yzzhao commited on
Commit
eec0134
·
verified ·
1 Parent(s): 63610a5

Show pure Kinex RLE evaluation progress; retain native VLA and historical Kinex evidence

Browse files
hard/data-source.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
  "schema": "programvla/dataset-source/1",
3
  "dataset": "RLE-Bench/programmable-vla",
4
- "revision": "afee9db1b4b004e44604a0c644ac3e078090193a",
5
- "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/",
6
  "files": {
7
  "data.json": {
8
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/hard/data.json"
9
  },
10
  "cost-data.json": {
11
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/hard/cost-data.json"
12
  },
13
  "measured-instructions.json": {
14
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/hard/measured-instructions.json"
15
  },
16
  "sources.json": {
17
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/hard/sources.json"
18
  },
19
  "instruction-audit.json": {
20
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/hard/instruction-audit.json"
21
  },
22
  "attempt-history.json": {
23
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/hard/attempt-history.json"
24
  }
25
  }
26
  }
 
1
  {
2
  "schema": "programvla/dataset-source/1",
3
  "dataset": "RLE-Bench/programmable-vla",
4
+ "revision": "0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b",
5
+ "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/",
6
  "files": {
7
  "data.json": {
8
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/hard/data.json"
9
  },
10
  "cost-data.json": {
11
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/hard/cost-data.json"
12
  },
13
  "measured-instructions.json": {
14
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/hard/measured-instructions.json"
15
  },
16
  "sources.json": {
17
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/hard/sources.json"
18
  },
19
  "instruction-audit.json": {
20
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/hard/instruction-audit.json"
21
  },
22
  "attempt-history.json": {
23
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/hard/attempt-history.json"
24
  }
25
  }
26
  }
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/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/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/b07d88579523eeeefdf7ad2ca14ee65340af5d4e/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/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/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/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/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/b07d88579523eeeefdf7ad2ca14ee65340af5d4e/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/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/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": 3630,
115
- "sha256": "22e9e14ada292066a76b1da9062724bfad3ea1fddc72cc436b47101174e6900b"
116
  },
117
  "hard/policy.css": {
118
  "bytes": 1067,
@@ -124,7 +124,7 @@
124
  },
125
  "hard/data-source.json": {
126
  "bytes": 1587,
127
- "sha256": "6c984f8208f10798add5bf79fadcf87819be7f41f6ea01b403c247e31e2ee711"
128
  },
129
  "plus/app.js": {
130
  "bytes": 98313,
@@ -140,7 +140,7 @@
140
  },
141
  "plus/index.html": {
142
  "bytes": 3639,
143
- "sha256": "df730fcf9d346f2c1f0e3af6c02b48681c241328662df4b829b3f667e5528cb2"
144
  },
145
  "plus/policy.css": {
146
  "bytes": 1067,
@@ -152,7 +152,7 @@
152
  },
153
  "plus/data-source.json": {
154
  "bytes": 1587,
155
- "sha256": "88850333910c6fce607718c50b445bc02212b9bbaf22250d049d98d64aeb041b"
156
  },
157
  "instruction-audit/sources/task03-manifest.yaml": {
158
  "bytes": 5747,
@@ -255,7 +255,7 @@
255
  },
256
  "kinex_rle_dataset": {
257
  "repo": "RLE-Bench/programmable-vla",
258
- "revision": "afee9db1b4b004e44604a0c644ac3e078090193a",
259
  "prefix": "research/kinex-rle-20261104",
260
  "scope": "Pure Kinex, RLE revised instructions; Hard 50 selected, Plus 24 selected",
261
  "complete": false
 
112
  },
113
  "hard/index.html": {
114
  "bytes": 3630,
115
+ "sha256": "1376006f78d3b64a34983921154d1288f98af22947f7c4c70d59b657afc47e45"
116
  },
117
  "hard/policy.css": {
118
  "bytes": 1067,
 
124
  },
125
  "hard/data-source.json": {
126
  "bytes": 1587,
127
+ "sha256": "d791ad351cd1da78b9a4a63fd620395cda6340ff3cc3f5ea6aa78cee0f5d19f5"
128
  },
129
  "plus/app.js": {
130
  "bytes": 98313,
 
140
  },
141
  "plus/index.html": {
142
  "bytes": 3639,
143
+ "sha256": "d891cb116dae891a0a1b9ec1351129d05f41a0041eedb04a331c02f6f04bb06f"
144
  },
145
  "plus/policy.css": {
146
  "bytes": 1067,
 
152
  },
153
  "plus/data-source.json": {
154
  "bytes": 1587,
155
+ "sha256": "5751e9bb635aab4ee28a0d6b4f9a428580a249b12ee67d41a5f3a618773a163f"
156
  },
157
  "instruction-audit/sources/task03-manifest.yaml": {
158
  "bytes": 5747,
 
255
  },
256
  "kinex_rle_dataset": {
257
  "repo": "RLE-Bench/programmable-vla",
258
+ "revision": "0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b",
259
  "prefix": "research/kinex-rle-20261104",
260
  "scope": "Pure Kinex, RLE revised instructions; Hard 50 selected, Plus 24 selected",
261
  "complete": false
plus/data-source.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
  "schema": "programvla/dataset-source/1",
3
  "dataset": "RLE-Bench/programmable-vla",
4
- "revision": "afee9db1b4b004e44604a0c644ac3e078090193a",
5
- "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/",
6
  "files": {
7
  "data.json": {
8
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/plus/data.json"
9
  },
10
  "cost-data.json": {
11
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/plus/cost-data.json"
12
  },
13
  "measured-instructions.json": {
14
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/plus/measured-instructions.json"
15
  },
16
  "sources.json": {
17
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/plus/sources.json"
18
  },
19
  "instruction-audit.json": {
20
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/plus/instruction-audit.json"
21
  },
22
  "attempt-history.json": {
23
- "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/plus/attempt-history.json"
24
  }
25
  }
26
  }
 
1
  {
2
  "schema": "programvla/dataset-source/1",
3
  "dataset": "RLE-Bench/programmable-vla",
4
+ "revision": "0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b",
5
+ "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/",
6
  "files": {
7
  "data.json": {
8
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/plus/data.json"
9
  },
10
  "cost-data.json": {
11
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/plus/cost-data.json"
12
  },
13
  "measured-instructions.json": {
14
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/plus/measured-instructions.json"
15
  },
16
  "sources.json": {
17
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/plus/sources.json"
18
  },
19
  "instruction-audit.json": {
20
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/plus/instruction-audit.json"
21
  },
22
  "attempt-history.json": {
23
+ "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/plus/attempt-history.json"
24
  }
25
  }
26
  }
plus/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="../index.html#overview">Easy</a><a href="../hard/index.html#overview">Hard</a><a href="#overview" data-nav="overview">Plus</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/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/plus/data.json" target="_blank">Plus 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/b2d67a67dd2f9d8e12c1f8db13ba8de309739883/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/afee9db1b4b004e44604a0c644ac3e078090193a/research/kinex-rle-20261104/panels/plus/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="../index.html#overview">Easy</a><a href="../hard/index.html#overview">Hard</a><a href="#overview" data-nav="overview">Plus</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/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/plus/data.json" target="_blank">Plus 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/b2d67a67dd2f9d8e12c1f8db13ba8de309739883/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/0bca7555cfcb6d55c1ccec40c1a6cfac6108c01b/research/kinex-rle-20261104/panels/plus/data.json">Download the complete results index.</a></p></noscript>
25
  </body>
26
  </html>