Spaces:
Running
Running
Use simple text disclosures without decorative plus/minus icons
Browse files- index.html +1 -1
index.html
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
<title>AutoRSE Leaderboard</title>
|
| 8 |
<meta name="description" content="Compare LLM agents as recommendation engineers on the AutoRSE benchmark. Explore paper reference results and contribute reproducible community evaluations.">
|
| 9 |
<style>
|
| 10 |
-
:root{--ink:#17243d;--blue:#2759c4;--muted:#52647c;--line:#dfe6ef;--soft:#f3f6fc;--green:#16786e;--red:#b64e45;font-family:Inter,-apple-system,BlinkMacSystemFont,"Segoe UI",Arial,sans-serif;color:var(--ink);background:#fff;font-synthesis:none}*{box-sizing:border-box}body{margin:0;font-size:16px;line-height:1.65;-webkit-font-smoothing:antialiased}a{color:var(--blue);text-decoration:none}a:hover{text-decoration:underline}button,select{font:inherit}a:focus-visible,button:focus-visible,select:focus-visible,summary:focus-visible{outline:3px solid #4d85e7;outline-offset:4px}button{cursor:pointer}h1,h2,h3,p{margin:0}h1,h2,h3{line-height:1.2;letter-spacing:-.035em}h1{font-size:clamp(32px,4vw,44px);font-weight:750}h2{font-size:27px;font-weight:700}main{max-width:1080px;margin:auto;padding:42px 32px 32px}.brand{display:flex;align-items:center;gap:10px;color:var(--blue);font-weight:750;font-size:18px;letter-spacing:-.03em;margin-bottom:21px}.brand svg{width:30px;height:30px}.intro{font-size:18px;color:var(--muted);max-width:760px;margin-top:16px}.links{display:flex;gap:10px;flex-wrap:wrap;margin:25px 0 34px}.links a{display:inline-flex;align-items:center;gap:10px;border:1px solid var(--line);border-radius:7px;min-height:44px;padding:8px 16px;font-size:16px;font-weight:600}.links .primary{color:white;background:var(--blue);border-color:var(--blue)}.links a:hover{text-decoration:none;background:#edf3fe;color:var(--blue)}.board{border:1px solid #d8e2ef;border-radius:16px;background:white;overflow:hidden}.filters{display:grid;grid-template-columns:repeat(3,minmax(0,1fr));gap:22px;padding:24px;background:#f8faff;border-bottom:1px solid var(--line)}.filters label{display:flex;flex-direction:column;gap:8px;font-weight:600;color:#3b5274;font-size:16px}select{width:100%;min-height:46px;padding:9px 35px 9px 12px;border:1px solid #ccd9eb;border-radius:7px;color:var(--ink);background:#fff;font-size:16px}.board-heading{display:flex;justify-content:space-between;align-items:baseline;gap:20px;padding:23px 24px 20px}.board-heading h2{font-size:22px}.board-heading p{font-size:16px;color:var(--muted)}.metric-note{font-size:16px;color:var(--muted);padding:0 24px 21px}.table-scroll{overflow-x:auto}.leaderboard{border-collapse:collapse;width:100%;font-variant-numeric:tabular-nums;table-layout:fixed}.leaderboard col.rank-col{width:80px}.leaderboard col.result-col{width:310px}.leaderboard thead th{padding:14px 24px;border-top:1px solid var(--line);border-bottom:1px solid var(--line);background:#f8faff;color:#415776;font-size:16px;font-weight:600;text-align:left}.leaderboard thead th:last-child{text-align:right}.leaderboard tbody td{border-bottom:1px solid #e8edf5;padding:19px 24px;vertical-align:middle}.leaderboard tbody tr:last-child td{border:0}.leaderboard tbody tr:hover{background:#f8fbff}.leaderboard tbody tr.leader-row{background:#f2f6ff}.rank{display:grid;place-items:center;width:32px;height:32px;border-radius:8px;font-size:17px;font-weight:650;color:#5a6d86;background:#f0f3f8}.rank.top{background:#e0eaff;color:#2759c4}.leaderboard tbody tr.leader-row .rank{background:var(--blue);color:#fff}.agent-name{font-size:18px;font-weight:650;line-height:1.4;overflow-wrap:anywhere}.agent-harness{font-size:16px;color:var(--muted);display:block;margin-top:4px}.result{text-align:right}.gain{display:block;font-size:23px;font-weight:700;line-height:1.3;letter-spacing:-.025em}.mean-rank{color:var(--blue)}.positive{color:var(--green)}.negative{color:var(--red)}.raw-score{display:block;font-size:16px;line-height:1.55;color:var(--muted);margin-top:7px}.table-note{font-size:16px;color:var(--muted);padding:20px 24px;border-top:1px solid var(--line);background:#fbfcff}.rank-breakdown{margin:0;padding:0 24px;border-top:1px solid var(--line)}.rank-breakdown>summary{padding:19px 0}.rank-table-scroll{overflow-x:auto;padding-bottom:20px}.rank-table{width:100%;min-width:810px;border-collapse:collapse;font-variant-numeric:tabular-nums;font-size:16px;text-align:center}.rank-table th,.rank-table td{padding:12px 10px;border-bottom:1px solid var(--line)}.rank-table thead th{font-weight:600;color:#415776;background:#f8faff}.rank-table th:first-child,.rank-table td:first-child{text-align:left;min-width:190px}.rank-table th:last-child,.rank-table td:last-child{font-weight:650;color:var(--blue)}.rank-table .agent-name{font-size:16px}.empty{font-size:18px;text-align:center;color:var(--muted);padding:32px!important}.data-links{display:flex;gap:22px;flex-wrap:wrap;font-size:16px;font-weight:550;margin:23px 0 28px}.contribute{border-top:1px solid var(--line);padding-top:30px;margin-top:28px}.contribute>p{color:var(--muted);font-size:18px;max-width:760px;margin-top:13px}.contribute .steps{display:grid;grid-template-columns:repeat(3,1fr);gap:24px;margin-top:24px}.step{padding:0 8px 0 17px;border-left:3px solid #d2e0fa}.step strong{font-size:18px;display:block}.step p{font-size:16px;color:var(--muted);margin-top:8px}.submission-links{display:flex;gap:22px;flex-wrap:wrap;margin-top:24px;font-size:16px;font-weight:600}details{border-top:1px solid var(--line);margin-top:30px}summary{cursor:pointer;list-style:none;font-size:16px;font-weight:600;padding:20px 0;display:flex;align-items:center;justify-content:space-between}summary::-webkit-details-marker{display:none}summary:
|
| 11 |
@media(max-width:600px){main{padding:28px 18px 24px}.brand{margin-bottom:16px}h1{font-size:32px}.intro,.contribute>p{font-size:17px}.links{gap:10px;margin:22px 0 26px}.links a{padding:8px 12px;font-size:16px}.filters{grid-template-columns:1fr;padding:20px 16px;gap:17px}.board{border-radius:12px}.board-heading{padding:20px 15px 15px;display:block}.board-heading p{margin-top:8px}.metric-note{padding:0 15px 19px;font-size:16px}.leaderboard col.rank-col{width:46px}.leaderboard col.result-col{width:147px}.leaderboard th,.leaderboard td{padding-left:10px!important;padding-right:10px!important}.leaderboard th{font-size:16px}.leaderboard tbody td{padding-top:18px;padding-bottom:18px}.leaderboard th:first-child,.leaderboard td:first-child{padding-right:0!important}.rank{width:29px;height:29px;font-size:16px}.agent-name{font-size:17px;line-height:1.45}.agent-harness{font-size:16px;line-height:1.4}.gain{font-size:21px}.raw-score{font-size:16px}.table-note{padding:18px 15px;font-size:16px}.contribute .steps{grid-template-columns:1fr;gap:22px}.contribute{padding-top:27px}.contribute h2{font-size:25px}.data-links{gap:15px 22px}.embed main{padding:18px 14px}.embed .leaderboard col.result-col{width:138px}.embed .leaderboard col.rank-col{width:42px}}
|
| 12 |
@media(prefers-reduced-motion:reduce){html{scroll-behavior:auto}}
|
| 13 |
</style>
|
|
|
|
| 7 |
<title>AutoRSE Leaderboard</title>
|
| 8 |
<meta name="description" content="Compare LLM agents as recommendation engineers on the AutoRSE benchmark. Explore paper reference results and contribute reproducible community evaluations.">
|
| 9 |
<style>
|
| 10 |
+
