="2" fill="#64748b"><title>proposal 26 old_sum: 2.4267</title></rect><rect x="919.6" y="24.0" width="10.5" height="288.0" rx="2" fill="#2563eb"><title>proposal 26 new_sum: 4.0000</title></rect><circle cx="918.6" cy="322" r="3" fill="#16a34a"><title>proposal 26: accepted</title></circle><rect x="940.9" y="164.2" width="10.5" height="147.8" rx="2" fill="#64748b"><title>proposal 27 old_sum: 2.0533</title></rect><rect x="953.3" y="24.0" width="10.5" height="288.0" rx="2" fill="#2563eb"><title>proposal 27 new_sum: 4.0000</title></rect><circle cx="952.4" cy="322" r="3" fill="#16a34a"><title>proposal 27: accepted</title></circle><rect x="974.6" y="55.7" width="10.5" height="256.3" rx="2" fill="#64748b"><title>proposal 28 old_sum: 3.5600</title></rect><rect x="987.1" y="136.8" width="10.5" height="175.2" rx="2" fill="#2563eb"><title>proposal 28 new_sum: 2.4333</title></rect><circle cx="986.1" cy="322" r="3" fill="#dc2626"><title>proposal 28: rejected</title></circle><text x="986.1" y="346" text-anchor="middle" class="tick">28</text><rect x="1008.4" y="24.0" width="10.5" height="288.0" rx="2" fill="#64748b"><title>proposal 29 old_sum: 4.0000</title></rect><circle cx="1019.9" cy="322" r="3" fill="#94a3b8"><title>proposal 29: no proposal</title></circle><rect x="1042.1" y="87.4" width="10.5" height="224.6" rx="2" fill="#64748b"><title>proposal 30 old_sum: 3.1200</title></rect><rect x="1054.6" y="24.0" width="10.5" height="288.0" rx="2" fill="#2563eb"><title>proposal 30 new_sum: 4.0000</title></rect><circle cx="1053.6" cy="322" r="3" fill="#16a34a"><title>proposal 30: accepted</title></circle><rect x="1075.9" y="156.0" width="10.5" height="156.0" rx="2" fill="#64748b"><title>proposal 31 old_sum: 2.1667</title></rect><rect x="1088.3" y="24.0" width="10.5" height="288.0" rx="2" fill="#2563eb"><title>proposal 31 new_sum: 4.0000</title></rect><circle cx="1087.4" cy="322" r="3" fill="#16a34a"><title>proposal 31: accepted</title></circle><rect x="1109.6" y="178.1" width="10.5" height="133.9" rx="2" fill="#64748b"><title>proposal 32 old_sum: 1.8600</title></rect><rect x="1122.1" y="137.3" width="10.5" height="174.7" rx="2" fill="#2563eb"><title>proposal 32 new_sum: 2.4267</title></rect><circle cx="1121.1" cy="322" r="3" fill="#16a34a"><title>proposal 32: accepted</title></circle><text x="1121.1" y="346" text-anchor="middle" class="tick">32</text><text x="598.0" y="366" text-anchor="middle" class="axis-label">proposal number</text></svg><div class="legend"><span><i style="background:#64748b"></i>old subsample sum</span><span><i style="background:#2563eb"></i>new subsample sum</span><span><i style="background:#16a34a"></i>accepted</span><span><i style="background:#dc2626"></i>rejected</span><span><i style="background:#94a3b8"></i>no proposal</span></div></div></section>
|
| 15 |
+
<section><h2>Subsample Delta, Every Proposal</h2><div class="chart-wrap"><svg viewBox="0 0 1160 360" role="img" aria-label="proposal delta per proposal"><rect width="100%" height="100%" fill="#fff"/><line x1="58" y1="302.0" x2="1138" y2="302.0" class="grid"/><text x="48" y="306.0" text-anchor="end" class="tick">-1.13</text><line x1="58" y1="232.5" x2="1138" y2="232.5" class="grid"/><text x="48" y="236.5" text-anchor="end" class="tick">-0.21</text><line x1="58" y1="163.0" x2="1138" y2="163.0" class="grid"/><text x="48" y="167.0" text-anchor="end" class="tick">0.70</text><line x1="58" y1="93.5" x2="1138" y2="93.5" class="grid"/><text x="48" y="97.5" text-anchor="end" class="tick">1.62</text><line x1="58" y1="24.0" x2="1138" y2="24.0" class="grid"/><text x="48" y="28.0" text-anchor="end" class="tick">2.53</text><line x1="58" y1="216.4" x2="1138" y2="216.4" class="axis"/><line x1="58" y1="24" x2="58" y2="302" class="axis"/><rect x="65.9" y="96.4" width="18.0" height="120.0" rx="2" fill="#16a34a"><title>proposal 1: delta 1.5800; accepted</title></rect><text x="74.9" y="336" text-anchor="middle" class="tick">1</text><rect x="99.6" y="111.6" width="18.0" height="104.8" rx="2" fill="#16a34a"><title>proposal 2: delta 1.3800; accepted</title></rect><rect x="133.4" y="216.4" width="18.0" height="1.0" rx="2" fill="#f59e0b"><title>proposal 3: delta 0.0000; rejected</title></rect><rect x="167.1" y="216.4" width="18.0" height="1.0" rx="2" fill="#f59e0b"><title>proposal 4: delta 0.0000; rejected</title></rect><text x="176.1" y="336" text-anchor="middle" class="tick">4</text><rect x="200.9" y="216.4" width="18.0" height="1.0" rx="2" fill="#f59e0b"><title>proposal 5: delta 0.0000; rejected</title></rect><rect