Add VLAct 50k autonomous and input-required Hard results

README.md

@@ -73,7 +73,7 @@ The current catalog snapshots include local, uncommitted RLE instruction revisio
 
 ## Kinex + VLAct Qwen3-VL-OFT · Clean 50k
 
-**Partial; evaluation continues: 62/100 audited episodes published.** Updated: 2026-11-06T20:35:54.108812+00:00.
+**Partial; evaluation continues: 72/100 audited episodes published.** Updated: 2026-11-06T20:42:56.828222+00:00.
 
 - Agent: Kinex, GPT-6 Astra / high.
 - VLA checkpoint: [StarVLA/VLAct_Qwen3OFT_Robotwin_Finetune](https://huggingface.co/StarVLA/VLAct_Qwen3OFT_Robotwin_Finetune/tree/dcf0f1d7239b28ae81a039c8d05bdfcd1d4792a5), step **50,000**, **RoboTwin clean** training distribution.
@@ -93,8 +93,8 @@ This campaign is separate from **Kinex + Qwen3-VL-OFT · All 140k**, whose histo
 
 | Protocol | Published / planned | Successes / evaluated | Episodes using VLA |
 | --- | ---: | ---: | ---: |
-| autonomous | 31 / 50 | 20 / 31 | 29 |
-| input-required | 31 / 50 | 26 / 31 | 3 |
+| autonomous | 35 / 50 | 21 / 35 | 33 |
+| input-required | 37 / 50 | 32 / 37 | 4 |
 
 Pending tasks are not failures and are excluded from success-rate denominators. Partial results are not a full-suite score. All completed valid outcomes are retained; no success-based selection or valid-outcome retries.
 

hard/data-source.json

@@ -1,23 +1,23 @@
 {
   "schema": "programvla/dataset-source/1",
   "dataset": "RLE-Bench/programmable-vla",
-  "revision": "8197cf51c79789f36b9ce958b5a30816790228bf",
-  "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/8197cf51c79789f36b9ce958b5a30816790228bf/",
+  "revision": "bda9e6dde50246021b9f7784204fcddf81a68bbd",
+  "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/bda9e6dde50246021b9f7784204fcddf81a68bbd/",
   "files": {
     "data.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/8197cf51c79789f36b9ce958b5a30816790228bf/research/numeric-target-hard50-20261106/panels/hard/data.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/bda9e6dde50246021b9f7784204fcddf81a68bbd/research/numeric-target-hard50-20261106/panels/hard/data.json"
     },
     "cost-data.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/8197cf51c79789f36b9ce958b5a30816790228bf/research/numeric-target-hard50-20261106/panels/hard/cost-data.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/bda9e6dde50246021b9f7784204fcddf81a68bbd/research/numeric-target-hard50-20261106/panels/hard/cost-data.json"
     },
     "measured-instructions.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/8197cf51c79789f36b9ce958b5a30816790228bf/research/numeric-target-hard50-20261106/panels/hard/measured-instructions.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/bda9e6dde50246021b9f7784204fcddf81a68bbd/research/numeric-target-hard50-20261106/panels/hard/measured-instructions.json"
     },
     "sources.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/8197cf51c79789f36b9ce958b5a30816790228bf/research/numeric-target-hard50-20261106/panels/hard/sources.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/bda9e6dde50246021b9f7784204fcddf81a68bbd/research/numeric-target-hard50-20261106/panels/hard/sources.json"
     },
     "instruction-audit.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/8197cf51c79789f36b9ce958b5a30816790228bf/research/numeric-target-hard50-20261106/panels/hard/instruction-audit.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/bda9e6dde50246021b9f7784204fcddf81a68bbd/research/numeric-target-hard50-20261106/panels/hard/instruction-audit.json"
     },
     "attempt-history.json": {
       "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/0c1485e58abde3e82a99e9762cc3dbac790c5dc0/research/kinex-rle-20261104/panels/hard/attempt-history.json"

hard/index.html

@@ -21,9 +21,9 @@
 <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/8197cf51c79789f36b9ce958b5a30816790228bf/research/numeric-target-hard50-20261106/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/8197cf51c79789f36b9ce958b5a30816790228bf/research/numeric-target-hard50-20261106/panels/hard/sources.json" target="_blank">Data sources</a><a href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/8197cf51c79789f36b9ce958b5a30816790228bf/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/bda9e6dde50246021b9f7784204fcddf81a68bbd/research/numeric-target-hard50-20261106/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/bda9e6dde50246021b9f7784204fcddf81a68bbd/research/numeric-target-hard50-20261106/panels/hard/sources.json" target="_blank">Data sources</a><a href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/bda9e6dde50246021b9f7784204fcddf81a68bbd/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/8197cf51c79789f36b9ce958b5a30816790228bf/research/numeric-target-hard50-20261106/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/bda9e6dde50246021b9f7784204fcddf81a68bbd/research/numeric-target-hard50-20261106/panels/hard/data.json">Download the complete results index.</a></p></noscript>
 </body>
 </html>

manifest.json

@@ -24,7 +24,7 @@
     },
     "README.md": {
       "bytes": 10876,
-      "sha256": "10563319bf075816b56f76e5719806504f93521a568bef6bbb9b6f7f97448666"
+      "sha256": "5f3864cf5eee7379dda6ce1aea1d28e517632d6274ada6150ca4b23519d4eb8b"
     },
     "instruction-audit.js": {
       "bytes": 13118,
@@ -112,7 +112,7 @@
     },
     "hard/index.html": {
       "bytes": 4072,
-      "sha256": "311be2f1b9e1991fae98d9ed5071ea51c1cfd418cabb8cd9f25096fb771ca378"
+      "sha256": "fbcb6a0a86ad5013a34edd97c0474c15f3cc34ac5d9079ebb4019e5c93389f2a"
     },
     "hard/policy.css": {
       "bytes": 1067,
@@ -124,7 +124,7 @@
     },
     "hard/data-source.json": {
       "bytes": 1647,
-      "sha256": "eb74647c7489e02c0d0ac574dc6b3781f6fb26e4596e788ee15efe8cd42408ab"
+      "sha256": "f83001da4350203445f39278146f9bc8dd19bbf04e6aa97bdc7f97f9a2fcc3ee"
     },
     "plus/app.js": {
       "bytes": 96794,
@@ -298,7 +298,7 @@
   },
   "vlact50k_hard50_dataset": {
     "repo": "RLE-Bench/programmable-vla",
-    "revision": "8197cf51c79789f36b9ce958b5a30816790228bf",
+    "revision": "bda9e6dde50246021b9f7784204fcddf81a68bbd",
     "prefix": "research/numeric-target-hard50-20261106",
     "complete": false
   }