:root{--ink:#17243d;--blue:#2759c4;--muted:#52647c;--line:#dfe6ef;--soft:#f3f6fc;--green:#16786e;--red:#b64e45;font-family:Inter,-apple-system,BlinkMacSystemFont,"Segoe UI",Arial,sans-serif;color:var(--ink);background:#fff;font-synthesis:none}*{box-sizing:border-box}body{margin:0;font-size:16px;line-height:1.65;-webkit-font-smoothing:antialiased}a{color:var(--blue);text-decoration:none}a:hover{text-decoration:underline}button,select{font:inherit}a:focus-visible,button:focus-visible,select:focus-visible,summary:focus-visible{outline:3px solid #4d85e7;outline-offset:4px}button{cursor:pointer}h1,h2,h3,p{margin:0}h1,h2,h3{line-height:1.2;letter-spacing:-.035em}h1{font-size:clamp(32px,4vw,44px);font-weight:750}h2{font-size:27px;font-weight:700}main{max-width:1080px;margin:auto;padding:42px 32px 32px}.brand{display:flex;align-items:center;gap:10px;color:var(--blue);font-weight:750;font-size:18px;letter-spacing:-.03em;margin-bottom:21px}.brand svg{width:30px;height:30px}.intro{font-size:18px;color:var(--muted);max-width:760px;margin-top:16px}.links{display:flex;gap:10px;flex-wrap:wrap;margin:25px 0 34px}.links a{display:inline-flex;align-items:center;gap:10px;border:1px solid var(--line);border-radius:7px;min-height:44px;padding:8px 16px;font-size:16px;font-weight:600}.links .primary{color:white;background:var(--blue);border-color:var(--blue)}.links a:hover{text-decoration:none;background:#edf3fe;color:var(--blue)}.board{border:1px solid #d8e2ef;border-radius:16px;background:white;overflow:hidden}.filters{display:grid;grid-template-columns:repeat(3,minmax(0,1fr));gap:22px;padding:24px;background:#f8faff;border-bottom:1px solid var(--line)}.filters label{display:flex;flex-direction:column;gap:8px;font-weight:600;color:#3b5274;font-size:16px}select{width:100%;min-height:46px;padding:9px 35px 9px 12px;border:1px solid #ccd9eb;border-radius:7px;color:var(--ink);background:#fff;font-size:16px}.board-heading{display:flex;justify-content:space-between;align-items:baseline;gap:20px;padding:23px 24px 20px}.board-heading h2{font-size:22px}.board-heading p{font-size:16px;color:var(--muted)}.metric-note{font-size:16px;color:var(--muted);padding:0 24px 21px}.table-scroll{overflow-x:auto}.leaderboard{border-collapse:collapse;width:100%;font-variant-numeric:tabular-nums;table-layout:fixed}.leaderboard col.rank-col{width:80px}.leaderboard col.result-col{width:310px}.leaderboard thead th{padding:14px 24px;border-top:1px solid var(--line);border-bottom:1px solid var(--line);background:#f8faff;color:#415776;font-size:16px;font-weight:600;text-align:left}.leaderboard thead th:last-child{text-align:right}.leaderboard tbody td{border-bottom:1px solid #e8edf5;padding:19px 24px;vertical-align:middle}.leaderboard tbody tr:last-child td{border:0}.leaderboard tbody tr:hover{background:#f8fbff}.leaderboard tbody tr.leader-row{background:#f2f6ff}.rank{display:grid;place-items:center;width:32px;height:32px;border-radius:8px;font-size:17px;font-weight:650;color:#5a6d86;background:#f0f3f8}.rank.top{background:#e0eaff;color:#2759c4}.leaderboard tbody tr.leader-row .rank{background:var(--blue);color:#fff}.agent-name{font-size:18px;font-weight:650;line-height:1.4;overflow-wrap:anywhere}.agent-harness{font-size:16px;color:var(--muted);display:block;margin-top:4px}.result{text-align:right}.gain{display:block;font-size:23px;font-weight:700;line-height:1.3;letter-spacing:-.025em}.mean-rank{color:var(--blue)}.positive{color:var(--green)}.negative{color:var(--red)}.raw-score{display:block;font-size:16px;line-height:1.55;color:var(--muted);margin-top:7px}.table-note{font-size:16px;color:var(--muted);padding:20px 24px;border-top:1px solid var(--line);background:#fbfcff}.rank-breakdown{margin:0;padding:0 