x="234.6" y="216.4" width="18.0" height="1.0" rx="2" fill="#f59e0b"><title>proposal 6: delta 0.0000; rejected</title></rect><rect x="268.4" y="216.4" width="18.0" height="1.0" rx="2" fill="#f59e0b"><title>proposal 7: delta 0.0000; rejected</title></rect><rect x="302.1" y="216.4" width="18.0" height="1.0" rx="2" fill="#f59e0b"><title>proposal 8: delta 0.0000; rejected</title></rect><text x="311.1" y="336" text-anchor="middle" class="tick">8</text><rect x="335.9" y="216.4" width="18.0" height="1.0" rx="2" fill="#f59e0b"><title>proposal 9: delta 0.0000; rejected</title></rect><rect x="369.6" y="64.5" width="18.0" height="151.9" rx="2" fill="#16a34a"><title>proposal 10: delta 2.0000; accepted</title></rect><rect x="403.4" y="216.4" width="18.0" height="53.2" rx="2" fill="#dc2626"><title>proposal 11: delta -0.7000; rejected</title></rect><rect x="437.1" y="183.0" width="18.0" height="33.4" rx="2" fill="#16a34a"><title>proposal 12: delta 0.4400; accepted</title></rect><text x="446.1" y="336" text-anchor="middle" class="tick">12</text><rect x="470.9" y="206.8" width="18.0" height="9.6" rx="2" fill="#16a34a"><title>proposal 13: delta 0.1267; accepted</title></rect><rect x="504.6" y="163.3" width="18.0" height="53.2" rx="2" fill="#16a34a"><title>proposal 14: delta 0.7000; accepted</title></rect><rect x="538.4" y="216.4" width="18.0" height="1.0" rx="2" fill="#f59e0b"><title>proposal 15: delta 0.0000; rejected</title></rect><rect x="572.1" y="216.4" width="18.0" height="76.0" rx="2" fill="#dc2626"><title>proposal 16: delta -1.0000; rejected</title></rect><text x="581.1" y="336" text-anchor="middle" class="tick">16</text><rect x="605.9" y="96.9" width="18.0" height="119.5" rx="2" fill="#16a34a"><title>proposal 17: delta 1.5733; accepted</title></rect><rect x="639.6" y="124.5" width="18.0" height="91.9" rx="2" fill="#16a34a"><title>proposal 18: delta 1.2100; accepted</title></rect><rect x="673.4" y="56.4" width="18.0" height="160.0" rx="2" fill="#16a34a"><title>proposal 19: delta 2.1067; accepted</title></rect><rect x="707.1" y="196.2" width="18.0" height="20.3" rx="2" fill="#16a34a"><title>proposal 20: delta 0.2667; accepted</title></rect><text x="716.1" y="336" text-anchor="middle" class="tick">20</text><rect x="740.9" y="24.0" width="18.0" height="192.4" rx="2" fill="#16a34a"><title>proposal 21: delta 2.5333; accepted</title></rect><rect x="774.6" y="30.6" width="18.0" height="185.8" rx="2" fill="#16a34a"><title>proposal 22: delta 2.4467; accepted</title></rect><rect x="808.4" y="106.5" width="18.0" height="109.9" rx="2" fill="#16a34a"><title>proposal 23: delta 1.4467; accepted</title></rect><rect x="842.1" y="96.9" width="18.0" height="119.5" rx="2" fill="#16a34a"><title>proposal 24: delta 1.5733; accepted</title></rect><text x="851.1" y="336" text-anchor="middle" class="tick">24</text><rect x="875.9" y="216.4" width="18.0" height="27.6" rx="2" fill="#dc2626"><title>proposal 25: delta -0.3633; rejected</title></rect><rect x="909.6" y="96.9" width="18.0" height="119.5" rx="2" fill="#16a34a"><title>proposal 26: delta 1.5733; accepted</title></rect><rect x="943.4" y="68.6" width="18.0" height="147.9" rx="2" fill="#16a34a"><title>proposal 27: delta 1.9467; accepted</title></rect><rect x="977.1" y="216.4" width="18.0" height="85.6" rx="2" fill="#dc2626"><title>proposal 28: delta -1.1267; rejected</title></rect><text x="986.1" y="336" text-anchor="middle" class="tick">28</text><circle cx="1019.9" cy="216.4" r="4" fill="#94a3b8"><title>proposal 29: no proposal generated</title></circle><rect x="1044.6" y="149.6" width="18.0" height="66.8" rx="2" fill="#16a34a"><title>proposal 30: delta 0.8800; accepted</title></rect><rect x="1078.4" y="77.2" width="18.0" height="139.3" rx="2" fill="#16a34a"><title>proposal 31: delta 1.8333; accepted</title></rect><rect x="1112.1" y="173.4" width="18.0" height="43.0" rx="2" fill="#16a34a"><title>proposal 32: delta 0.5667; accepted</title></rect><text x="1121.1" y="336" text-anchor="middle" class="tick">32</text><text x="598.0" y="356" text-anchor="middle" class="axis-label">proposal number</text></svg><div class="legend"><span><i style="background:#16a34a"></i>accepted for full eval</span><span><i style="background:#dc2626"></i>rejected</span><span><i style="background:#f59e0b"></i>zero-delta rejected</span><span><i style="background:#94a3b8"></i>no proposal</span></div></div></section>
|
| 16 |
+
