Spaces:
Running
Running
Extend autonomous and input-required to fifty Hard tasks
Browse files- hard/data-source.json +7 -7
- hard/index.html +2 -2
- 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": "
|
| 5 |
-
"evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/
|
| 6 |
"files": {
|
| 7 |
"data.json": {
|
| 8 |
-
"url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/
|
| 9 |
},
|
| 10 |
"cost-data.json": {
|
| 11 |
-
"url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/
|
| 12 |
},
|
| 13 |
"measured-instructions.json": {
|
| 14 |
-
"url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/
|
| 15 |
},
|
| 16 |
"sources.json": {
|
| 17 |
-
"url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/
|
| 18 |
},
|
| 19 |
"instruction-audit.json": {
|
| 20 |
-
"url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/
|
| 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": "eeadca998274456edfddcb9d72d93f0bcf33582f",
|
| 5 |
+
"evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/eeadca998274456edfddcb9d72d93f0bcf33582f/",
|
| 6 |
"files": {
|
| 7 |
"data.json": {
|
| 8 |
+
"url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/eeadca998274456edfddcb9d72d93f0bcf33582f/research/hard50-expansion-20261105/panels/hard/data.json"
|
| 9 |
},
|
| 10 |
"cost-data.json": {
|
| 11 |
+
"url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/eeadca998274456edfddcb9d72d93f0bcf33582f/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/eeadca998274456edfddcb9d72d93f0bcf33582f/research/hard50-expansion-20261105/panels/hard/measured-instructions.json"
|
| 15 |
},
|
| 16 |
"sources.json": {
|
| 17 |
+
"url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/eeadca998274456edfddcb9d72d93f0bcf33582f/research/hard50-expansion-20261105/panels/hard/sources.json"
|
| 18 |
},
|
| 19 |
"instruction-audit.json": {
|
| 20 |
+
"url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/eeadca998274456edfddcb9d72d93f0bcf33582f/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/
|
| 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/
|
| 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/eeadca998274456edfddcb9d72d93f0bcf33582f/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/eeadca998274456edfddcb9d72d93f0bcf33582f/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/eeadca998274456edfddcb9d72d93f0bcf33582f/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": "
|
| 116 |
},
|
| 117 |
"hard/policy.css": {
|
| 118 |
"bytes": 1067,
|
|
@@ -124,7 +124,7 @@
|
|
| 124 |
},
|
| 125 |
"hard/data-source.json": {
|
| 126 |
"bytes": 1622,
|
| 127 |
-
"sha256": "
|
| 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": "
|
| 292 |
"prefix": "research/hard50-expansion-20261105",
|
| 293 |
"complete": false
|
| 294 |
}
|
|
|
|
| 112 |
},
|
| 113 |
"hard/index.html": {
|
| 114 |
"bytes": 3715,
|
| 115 |
+
"sha256": "857fef15aa066bcd1b073f31f2860965489d77f888eeb93fccc85ca5d316cd88"
|
| 116 |
},
|
| 117 |
"hard/policy.css": {
|
| 118 |
"bytes": 1067,
|
|
|
|
| 124 |
},
|
| 125 |
"hard/data-source.json": {
|
| 126 |
"bytes": 1622,
|
| 127 |
+
"sha256": "e545a89ad8dfeef1f558c7727784733e5c20c4879db9a4eca3c5bf862181f2c4"
|
| 128 |
},
|
| 129 |
"plus/app.js": {
|
| 130 |
"bytes": 95753,
|
|
|
|
| 288 |
},
|
| 289 |
"hard50_expansion_dataset": {
|
| 290 |
"repo": "RLE-Bench/programmable-vla",
|
| 291 |
+
"revision": "eeadca998274456edfddcb9d72d93f0bcf33582f",
|
| 292 |
"prefix": "research/hard50-expansion-20261105",
|
| 293 |
"complete": false
|
| 294 |
}
|