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

hard/data-source.json

@@ -1,26 +1,26 @@
 {
   "schema": "programvla/dataset-source/1",
   "dataset": "RLE-Bench/programmable-vla",
-  "revision": "23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2",
-  "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/",
+  "revision": "298f91505c96a7d842b13c4d88fe114114f3fa66",
+  "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/",
   "files": {
     "data.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/hard/data.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/hard/data.json"
     },
     "cost-data.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/hard/cost-data.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/hard/cost-data.json"
     },
     "measured-instructions.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/hard/measured-instructions.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/hard/measured-instructions.json"
     },
     "sources.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/hard/sources.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/hard/sources.json"
     },
     "instruction-audit.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/hard/instruction-audit.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/hard/instruction-audit.json"
     },
     "attempt-history.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/hard/attempt-history.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/hard/attempt-history.json"
     }
   }
 }

hard/index.html

@@ -18,9 +18,9 @@
 <a class="skip" href="#main">Skip to content</a>
 <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>
 <main id="main" tabindex="-1"><div class="loading"><span class="spinner"></span>Loading benchmark results…</div></main>
-<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/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/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>
+<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/298f91505c96a7d842b13c4d88fe114114f3fa66/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>
 <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>
 <div id="toast" role="status" aria-live="polite"></div>
-<noscript><p>This site needs JavaScript. <a data-result-file="data.json" href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/hard/data.json">Download the complete results index.</a></p></noscript>
+<noscript><p>This site needs JavaScript. <a data-result-file="data.json" href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/hard/data.json">Download the complete results index.</a></p></noscript>
 </body>
 </html>

manifest.json

@@ -112,7 +112,7 @@
     },
     "hard/index.html": {
       "bytes": 3630,
-      "sha256": "1d02381aaadf21e60e7650119a0b644d42394f1bb08f6c12c773374b1befb443"
+      "sha256": "0b501c0dab44e456f5df1e17751c8313986006cde502bf9eaac9071b27b32402"
     },
     "hard/policy.css": {
       "bytes": 1067,
@@ -124,7 +124,7 @@
     },
     "hard/data-source.json": {
       "bytes": 1587,
-      "sha256": "b532cffd3e672655a87906a294ae398f3c3de31f4f90d23e9abe6c7553e5d71d"
+      "sha256": "62d13677d04c05845337e385eb72e91b907442ba74e3876989098853ad2ca690"
     },
     "plus/app.js": {
       "bytes": 98374,
@@ -140,7 +140,7 @@
     },
     "plus/index.html": {
       "bytes": 3639,
-      "sha256": "be8b5f8d4cbf94be4018c85be9ea3e93d9a0fb5414f650bd0c38db35da142881"
+      "sha256": "ceea4ade284c1218e912984fcfe7ea3a6ea520ed4cbe4b4aa0403bb9e3d0589c"
     },
     "plus/policy.css": {
       "bytes": 1067,
@@ -152,7 +152,7 @@
     },
     "plus/data-source.json": {
       "bytes": 1587,
-      "sha256": "2d1f0afbdac2cc7d489077aa1bd5ac29188a37c21c18bfe1fcd7e3e189d7a9e7"
+      "sha256": "443a257b585c8a761670be76245ae98820a77347d7094c00bfd0b27e47f3ea90"
     },
     "instruction-audit/sources/task03-manifest.yaml": {
       "bytes": 5747,
@@ -255,7 +255,7 @@
   },
   "kinex_rle_dataset": {
     "repo": "RLE-Bench/programmable-vla",
-    "revision": "23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2",
+    "revision": "298f91505c96a7d842b13c4d88fe114114f3fa66",
     "prefix": "research/kinex-rle-20261104",
     "scope": "Pure Kinex, RLE revised instructions; Hard 50 selected, Plus 24 selected",
     "complete": false

plus/data-source.json

@@ -1,26 +1,26 @@
 {
   "schema": "programvla/dataset-source/1",
   "dataset": "RLE-Bench/programmable-vla",
-  "revision": "23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2",
-  "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/",
+  "revision": "298f91505c96a7d842b13c4d88fe114114f3fa66",
+  "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/",
   "files": {
     "data.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/plus/data.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/plus/data.json"
     },
     "cost-data.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/plus/cost-data.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/plus/cost-data.json"
     },
     "measured-instructions.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/plus/measured-instructions.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/plus/measured-instructions.json"
     },
     "sources.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/plus/sources.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/plus/sources.json"
     },
     "instruction-audit.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/plus/instruction-audit.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/plus/instruction-audit.json"
     },
     "attempt-history.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/plus/attempt-history.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/plus/attempt-history.json"
     }
   }
 }

plus/index.html

@@ -18,9 +18,9 @@
 <a class="skip" href="#main">Skip to content</a>
 <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>
 <main id="main" tabindex="-1"><div class="loading"><span class="spinner"></span>Loading benchmark results…</div></main>
-<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/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/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>
+<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/298f91505c96a7d842b13c4d88fe114114f3fa66/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>
 <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>
 <div id="toast" role="status" aria-live="polite"></div>
-<noscript><p>This site needs JavaScript. <a data-result-file="data.json" href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/23d3e0ed1d5488e3a2c7d4ec6fda912814eb3db2/research/kinex-rle-20261104/panels/plus/data.json">Download the complete results index.</a></p></noscript>
+<noscript><p>This site needs JavaScript. <a data-result-file="data.json" href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/298f91505c96a7d842b13c4d88fe114114f3fa66/research/kinex-rle-20261104/panels/plus/data.json">Download the complete results index.</a></p></noscript>
 </body>
 </html>