<section><h2>Full Pareto Score for Accepted Proposals</h2><div class="chart-wrap"><svg viewBox="0 0 1040 340" role="img" aria-label="full score for accepted proposals"><rect width="100%" height="100%" fill="#fff"/><line x1="58" y1="290.0" x2="1016" y2="290.0" class="grid"/><text x="48" y="294.0" text-anchor="end" class="tick">0.000</text><line x1="58" y1="223.5" x2="1016" y2="223.5" class="grid"/><text x="48" y="227.5" text-anchor="end" class="tick">0.250</text><line x1="58" y1="157.0" x2="1016" y2="157.0" class="grid"/><text x="48" y="161.0" text-anchor="end" class="tick">0.500</text><line x1="58" y1="90.5" x2="1016" y2="90.5" class="grid"/><text x="48" y="94.5" text-anchor="end" class="tick">0.750</text><line x1="58" y1="24.0" x2="1016" y2="24.0" class="grid"/><text x="48" y="28.0" text-anchor="end" class="tick">1.000</text><line x1="58" y1="290" x2="1016" y2="290" class="axis"/><line x1="58" y1="24" x2="58" y2="290" class="axis"/><polyline points="58.0,140.3 88.9,187.8 336.1,130.9 397.9,126.1 428.8,118.2 459.7,127.0 552.5,135.9 583.4,114.9 614.3,122.9 645.2,123.3 676.1,124.0 707.0,128.6 737.9,127.3 768.8,123.9 830.6,122.7 861.5,104.3 954.2,132.4 985.1,128.5 1016.0,125.6" fill="none" stroke="#2563eb" stroke-width="3" stroke-linecap="round" stroke-linejoin="round"/><circle cx="58.0" cy="140.3" r="4" fill="#2563eb"><title>accepted proposal full score proposal 1: 0.5627</title></circle><circle cx="88.9" cy="187.8" r="4" fill="#2563eb"><title>accepted proposal full score proposal 2: 0.3842</title></circle><circle cx="336.1" cy="130.9" r="4" fill="#2563eb"><title>accepted proposal full score proposal 10: 0.5982</title></circle><circle cx="397.9" cy="126.1" r="4" fill="#2563eb"><title>accepted proposal full score proposal 12: 0.6161</title></circle><circle cx="428.8" cy="118.2" r="4" fill="#2563eb"><title>accepted proposal full score proposal 13: 0.6458</title></circle><circle cx="459.7" cy="127.0" r="4" fill="#2563eb"><title>accepted proposal full score proposal 14: 0.6127</title></circle><circle cx="552.5" cy="135.9" r="4" fill="#2563eb"><title>accepted proposal full score proposal 17: 0.5795</title></circle><circle cx="583.4" cy="114.9" r="4" fill="#2563eb"><title>accepted proposal full score proposal 18: 0.6582</title></circle><circle cx="614.3" cy="122.9" r="4" fill="#2563eb"><title>accepted proposal full score proposal 19: 0.6282</title></circle><circle cx="645.2" cy="123.3" r="4" fill="#2563eb"><title>accepted proposal full score proposal 20: 0.6267</title></circle><circle cx="676.1" cy="124.0" r="4" fill="#2563eb"><title>accepted proposal full score proposal 21: 0.6240</title></circle><circle cx="707.0" cy="128.6" r="4" fill="#2563eb"><title>accepted proposal full score proposal 22: 0.6069</title></circle><circle cx="737.9" cy="127.3" r="4" fill="#2563eb"><title>accepted proposal full score proposal 23: 0.6116</title></circle><circle cx="768.8" cy="123.9" r="4" fill="#2563eb"><title>accepted proposal full score proposal 24: 0.6246</title></circle><circle cx="830.6" cy="122.7" r="4" fill="#2563eb"><title>accepted proposal full score proposal 26: 0.6288</title></circle><circle cx="861.5" cy="104.3" r="4" fill="#2563eb"><title>accepted proposal full score proposal 27: 0.6979</title></circle><circle cx="954.2" cy="132.4" r="4" fill="#2563eb"><title>accepted proposal full score proposal 30: 0.5924</title></circle><circle cx="985.1" cy="128.5" r="4" fill="#2563eb"><title>accepted proposal full score proposal 31: 0.6071</title></circle><circle cx="1016.0" cy="125.6" r="4" fill="#2563eb"><title>accepted proposal full score proposal 32: 0.6180</title></circle><polyline points="58.0,137.3 88.9,137.3 119.8,137.3 150.7,137.3 181.6,137.3 212.5,137.3 243.4,137.3 274.3,137.3 305.2,137.3 336.1,130.9 367.0,130.9 397.9,126.1 428.8,118.2 459.7,118.2 490.6,118.2 521.5,118.2 552.5,118.2 583.4,114.9 614.3,114.9 645.2,114.9 676.1,114.9 707.0,114.9 737.9,114.9 768.8,114.9 799.7,114.9 830.6,114.9 861.5,104.3 892.4,104.3 923.3,104.3 954.2,104.3 985.1,104.3 1016.0,104.3" fill="none" stroke="#16a34a" stroke-width="3" stroke-linecap="round" stroke-linejoin="round"/><circle cx="58.0" cy="137.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 1: 0.5742</title></circle><circle cx="88.9" cy="137.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 2: 0.5742</title></circle><circle cx="119.8" cy="137.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 3: 0.5742</title></circle><circle cx="150.7" cy="137.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 4: 0.5742</title></circle><circle cx="181.6" cy="137.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 5: 0.5742</title></circle><circle cx="212.5" cy="137.