yzzhao commited on
Commit
348cb69
·
verified ·
1 Parent(s): 074c0f5

Extend autonomous and input-required to fifty Hard tasks

Browse files
Files changed (3) hide show
  1. hard/data-source.json +7 -7
  2. hard/index.html +2 -2
  3. manifest.json +3 -3
hard/data-source.json CHANGED
@@ -1,23 +1,23 @@
1
  {
2
  "schema": "programvla/dataset-source/1",
3
  "dataset": "RLE-Bench/programmable-vla",
4
- "revision": "3bca5873577124c4dee20f7d0c3ad4ac2cd6a492",
5
- "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3bca5873577124c4dee20f7d0c3ad4ac2cd6a492/",
6
  "files": {
7
  "data.json": {
8
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3bca5873577124c4dee20f7d0c3ad4ac2cd6a492/research/hard50-expansion-20261105/panels/hard/data.json"
9
  },
10
  "cost-data.json": {
11
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3bca5873577124c4dee20f7d0c3ad4ac2cd6a492/research/hard50-expansion-20261105/panels/hard/cost-data.json"
12
  },
13
  "measured-instructions.json": {
14
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3bca5873577124c4dee20f7d0c3ad4ac2cd6a492/research/hard50-expansion-20261105/panels/hard/measured-instructions.json"
15
  },
16
  "sources.json": {
17
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3bca5873577124c4dee20f7d0c3ad4ac2cd6a492/research/hard50-expansion-20261105/panels/hard/sources.json"
18
  },
19
  "instruction-audit.json": {
20
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3bca5873577124c4dee20f7d0c3ad4ac2cd6a492/research/hard50-expansion-20261105/panels/hard/instruction-audit.json"
21
  },
22
  "attempt-history.json": {
23
  "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0c1485e58abde3e82a99e9762cc3dbac790c5dc0/research/kinex-rle-20261104/panels/hard/attempt-history.json"
 
1
  {
2
  "schema": "programvla/dataset-source/1",
3
  "dataset": "RLE-Bench/programmable-vla",
4
+ "revision": "16357d3813fc80d57280961efa816ec58d52644d",
5
+ "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/16357d3813fc80d57280961efa816ec58d52644d/",
6
  "files": {
7
  "data.json": {
8
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/16357d3813fc80d57280961efa816ec58d52644d/research/hard50-expansion-20261105/panels/hard/data.json"
9
  },
10
  "cost-data.json": {
11
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/16357d3813fc80d57280961efa816ec58d52644d/research/hard50-expansion-20261105/panels/hard/cost-data.json"
12
  },
13
  "measured-instructions.json": {
14
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/16357d3813fc80d57280961efa816ec58d52644d/research/hard50-expansion-20261105/panels/hard/measured-instructions.json"
15
  },
16
  "sources.json": {
17
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/16357d3813fc80d57280961efa816ec58d52644d/research/hard50-expansion-20261105/panels/hard/sources.json"
18
  },
19
  "instruction-audit.json": {
20
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/16357d3813fc80d57280961efa816ec58d52644d/research/hard50-expansion-20261105/panels/hard/instruction-audit.json"
21
  },
22
  "attempt-history.json": {
23
  "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0c1485e58abde3e82a99e9762cc3dbac790c5dc0/research/kinex-rle-20261104/panels/hard/attempt-history.json"
hard/index.html CHANGED
@@ -19,9 +19,9 @@
19
  <a class="skip" href="#main">Skip to content</a>
20
  <header class="site-header"><div class="header-inner"><a class="brand" href="#overview" aria-label="Programmable VLA home"><img src="assets/kinex-logo.svg" width="34" height="34" alt="Kinex"><span>programmable<span class="brand-divider">/</span><span class="brand-benchmark">vla</span></span></a><nav aria-label="Main navigation"><a href="../plus/index.html">Plus</a><a href="../index.html#overview">Easy</a><a href="#overview" data-nav="overview">Hard</a><a href="#tasks" data-nav="tasks">Explore tasks</a><a href="#instructions" data-nav="instructions">Instructions audit</a><a href="#methodology" data-nav="methodology">Protocol</a></nav><a class="header-link" href="https://huggingface.co/spaces/RLE-Bench/programmable-vla" target="_blank" rel="noopener">Hugging Face <span aria-hidden="true">↗</span></a></div></header>
21
  <main id="main" tabindex="-1"><div class="loading"><span class="spinner"></span>Loading benchmark results…</div></main>
22
- <footer class="site-footer"><div><img src="assets/kinex-logo.svg" width="22" height="22" alt=""><strong>Programmable VLA</strong><span class="footer-org">by RLE-Bench</span></div><div><a data-result-file="data.json" href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3bca5873577124c4dee20f7d0c3ad4ac2cd6a492/research/hard50-expansion-20261105/panels/hard/data.json" target="_blank">Hard results JSON</a><a data-result-file="sources.json" href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/b07d88579523eeeefdf7ad2ca14ee65340af5d4e/hard/sources.json" target="_blank">Data sources</a><a href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3bca5873577124c4dee20f7d0c3ad4ac2cd6a492/manifest.json" target="_blank">Manifest</a><span id="updated"></span></div></footer>
23
  <dialog id="image-viewer" aria-labelledby="image-caption"><div class="viewer-toolbar"><span id="image-caption"></span><a id="image-original" target="_blank" rel="noopener">Open original ↗</a><button class="icon-button" id="close-viewer" aria-label="Close image">×</button></div><div class="viewer-image"><button id="previous-image" class="viewer-arrow" aria-label="Previous image">←</button><img id="large-image" alt="Recorded agent observation"><button id="next-image" class="viewer-arrow" aria-label="Next image">→</button></div><p>Recorded agent observation · Use ← → to browse · Esc to close</p></dialog>
24
  <div id="toast" role="status" aria-live="polite"></div>
25
- <noscript><p>This site needs JavaScript. <a data-result-file="data.json" href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3bca5873577124c4dee20f7d0c3ad4ac2cd6a492/research/hard50-expansion-20261105/panels/hard/data.json">Download the complete results index.</a></p></noscript>
26
  </body>
27
  </html>
 