24px;border-top:1px solid var(--line)}.rank-breakdown>summary{padding:19px 0}.rank-table-scroll{overflow-x:auto;padding-bottom:20px}.rank-table{width:100%;min-width:810px;border-collapse:collapse;font-variant-numeric:tabular-nums;font-size:16px;text-align:center}.rank-table th,.rank-table td{padding:12px 10px;border-bottom:1px solid var(--line)}.rank-table thead th{font-weight:600;color:#415776;background:#f8faff}.rank-table th:first-child,.rank-table td:first-child{text-align:left;min-width:190px}.rank-table th:last-child,.rank-table td:last-child{font-weight:650;color:var(--blue)}.rank-table .agent-name{font-size:16px}.empty{font-size:18px;text-align:center;color:var(--muted);padding:32px!important}.data-links{display:flex;gap:22px;flex-wrap:wrap;font-size:16px;font-weight:550;margin:23px 0 28px}.contribute{border-top:1px solid var(--line);padding-top:30px;margin-top:28px}.contribute>p{color:var(--muted);font-size:18px;max-width:760px;margin-top:13px}.contribute .steps{display:grid;grid-template-columns:repeat(3,1fr);gap:24px;margin-top:24px}.step{padding:0 8px 0 17px;border-left:3px solid #d2e0fa}.step strong{font-size:18px;display:block}.step p{font-size:16px;color:var(--muted);margin-top:8px}.submission-links{display:flex;gap:22px;flex-wrap:wrap;margin-top:24px;font-size:16px;font-weight:600}details{border-top:1px solid var(--line);margin-top:30px}summary{cursor:pointer;list-style:none;font-size:16px;font-weight:600;padding:20px 0;display:flex;align-items:center;justify-content:space-between}summary::-webkit-details-marker{display:none}summary:hover{text-decoration:underline;text-underline-offset:4px}.method{color:var(--muted);font-size:16px;padding:0 0 6px;max-width:900px}.method p+p{margin-top:13px}.source-label{color:var(--muted);font-size:16px}.sr-only{position:absolute;width:1px;height:1px;margin:-1px;padding:0;overflow:hidden;clip:rect(0,0,0,0);white-space:nowrap;border:0}[hidden]{display:none!important}.status{padding:18px 0;color:#875b21;font-size:16px}.noscript{padding:24px;font-size:18px}.footer{margin-top:30px;padding-top:22px;border-top:1px solid var(--line);color:var(--muted);font-size:16px}.embed .standalone{display:none}.embed main{padding:24px;max-width:none}.embed .links{margin-bottom:24px}.embed .contribute{margin-bottom:0}.embed .board-heading{padding-top:21px}
|
| 11 |
@media(max-width:600px){main{padding:28px 18px 24px}.brand{margin-bottom:16px}h1{font-size:32px}.intro,.contribute>p{font-size:17px}.links{gap:10px;margin:22px 0 26px}.links a{padding:8px 12px;font-size:16px}.filters{grid-template-columns:1fr;padding:20px 16px;gap:17px}.board{border-radius:12px}.board-heading{padding:20px 15px 15px;display:block}.board-heading p{margin-top:8px}.metric-note{padding:0 15px 19px;font-size:16px}.leaderboard col.rank-col{width:46px}.leaderboard col.result-col{width:147px}.leaderboard th,.leaderboard td{padding-left:10px!important;padding-right:10px!important}.leaderboard th{font-size:16px}.leaderboard tbody td{padding-top:18px;padding-bottom:18px}.leaderboard th:first-child,.leaderboard td:first-child{padding-right:0!important}.rank{width:29px;height:29px;font-size:16px}.agent-name{font-size:17px;line-height:1.45}.agent-harness{font-size:16px;line-height:1.4}.gain{font-size:21px}.raw-score{font-size:16px}.table-note{padding:18px 15px;font-size:16px}.contribute .steps{grid-template-columns:1fr;gap:22px}.contribute{padding-top:27px}.contribute h2{font-size:25px}.data-links{gap:15px 22px}.embed main{padding:18px 14px}.embed .leaderboard col.result-col{width:138px}.embed .leaderboard col.rank-col{width:42px}}
|
| 12 |
@media(prefers-reduced-motion:reduce){html{scroll-behavior:auto}}
|
| 13 |
</style>
|