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 6: 0.5742</title></circle><circle cx="243.4" cy="137.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 7: 0.5742</title></circle><circle cx="274.3" cy="137.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 8: 0.5742</title></circle><circle cx="305.2" cy="137.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 9: 0.5742</title></circle><circle cx="336.1" cy="130.9" r="4" fill="#16a34a"><title>best so far after proposal proposal 10: 0.5982</title></circle><circle cx="367.0" cy="130.9" r="4" fill="#16a34a"><title>best so far after proposal proposal 11: 0.5982</title></circle><circle cx="397.9" cy="126.1" r="4" fill="#16a34a"><title>best so far after proposal proposal 12: 0.6161</title></circle><circle cx="428.8" cy="118.2" r="4" fill="#16a34a"><title>best so far after proposal proposal 13: 0.6458</title></circle><circle cx="459.7" cy="118.2" r="4" fill="#16a34a"><title>best so far after proposal proposal 14: 0.6458</title></circle><circle cx="490.6" cy="118.2" r="4" fill="#16a34a"><title>best so far after proposal proposal 15: 0.6458</title></circle><circle cx="521.5" cy="118.2" r="4" fill="#16a34a"><title>best so far after proposal proposal 16: 0.6458</title></circle><circle cx="552.5" cy="118.2" r="4" fill="#16a34a"><title>best so far after proposal proposal 17: 0.6458</title></circle><circle cx="583.4" cy="114.9" r="4" fill="#16a34a"><title>best so far after proposal proposal 18: 0.6582</title></circle><circle cx="614.3" cy="114.9" r="4" fill="#16a34a"><title>best so far after proposal proposal 19: 0.6582</title></circle><circle cx="645.2" cy="114.9" r="4" fill="#16a34a"><title>best so far after proposal proposal 20: 0.6582</title></circle><circle cx="676.1" cy="114.9" r="4" fill="#16a34a"><title>best so far after proposal proposal 21: 0.6582</title></circle><circle cx="707.0" cy="114.9" r="4" fill="#16a34a"><title>best so far after proposal proposal 22: 0.6582</title></circle><circle cx="737.9" cy="114.9" r="4" fill="#16a34a"><title>best so far after proposal proposal 23: 0.6582</title></circle><circle cx="768.8" cy="114.9" r="4" fill="#16a34a"><title>best so far after proposal proposal 24: 0.6582</title></circle><circle cx="799.7" cy="114.9" r="4" fill="#16a34a"><title>best so far after proposal proposal 25: 0.6582</title></circle><circle cx="830.6" cy="114.9" r="4" fill="#16a34a"><title>best so far after proposal proposal 26: 0.6582</title></circle><circle cx="861.5" cy="104.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 27: 0.6979</title></circle><circle cx="892.4" cy="104.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 28: 0.6979</title></circle><circle cx="923.3" cy="104.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 29: 0.6979</title></circle><circle cx="954.2" cy="104.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 30: 0.6979</title></circle><circle cx="985.1" cy="104.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 31: 0.6979</title></circle><circle cx="1016.0" cy="104.3" r="4" fill="#16a34a"><title>best so far after proposal proposal 32: 0.6979</title></circle><text x="58.0" y="318" text-anchor="middle" class="tick">1</text><text x="150.7" y="318" text-anchor="middle" class="tick">4</text><text x="274.3" y="318" text-anchor="middle" class="tick">8</text><text x="397.9" y="318" text-anchor="middle" class="tick">12</text><text x="521.5" y="318" text-anchor="middle" class="tick">16</text><text x="645.2" y="318" text-anchor="middle" class="tick">20</text><text x="768.8" y="318" text-anchor="middle" class="tick">24</text><text x="892.4" y="318" text-anchor="middle" class="tick">28</text><text x="1016.0" y="318" text-anchor="middle" class="tick">32</text><text x="537.0" y="336" text-anchor="middle" class="axis-label">proposal number</text></svg><div class="legend"><span><i style="background:#2563eb"></i>accepted proposal full score</span><span><i style="background:#16a34a"></i>best so far after proposal</span></div></div></section>
|
| 17 |
+