19
  <a class="skip" href="#main">Skip to content</a>
20
  <header class="site-header"><div class="header-inner"><a class="brand" href="#overview" aria-label="Programmable VLA home"><img src="assets/kinex-logo.svg" width="34" height="34" alt="Kinex"><span>programmable<span class="brand-divider">/</span><span class="brand-benchmark">vla</span></span></a><nav aria-label="Main navigation"><a href="../plus/index.html">Plus</a><a href="../index.html#overview">Easy</a><a href="#overview" data-nav="overview">Hard</a><a href="#tasks" data-nav="tasks">Explore tasks</a><a href="#instructions" data-nav="instructions">Instructions audit</a><a href="#methodology" data-nav="methodology">Protocol</a></nav><a class="header-link" href="https://huggingface.co/spaces/RLE-Bench/programmable-vla" target="_blank" rel="noopener">Hugging Face <span aria-hidden="true">↗</span></a></div></header>
21
  <main id="main" tabindex="-1"><div class="loading"><span class="spinner"></span>Loading benchmark results…</div></main>
22
+ <footer class="site-footer"><div><img src="assets/kinex-logo.svg" width="22" height="22" alt=""><strong>Programmable VLA</strong><span class="footer-org">by RLE-Bench</span></div><div><a data-result-file="data.json" href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/16357d3813fc80d57280961efa816ec58d52644d/research/hard50-expansion-20261105/panels/hard/data.json" target="_blank">Hard results JSON</a><a data-result-file="sources.json" href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/b07d88579523eeeefdf7ad2ca14ee65340af5d4e/hard/sources.json" target="_blank">Data sources</a><a href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/16357d3813fc80d57280961efa816ec58d52644d/manifest.json" target="_blank">Manifest</a><span id="updated"></span></div></footer>
23
  <dialog id="image-viewer" aria-labelledby="image-caption"><div class="viewer-toolbar"><span id="image-caption"></span><a id="image-original" target="_blank" rel="noopener">Open original ↗</a><button class="icon-button" id="close-viewer" aria-label="Close image">×</button></div><div class="viewer-image"><button id="previous-image" class="viewer-arrow" aria-label="Previous image">←</button><img id="large-image" alt="Recorded agent observation"><button id="next-image" class="viewer-arrow" aria-label="Next image">→</button></div><p>Recorded agent observation · Use ← → to browse · Esc to close</p></dialog>
24
  <div id="toast" role="status" aria-live="polite"></div>
25
+ <noscript><p>This site needs JavaScript. <a data-result-file="data.json" href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/16357d3813fc80d57280961efa816ec58d52644d/research/hard50-expansion-20261105/panels/hard/data.json">Download the complete results index.</a></p></noscript>
26
  </body>
27
  </html>
manifest.json CHANGED
@@ -112,7 +112,7 @@
112
  },
113
  "hard/index.html": {
114
  "bytes": 3715,
115
- "sha256": "04f5a4e0af5a970ad11c60f23a13ae6b6361ee1ce1fb9261c25d6c8b67a99f19"
116
  },
117
  "hard/policy.css": {
118
  "bytes": 1067,
@@ -124,7 +124,7 @@
124
  },
125
  "hard/data-source.json": {
126
  "bytes": 1622,
127
- "sha256": "9c97eee679b550badfd4ccfd8fc7b5b5ad65ad0e9c3b3097ac70063b166960a9"
128
  },
129
  "plus/app.js": {
130
  "bytes": 95753,
@@ -288,7 +288,7 @@
288
  },
289
  "hard50_expansion_dataset": {
290
  "repo": "RLE-Bench/programmable-vla",
291
- "revision": "3bca5873577124c4dee20f7d0c3ad4ac2cd6a492",
292
  "prefix": "research/hard50-expansion-20261105",
293
  "complete": false
294
  }
 
112
  },
113
  "hard/index.html": {
114
  "bytes": 3715,
115
+ "sha256": "938c7a80a52846a018b7768a6e5e54e8fecf30c19ae05318e555cd6f79a54591"
116
  },
117
  "hard/policy.css": {
118
  "bytes": 1067,
 
124
  },
125
  "hard/data-source.json": {
126
  "bytes": 1622,
127
+ "sha256": "ae8fceea18c61d4c770e4be28712b069883f2a12df515f978f7dfc4eb814a171"
128
  },
129
  "plus/app.js": {
130
  "bytes": 95753,
 
288
  },
289
  "hard50_expansion_dataset": {
290
  "repo": "RLE-Bench/programmable-vla",
291
+ "revision": "16357d3813fc80d57280961efa816ec58d52644d",
292
  "prefix": "research/hard50-expansion-20261105",
293
  "complete": false
294
  }