yzzhao commited on
Commit
6c2f24f
·
verified ·
1 Parent(s): 578d8b9

Show input-required Kinex + VLA results on the Hard panel

Browse files
Files changed (3) hide show
  1. hard/data-source.json +7 -7
  2. hard/index.html +2 -2
  3. manifest.json +4 -4
hard/data-source.json CHANGED
@@ -1,23 +1,23 @@
1
  {
2
  "schema": "programvla/dataset-source/1",
3
  "dataset": "RLE-Bench/programmable-vla",
4
- "revision": "f3be89e5a0c62d7c2c1a8987cce1961e2d451102",
5
- "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/f3be89e5a0c62d7c2c1a8987cce1961e2d451102/",
6
  "files": {
7
  "data.json": {
8
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/f3be89e5a0c62d7c2c1a8987cce1961e2d451102/research/input-required-20261105/panels/hard/data.json"
9
  },
10
  "cost-data.json": {
11
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/f3be89e5a0c62d7c2c1a8987cce1961e2d451102/research/input-required-20261105/panels/hard/cost-data.json"
12
  },
13
  "measured-instructions.json": {
14
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/f3be89e5a0c62d7c2c1a8987cce1961e2d451102/research/input-required-20261105/panels/hard/measured-instructions.json"
15
  },
16
  "sources.json": {
17
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/f3be89e5a0c62d7c2c1a8987cce1961e2d451102/research/input-required-20261105/panels/hard/sources.json"
18
  },
19
  "instruction-audit.json": {
20
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/f3be89e5a0c62d7c2c1a8987cce1961e2d451102/research/input-required-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": "918281b2119b69fb4b3208f0d538ac0006098a42",
5
+ "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/918281b2119b69fb4b3208f0d538ac0006098a42/",
6
  "files": {
7
  "data.json": {
8
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/918281b2119b69fb4b3208f0d538ac0006098a42/research/input-required-20261105/panels/hard/data.json"
9
  },
10
  "cost-data.json": {
11
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/918281b2119b69fb4b3208f0d538ac0006098a42/research/input-required-20261105/panels/hard/cost-data.json"
12
  },
13
  "measured-instructions.json": {
14
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/918281b2119b69fb4b3208f0d538ac0006098a42/research/input-required-20261105/panels/hard/measured-instructions.json"
15
  },
16
  "sources.json": {
17
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/918281b2119b69fb4b3208f0d538ac0006098a42/research/input-required-20261105/panels/hard/sources.json"
18
  },
19
  "instruction-audit.json": {
20
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/918281b2119b69fb4b3208f0d538ac0006098a42/research/input-required-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
@@ -18,9 +18,9 @@
18
  <a class="skip" href="#main">Skip to content</a>
19
  <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>
20
  <main id="main" tabindex="-1"><div class="loading"><span class="spinner"></span>Loading benchmark results…</div></main>
21
- <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/f3be89e5a0c62d7c2c1a8987cce1961e2d451102/research/input-required-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/f3be89e5a0c62d7c2c1a8987cce1961e2d451102/manifest.json" target="_blank">Manifest</a><span id="updated"></span></div></footer>
22
  <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>
23
  <div id="toast" role="status" aria-live="polite"></div>
24
- <noscript><p>This site needs JavaScript. <a data-result-file="data.json" href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/f3be89e5a0c62d7c2c1a8987cce1961e2d451102/research/input-required-20261105/panels/hard/data.json">Download the complete results index.</a></p></noscript>
25
  </body>
26
  </html>
 
18
  <a class="skip" href="#main">Skip to content</a>
19
  <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>
20
  <main id="main" tabindex="-1"><div class="loading"><span class="spinner"></span>Loading benchmark results…</div></main>
21
+ <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/918281b2119b69fb4b3208f0d538ac0006098a42/research/input-required-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/918281b2119b69fb4b3208f0d538ac0006098a42/manifest.json" target="_blank">Manifest</a><span id="updated"></span></div></footer>
22
  <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>
23
  <div id="toast" role="status" aria-live="polite"></div>
24
+ <noscript><p>This site needs JavaScript. <a data-result-file="data.json" href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/918281b2119b69fb4b3208f0d538ac0006098a42/research/input-required-20261105/panels/hard/data.json">Download the complete results index.</a></p></noscript>
25
  </body>
26
  </html>
manifest.json CHANGED
@@ -112,7 +112,7 @@
112
  },
113
  "hard/index.html": {
114
  "bytes": 3640,
115
- "sha256": "6b6046a5433231bba7f6630583e0c24bbd3b2baba0a3d9e2764d67913cfc0ef5"
116
  },
117
  "hard/policy.css": {
118
  "bytes": 1067,
@@ -124,7 +124,7 @@
124
  },
125
  "hard/data-source.json": {
126
  "bytes": 1612,
127
- "sha256": "106691f00c6da59ee961791cba9a887173446c873fc6fbd6ee83204cf66a3408"
128
  },
129
  "plus/app.js": {
130
  "bytes": 93565,
@@ -272,8 +272,8 @@
272
  },
273
  "input_required_dataset": {
274
  "repo": "RLE-Bench/programmable-vla",
275
- "revision": "f3be89e5a0c62d7c2c1a8987cce1961e2d451102",
276
  "prefix": "research/input-required-20261105",
277
- "complete": false
278
  }
279
  }
 
112
  },
113
  "hard/index.html": {
114
  "bytes": 3640,
115
+ "sha256": "817527e74bc292495d88292e750a2f07e7ab278d60eff8be7cca28af89a0f416"
116
  },
117
  "hard/policy.css": {
118
  "bytes": 1067,
 
124
  },
125
  "hard/data-source.json": {
126
  "bytes": 1612,
127
+ "sha256": "c7cb3e4244b195d15813c67af022775725e98d4f8a75b824b05b97f26e1db53f"
128
  },
129
  "plus/app.js": {
130
  "bytes": 93565,
 
272
  },
273
  "input_required_dataset": {
274
  "repo": "RLE-Bench/programmable-vla",
275
+ "revision": "918281b2119b69fb4b3208f0d538ac0006098a42",
276
  "prefix": "research/input-required-20261105",
277
+ "complete": true
278
  }
279
  }