<section><h2>Old and New Subsample Sum Lines</h2><div class="chart-wrap"><svg viewBox="0 0 1040 340" role="img" aria-label="old and new subsample sums"><rect width="100%" height="100%" fill="#fff"/><line x1="58" y1="290.0" x2="1016" y2="290.0" class="grid"/><text x="48" y="294.0" text-anchor="end" class="tick">0.000</text><line x1="58" y1="223.5" x2="1016" y2="223.5" class="grid"/><text x="48" y="227.5" text-anchor="end" class="tick">1.000</text><line x1="58" y1="157.0" x2="1016" y2="157.0" class="grid"/><text x="48" y="161.0" text-anchor="end" class="tick">2.000</text><line x1="58" y1="90.5" x2="1016" y2="90.5" class="grid"/><text x="48" y="94.5" text-anchor="end" class="tick">3.000</text><line x1="58" y1="24.0" x2="1016" y2="24.0" class="grid"/><text x="48" y="28.0" text-anchor="end" class="tick">4.000</text><line x1="58" y1="290" x2="1016" y2="290" class="axis"/><line x1="58" y1="24" x2="58" y2="290" class="axis"/><polyline points="58.0,166.8 88.9,153.5 119.8,290.0 150.7,290.0 181.6,290.0 212.5,290.0 243.4,290.0 274.3,290.0 305.2,290.0 336.1,290.0 367.0,61.7 397.9,120.2 428.8,90.9 459.7,70.6 490.6,61.7 521.5,53.3 552.5,128.6 583.4,171.4 614.3,164.1 645.2,108.2 676.1,192.5 707.0,186.7 737.9,120.2 768.8,128.6 799.7,75.2 830.6,128.6 861.5,153.5 892.4,53.3 923.3,24.0 954.2,82.5 985.1,145.9 1016.0,166.3" fill="none" stroke="#64748b" stroke-width="3" stroke-linecap="round" stroke-linejoin="round"/><circle cx="58.0" cy="166.8" r="4" fill="#64748b"><title>old subsample sum proposal 1: 1.8533</title></circle><circle cx="88.9" cy="153.5" r="4" fill="#64748b"><title>old subsample sum proposal 2: 2.0533</title></circle><circle cx="119.8" cy="290.0" r="4" fill="#64748b"><title>old subsample sum proposal 3: 0.0000</title></circle><circle cx="150.7" cy="290.0" r="4" fill="#64748b"><title>old subsample sum proposal 4: 0.0000</title></circle><circle cx="181.6" cy="290.0" r="4" fill="#64748b"><title>old subsample sum proposal 5: 0.0000</title></circle><circle cx="212.5" cy="290.0" r="4" fill="#64748b"><title>old subsample sum proposal 6: 0.0000</title></circle><circle cx="243.4" cy="290.0" r="4" fill="#64748b"><title>old subsample sum proposal 7: 0.0000</title></circle><circle cx="274.3" cy="290.0" r="4" fill="#64748b"><title>old subsample sum proposal 8: 0.0000</title></circle><circle cx="305.2" cy="290.0" r="4" fill="#64748b"><title>old subsample sum proposal 9: 0.0000</title></circle><circle cx="336.1" cy="290.0" r="4" fill="#64748b"><title>old subsample sum proposal 10: 0.0000</title></circle><circle cx="367.0" cy="61.7" r="4" fill="#64748b"><title>old subsample sum proposal 11: 3.4333</title></circle><circle cx="397.9" cy="120.2" r="4" fill="#64748b"><title>old subsample sum proposal 12: 2.5533</title></circle><circle cx="428.8" cy="90.9" r="4" fill="#64748b"><title>old subsample sum proposal 13: 2.9933</title></circle><circle cx="459.7" cy="70.6" r="4" fill="#64748b"><title>old subsample sum proposal 14: 3.3000</title></circle><circle cx="490.6" cy="61.7" r="4" fill="#64748b"><title>old subsample sum proposal 15: 3.4333</title></circle><circle cx="521.5" cy="53.3" r="4" fill="#64748b"><title>old subsample sum proposal 16: 3.5600</title></circle><circle cx="552.5" cy="128.6" r="4" fill="#64748b"><title>old subsample sum proposal 17: 2.4267</title></circle><circle cx="583.4" cy="171.4" r="4" fill="#64748b"><title>old subsample sum proposal 18: 1.7833</title></circle><circle cx="614.3" cy="164.1" r="4" fill="#64748b"><title>old subsample sum proposal 19: 1.8933</title></circle><circle cx="645.2" cy="108.2" r="4" fill="#64748b"><title>old subsample sum proposal 20: 2.7333</title></circle><circle cx="676.1" cy="192.5" r="4" fill="#64748b"><title>old subsample sum proposal 21: 1.4667</title></circle><circle cx="707.0" cy="186.7" r="4" fill="#64748b"><title>old subsample sum proposal 22: 1.5533</title></circle><circle cx="737.9" cy="120.2" r="4" fill="#64748b"><title>old subsample sum proposal 23: 2.5533</title></circle><circle cx="768.8" cy="128.6" r="4" fill="#64748b"><title>old subsample sum proposal 24: 2.4267</title></circle><circle cx="799.7" cy="75.2" r="4" fill="#64748b"><title>old subsample sum proposal 25: 3.2300</title></circle><circle cx="830.6" cy="128.6" r="4" fill="#64748b"><title>old subsample sum proposal 26: 2.4267</title></circle><circle cx="861.5" cy="153.5" r="4" fill="#64748b"><title>old subsample sum proposal 27: 2.0533</title></circle><circle cx="892.4" cy="53.3" r="4" fill="#64748b"><title>old subsample sum proposal 28: 3.5600</title></circle><circle cx="923.3" cy="24.0" r="4" fill="#64748b"><title>old subsample sum proposal 29: 4.0000</title></circle><circle cx="954.2" cy="82.5" r="4" fill="#64748b"><title>old subsample sum proposal 30: 3.1200</title></circle><circle cx="985.1" cy="145.9" r="4" fill="#64748b"><title>old subsample sum proposal 31: 2.1667</title></circle><circle cx="1016.0" cy="166.3" r="4" fill="#64748b"><title>old subsample sum proposal 32: 1.8600</title></circle><polyline points="58.0,61.7 88.9,61.7 119.8,290.0 150.7,290.0 181.6,290.0 212.5,290.0 243.4,290.0 274.3,290.0 305.2,290.0 336.1,157.0 367.0,108.2 397.9,90.9 428.8,82.5 459.7,24.0 490.6,61.7 521.5,119.8 552.5,24.0 583.4,90.9 614.3,24.0 645.2,90.5 676.1,24.0 707.0,24.0 737.9,24.0 768.8,24.0 799.7,99.4 830.6,24.0 861.5,24.0 892.4,128.2 954.2,24.0 985.1,24.0 1016.0,128.6" fill="none" stroke="#2563eb" stroke-width="3" stroke-linecap="round" stroke-linejoin="round"/><circle cx="58.0" cy="61.7" r="4" fill="#2563eb"><title>new subsample sum proposal 1: 3.4333</title></circle><circle cx="88.9" cy="61.7" r="4" fill="#2563eb"><title>new subsample sum proposal 2: 3.4333</title></circle><circle cx="119.8" cy="290.0" r="4" fill="#2563eb"><title>new subsample sum proposal 3: 0.0000</title></circle><circle cx="150.7" cy="290.0" r="4" fill="#2563eb"><title>new subsample sum proposal 4: 0.0000</title></circle><circle cx="181.6" cy="290.0" r="4" fill="#2563eb"><title>new subsample sum proposal 5: 0.0000</title></circle><circle cx="212.5" cy="290.0" r="4" fill="#2563eb"><title>new subsample sum proposal 6: 0.0000</title></circle><circle cx="243.4" cy="290.0" r="4" fill="#2563eb"><title>new subsample sum proposal 7: 0.0000</title></circle><circle cx="274.3" cy="290.0" r="4" fill="#2563eb"><title>new subsample sum proposal 8: 0.0000</title></circle><circle cx="305.2" cy="290.0" r="4" fill="#2563eb"><title>new subsample sum proposal 9: 0.0000</title></circle><circle cx="336.1" cy="157.0" r="4" fill="#2563eb"><title>new subsample sum proposal 10: 2.0000</title></circle><circle cx="367.0" cy="108.2" r="4" fill="#2563eb"><title>new subsample sum proposal 11: 2.7333</title></circle><circle cx="397.9" cy="90.9" r="4" fill="#2563eb"><title>new subsample sum proposal 12: 2.9933</title></circle><circle cx="428.8" cy="82.5" r="4" fill="#2563eb"><title>new subsample sum proposal 13: 3.1200</title></circle><circle cx="459.7" cy="24.0" r="4" fill="#2563eb"><title>new subsample sum proposal 14: 4.0000</title></circle><circle cx="490.6" cy="61.7" r="4" fill="#2563eb"><title>new subsample sum proposal 15: 3.4333</title></circle><circle cx="521.5" cy="119.8" r="4" fill="#2563eb"><title>new subsample sum proposal 16: 2.5600</title></circle><circle cx="552.5" cy="24.0" r="4" fill="#2563eb"><title>new subsample sum proposal 17: 4.0000</title></circle><circle cx="583.4" cy="90.9" r="4" fill="#2563eb"><title>new subsample sum proposal 18: 2.9933</title></circle><circle cx="614.3" cy="24.0" r="4" fill="#2563eb"><title>new subsample sum proposal 19: 4.0000</title></circle><circle cx="645.2" cy="90.5" r="4" fill="#2563eb"><title>new subsample sum proposal 20: 3.0000</title></circle><circle cx="676.1" cy="24.0" r="4" fill="#2563eb"><title>new subsample sum proposal 21: 4.0000</title></circle><circle cx="707.0" cy="24.0" r="4" fill="#2563eb"><title>new subsample sum proposal 22: 4.0000</title></circle><circle cx="737.9" cy="24.0" r="4" fill="#2563eb"><title>new subsample sum proposal 23: 4.0000</title></circle><circle cx="768.8" cy="24.0" r="4" fill="#2563eb"><title>new subsample sum proposal 24: 4.0000</title></circle><circle cx="799.7" cy="99.4" r="4" fill="#2563eb"><title>new subsample sum proposal 25: 2.8667</title></circle><circle cx="830.6" cy="24.0" r="4" fill="#2563eb"><title>new subsample sum proposal 26: 4.0000</title></circle><circle cx="861.5" cy="24.0" r="4" fill="#2563eb"><title>new subsample sum proposal 27: 4.0000</title></circle><circle cx="892.4" cy="128.2" r="4" fill="#2563eb"><title>new subsample sum proposal 28: 2.4333</title></circle><circle cx="954.2" cy="24.0" r="4" fill="#2563eb"><title>new subsample sum proposal 30: 4.0000</title></circle><circle cx="985.1" cy="24.0" r="4" fill="#2563eb"><title>new subsample sum proposal 31: 4.0000</title></circle><circle cx="1016.0" cy="128.6" r="4" fill="#2563eb"><title>new subsample sum proposal 32: 2.4267</title></circle><text x="58.0" y="318" text-anchor="middle" class="tick">1</text><text x="150.7" y="318" text-anchor="middle" class="tick">4</text><text x="274.3" y="318" text-anchor="middle" class="tick">8</text><text x="397.9" y="318" text-anchor="middle" class="tick">12</text><text x="521.5" y="318" text-anchor="middle" class="tick">16</text><text x="645.2" y="318" text-anchor="middle" class="tick">20</text><text x="768.8" y="318" text-anchor="middle" class="tick">24</text><text x="892.4" y="318" text-anchor="middle" class="tick">28</text><text x="1016.0" y="318" text-anchor="middle" class="tick">32</text><text x="537.0" y="336" text-anchor="middle" class="axis-label">proposal number</text></svg><div class="legend"><span><i style="background:#64748b"></i>old subsample sum</span><span><i style="background:#2563eb"></i>new subsample sum</span></div></div></section>
|
| 18 |
+
<section><h2>Proposal Details</h2><div class="scroll"><table><thead><tr><th>Proposal</th><th>Status</th><th>Parent</th><th>Candidate</th><th>Old sum</th><th>New sum</th><th>Delta</th><th>Full score</th><th>Rows</th><th>Old row scores</th><th>New row scores</th></tr></thead><tbody><tr class="accepted"><td>1</td><td>accepted</td><td>0</td><td>1</td><td>1.8533</td><td>3.4333</td><td>1.5800</td><td>0.5627</td><td>99, 54, 3, 34</td><td>0.560, 0.300, 0.560, 0.433</td><td>1.000, 1.000, 0.433, 1.000</td></tr><tr class="accepted"><td>2</td><td>accepted</td><td>1</td><td>2</td><td>2.0533</td><td>3.4333</td><td>1.3800</td><td>0.3842</td><td>211, 103, 283, 276</td><td>0.433, 0.433, 1.000, 0.187</td><td>1.000, 1.000, 0.433, 1.000</td></tr><tr class="rejected"><td>3</td><td>rejected</td><td>1</td><td></td><td>0.0000</td><td>0.0000</td><td>0.0000</td><td>n/a</td><td>57, 88, 101, 149</td><td>0.000, 0.000, 0.000, 0.000</td><td>0.000, 0.000, 0.000, 0.000</td></tr><tr class="rejected"><td>4</td><td>rejected</td><td>2</td><td></td><td>0.0000</td><td>0.0000</td><td>0.0000</td><td>n/a</td><td>178, 292, 240, 157</td><td>0.000, 0.000, 0.000, 0.000</td><td>0.000, 0.000, 0.000, 0.000</td></tr><tr class="rejected"><td>5</td><td>rejected</td><td>0</td><td></td><td>0.0000</td><td>0.0000</td><td>0.0000</td><td>n/a</td><td>151, 13, 188, 219</td><td>0.000, 0.000, 0.000, 0.000</td><td>0.000, 0.000, 0.000, 0.000</td></tr><tr class="rejected"><td>6</td><td>rejected</td><td>0</td><td></td><td>0.0000</td><td>0.0000</td><td>0.0000</td><td>n/a</td><td>142, 80, 143, 127</td><td>0.000, 0.000, 0.000, 0.000</td><td>0.000, 0.000, 0.000, 0.000</td></tr><tr class="rejected"><td>7</td><td>rejected</td><td>1</td><td></td><td>0.0000</td><td>0.0000</td><td>0.0000</td><td>n/a</td><td>112, 46, 79, 184</td><td>0.000, 0.000, 0.000, 0.000</td><td>0.000, 0.000, 0.000, 0.000</td></tr><tr class="rejected"><td>8</td><td>rejected</td><td>2</td><td></td><td>0.0000</td><td>0.0000</td><td>0.0000</td><td>n/a</td><td>116, 299, 294, 78</td><td>0.000, 0.000, 0.000, 0.000</td><td>0.000, 0.000, 0.000, 0.000</td></tr><tr class="rejected"><td>9</td><td>rejected</td><td>2</td><td></td><td>0.0000</td><td>0.0000</td><td>0.0000</td><td>n/a</td><td>63, 137, 167, 68</td><td>0.000, 0.000, 0.000, 0.000</td><td>0.000, 0.000, 0.000, 0.000</td></tr><tr class="accepted"><td>10</td><td>accepted</td><td>0</td><td>3</td><td>0.0000</td><td>2.0000</td><td>2.0000</td><td>0.5982</td><td>275, 286, 216, 293</td><td>0.000, 0.000, 0.000, 0.000</td><td>0.000, 0.000, 1.000, 1.000</td></tr><tr class="rejected"><td>11</td><td>rejected</td><td>1</td><td></td><td>3.4333</td><td>2.7333</td><td>-0.7000</td><td>n/a</td><td>290, 2, 110, 131</td><td>1.000, 1.000, 1.000, 0.433</td><td>0.433, 1.000, 0.300, 1.000</td></tr><tr class="accepted"><td>12</td><td>accepted</td><td>1</td><td>4</td><td>2.5533</td><td>2.9933</td><td>0.4400</td><td>0.6161</td><td>271, 92, 209, 28</td><td>1.000, 0.433, 0.560, 0.560</td><td>0.560, 0.433, 1.000, 1.000</td></tr><tr class="accepted"><td>13</td><td>accepted</td><td>0</td><td>5</td><td>2.9933</td><td>3.1200</td><td>0.1267</td><td>0.6458</td><td>40, 14, 163, 281</td><td>1.000, 0.560, 0.433, 1.000</td><td>0.560, 0.560, 1.000, 1.000</td></tr><tr class="accepted"><td>14</td><td>accepted</td><td>1</td><td>6</td><td>3.3000</td><td>4.0000</td><td>0.7000</td><td>0.6127</td><td>191, 182, 118, 201</td><td>0.300, 1.000, 1.000, 1.000</td><td>1.000, 1.000, 1.000, 1.000</td></tr><tr class="rejected"><td>15</td><td>rejected</td><td>6</td><td></td><td>3.4333</td><td>3.4333</td><td>0.0000</td><td>n/a</td><td>262, 225, 41, 153</td><td>1.000, 1.000, 1.000, 0.433</td><td>0.433, 1.000, 1.000, 1.000</td></tr><tr class="rejected"><td>16</td><td>rejected</td><td>2</td><td></td><td>3.5600</td><td>2.5600</td><td>-1.0000</td><td>n/a</td><td>105, 249, 24, 84</td><td>1.000, 0.560, 1.000, 1.000</td><td>0.560, 0.000, 1.000, 1.000</td></tr><tr class="accepted"><td>17</td><td>accepted</td><td>3</td><td>7</td><td>2.4267</td><td>4.0000</td><td>1.5733</td><td>0.5795</td><td>16, 256, 251, 82</td><td>0.433, 1.000, 0.433, 0.560</td><td>1.000, 1.000, 1.000, 1.000</td></tr><tr class="accepted"><td>18</td><td>accepted</td><td>5</td><td>8</td><td>1.7833</td><td>2.9933</td><td>1.2100</td><td>0.6582</td><td>217, 185, 243, 35</td><td>0.433, 0.230, 0.560, 0.560</td><td>1.000, 0.433, 0.560, 1.000</td></tr><tr class="accepted"><td>19</td><td>accepted</td><td>8</td><td>9</td><td>1.8933</td><td>4.0000</td><td>2.1067</td><td>0.6282</td><td>288, 120, 42, 10</td><td>1.000, 0.230, 0.433, 0.230</td><td>1.000, 1.000, 1.000, 1.000</td></tr><tr class="accepted"><td>20</td><td>accepted</td><td>8</td><td>10</td><td>2.7333</td><td>3.0000</td><td>0.2667</td><td>0.6267</td><td>58, 90, 285, 19</td><td>0.300, 1.000, 1.000, 0.433</td><td>1.000, 1.000, 1.000, 0.000</td></tr><tr class="accepted"><td>21</td><td>accepted</td><td>6</td><td>11</td><td>1.4667</td><td>4.0000</td><td>2.5333</td><td>0.6240</td><td>96, 227, 270, 176</td><td>0.433, 0.300, 0.300, 0.433</td><td>1.000, 1.000, 1.000, 1.000</td></tr><tr class="accepted"><td>22</td><td>accepted</td><td>0</td><td>12</td><td>1.5533</td><td>4.0000</td><td>2.4467</td><td>0.6069</td><td>39, 65, 160, 230</td><td>0.433, 0.000, 0.560, 0.560</td><td>1.000, 1.000, 1.000, 1.000</td></tr><tr class="accepted"><td>23</td><td>accepted</td><td>5</td><td>13</td><td>2.5533</td><td>4.0000</td><td>1.4467</td><td>0.6116</td><td>87, 289, 1, 250</td><td>1.000, 0.433, 0.560, 0.560</td><td>1.000, 1.000, 1.000, 1.000</td></tr><tr class="accepted"><td>24</td><td>accepted</td><td>10</td><td>14</td><td>2.4267</td><td>4.0000</td><td>1.5733</td><td>0.6246</td><td>171, 129, 119, 135</td><td>0.433, 1.000, 0.560, 0.433</td><td>1.000, 1.000, 1.000, 1.000</td></tr><tr class="rejected"><td>25</td><td>rejected</td><td>14</td><td></td><td>3.2300</td><td>2.8667</td><td>-0.3633</td><td>n/a</td><td>257, 67, 162, 102</td><td>1.000, 0.230, 1.000, 1.000</td><td>0.433, 1.000, 0.433, 1.000</td></tr><tr class="accepted"><td>26</td><td>accepted</td><td>14</td><td>15</td><td>2.4267</td><td>4.0000</td><td>1.5733</td><td>0.6288</td><td>199, 106, 228, 123</td><td>0.433, 0.560, 0.433, 1.000</td><td>1.000, 1.000, 1.000, 1.000</td></tr><tr class="accepted"><td>27</td><td>accepted best</td><td>15</td><td>16</td><td>2.0533</td><td>4.0000</td><td>1.9467</td><td>0.6979</td><td>220, 26, 86, 117</td><td>0.433, 0.187, 0.433, 1.000</td><td>1.000, 1.000, 1.000, 1.000</td></tr><tr class="rejected"><td>28</td><td>rejected</td><td>15</td><td></td><td>3.5600</td><td>2.4333</td><td>-1.1267</td><td>n/a</td><td>177, 72, 186, 190</td><td>1.000, 1.000, 1.000, 0.560</td><td>0.433, 1.000, 0.000, 1.000</td></tr><tr class="noop"><td>29</td><td>no proposal</td><td>15</td><td></td><td>4.0000</td><td>n/a</td><td>n/a</td><td>n/a</td><td>93, 45, 202, 296</td><td>1.000, 1.000, 1.000, 1.000</td><td>n/a</td></tr><tr class="accepted"><td>30</td><td>accepted</td><td>16</td><td>17</td><td>3.1200</td><td>4.0000</td><td>0.8800</td><td>0.5924</td><td>279, 89, 12, 76</td><td>1.000, 0.560, 1.000, 0.560</td><td>1.000, 1.000, 1.000, 1.000</td></tr><tr class="accepted"><td>31</td><td>accepted</td><td>6</td><td>18</td><td>2.1667</td><td>4.0000</td><td>1.8333</td><td>0.6071</td><td>203, 59, 64, 265</td><td>0.433, 0.300, 1.000, 0.433</td><td>1.000, 1.000, 1.000, 1.000</td></tr><tr class="accepted"><td>32</td><td>accepted</td><td>6</td><td>19</td><td>1.8600</td><td>2.4267</td><td>0.5667</td><td>0.6180</td><td>145, 189, 44, 239</td><td>0.300, 1.000, 0.560, 0.000</td><td>0.433, 0.433, 1.000, 0.560</td></tr></tbody></table></div></section>
|
| 19 |
+
</main></body></html>
|
index.html
CHANGED
|
@@ -47,6 +47,7 @@ code { font-family:ui-monospace,SFMono-Regular,Consolas,monospace; font-size:12p
|
|
| 47 |
<h2>Latest Links</h2>
|
| 48 |
<p>
|
| 49 |
<a class="button" href="gepa-evalstate-qwen-overlay-c4-full-20260616T172947Z/final-report.html">Final report</a>
|
|
|
|
| 50 |
<a class="button" href="gepa-evalstate-qwen-overlay-c4-full-20260616T172947Z/score_report.html">Score graph</a>
|
| 51 |
<a class="button" href="gepa-evalstate-qwen-overlay-c4-full-20260616T172947Z/prompt-diffs/index.html">Prompt diffs</a>
|
| 52 |
<a class="button" href="gepa-evalstate-qwen-overlay-c4-full-20260616T172947Z/candidate_tree.html">Candidate tree</a>
|
|
|
|
| 47 |
<h2>Latest Links</h2>
|
| 48 |
<p>
|
| 49 |
<a class="button" href="gepa-evalstate-qwen-overlay-c4-full-20260616T172947Z/final-report.html">Final report</a>
|
| 50 |
+
<a class="button" href="gepa-evalstate-qwen-overlay-c4-full-20260616T172947Z/proposal-graphs.html">Proposal graphs</a>
|
| 51 |
<a class="button" href="gepa-evalstate-qwen-overlay-c4-full-20260616T172947Z/score_report.html">Score graph</a>
|
| 52 |
<a class="button" href="gepa-evalstate-qwen-overlay-c4-full-20260616T172947Z/prompt-diffs/index.html">Prompt diffs</a>
|
| 53 |
<a class="button" href="gepa-evalstate-qwen-overlay-c4-full-20260616T172947Z/candidate_tree.html">Candidate tree</a>
|