Add VLAct Clean 50k input-required text-target Hard results

README.md

@@ -106,7 +106,7 @@ VLA input: three RGB images and caller text. Output: 32 absolute-joint samples a
 
 ## Kinex + VLAct Qwen3-VL-OFT · Clean 50k (input-required · text targets)
 
-**Partial; evaluation continues: 1/50 audited Hard episodes published.** Updated: 2026-11-06T21:32:06.489819+00:00.
+**Partial; evaluation continues: 11/50 audited Hard episodes published.** Updated: 2026-11-06T21:44:27.951305+00:00.
 
 - Agent: Kinex, GPT-6 Astra / high.
 - Checkpoint: [StarVLA/VLAct_Qwen3OFT_Robotwin_Finetune](https://huggingface.co/StarVLA/VLAct_Qwen3OFT_Robotwin_Finetune/tree/dcf0f1d7239b28ae81a039c8d05bdfcd1d4792a5), step **50,000**, **RoboTwin clean** training distribution.
@@ -118,7 +118,7 @@ Every VLA request serializes a JSON object with goal, context, feedback, constra
 
 Kinex retains control of observations, whether to invoke VLA, direct control, execution prefixes and feedback. Zero VLA calls are valid. This uses the historical five-field text-target schema within the current shared operation description and model/execution pipeline. The present numeric-target-text-v1 results require numerical TCP/joint destinations; the two input-required variants remain separate. Earlier All 140k text-target results retain their own checkpoint and frozen runtime/prompt versions.
 
-Native successes: **0/1 evaluated**. Episodes using VLA: **1**; zero-call episodes: **0**. VLA calls: **4**; rejected requests: **0**; accepted calls with null target: **0**.
+Native successes: **7/11 evaluated**. Episodes using VLA: **7**; zero-call episodes: **4**. VLA calls: **35**; rejected requests: **0**; accepted calls with null target: **0**.
 
 Pending tasks are excluded from score denominators. Partial results are not full-suite scores. All valid successes and failures are retained; no valid-outcome retries, seed substitution, fine-tuning or expert-success filtering. One authored seed per task does not establish multi-seed reliability.
 

hard/data-source.json

@@ -1,23 +1,23 @@
 {
   "schema": "programvla/dataset-source/1",
   "dataset": "RLE-Bench/programmable-vla",
-  "revision": "3f0130f10e3e267822b9a61208378de4da3f76a0",
-  "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3f0130f10e3e267822b9a61208378de4da3f76a0/",
+  "revision": "19000defaa156236c058f1e7a778dc663d19c609",
+  "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/19000defaa156236c058f1e7a778dc663d19c609/",
   "files": {
     "data.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3f0130f10e3e267822b9a61208378de4da3f76a0/research/text-target-hard50-20261106/panels/hard/data.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/19000defaa156236c058f1e7a778dc663d19c609/research/text-target-hard50-20261106/panels/hard/data.json"
     },
     "cost-data.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3f0130f10e3e267822b9a61208378de4da3f76a0/research/text-target-hard50-20261106/panels/hard/cost-data.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/19000defaa156236c058f1e7a778dc663d19c609/research/text-target-hard50-20261106/panels/hard/cost-data.json"
     },
     "measured-instructions.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3f0130f10e3e267822b9a61208378de4da3f76a0/research/text-target-hard50-20261106/panels/hard/measured-instructions.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/19000defaa156236c058f1e7a778dc663d19c609/research/text-target-hard50-20261106/panels/hard/measured-instructions.json"
     },
     "sources.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3f0130f10e3e267822b9a61208378de4da3f76a0/research/text-target-hard50-20261106/panels/hard/sources.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/19000defaa156236c058f1e7a778dc663d19c609/research/text-target-hard50-20261106/panels/hard/sources.json"
     },
     "instruction-audit.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3f0130f10e3e267822b9a61208378de4da3f76a0/research/text-target-hard50-20261106/panels/hard/instruction-audit.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/19000defaa156236c058f1e7a778dc663d19c609/research/text-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/3f0130f10e3e267822b9a61208378de4da3f76a0/research/text-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/3f0130f10e3e267822b9a61208378de4da3f76a0/research/text-target-hard50-20261106/panels/hard/sources.json" target="_blank">Data sources</a><a href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/3f0130f10e3e267822b9a61208378de4da3f76a0/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/19000defaa156236c058f1e7a778dc663d19c609/research/text-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/19000defaa156236c058f1e7a778dc663d19c609/research/text-target-hard50-20261106/panels/hard/sources.json" target="_blank">Data sources</a><a href="https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/19000defaa156236c058f1e7a778dc663d19c609/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/3f0130f10e3e267822b9a61208378de4da3f76a0/research/text-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/19000defaa156236c058f1e7a778dc663d19c609/research/text-target-hard50-20261106/panels/hard/data.json">Download the complete results index.</a></p></noscript>
 </body>
 </html>

manifest.json

@@ -23,8 +23,8 @@
       "sha256": "34a4d6e437537e78bc242418805a3af3d71b43980280482fd8fc6bfda91f79f8"
     },
     "README.md": {
-      "bytes": 13718,
-      "sha256": "61a2eda3f0c3fe4b786e4286879c943a8974596a70214b12cbdf5be42b2baacf"
+      "bytes": 13721,
+      "sha256": "75b26e6eb2cf7b5de63844ceb1c28cead692598131ac6352db8d9549ae9ea605"
     },
     "instruction-audit.js": {
       "bytes": 13118,
@@ -112,7 +112,7 @@
     },
     "hard/index.html": {
       "bytes": 4063,
-      "sha256": "6cdd420d6a9699a83478e1be6ed2aaa25985033795ad08afb5f3bde32f640ac5"
+      "sha256": "bc401dc3546f137b5cd0a873dbf9e8174feeed524c8d2b6c68c0dd7d0fb99f55"
     },
     "hard/policy.css": {
       "bytes": 1067,
@@ -124,7 +124,7 @@
     },
     "hard/data-source.json": {
       "bytes": 1632,
-      "sha256": "f56e118cdae78a29930f6298a458990a8e2e3ab574cba8bbe116532b5f610192"
+      "sha256": "56416100bc64c61c6038de566e33062b8e60dab93b8563dadfd792e4cdf9a65c"
     },
     "plus/app.js": {
       "bytes": 96794,
@@ -304,7 +304,7 @@
   },
   "vlact50k_text_targets_hard50_dataset": {
     "repo": "RLE-Bench/programmable-vla",
-    "revision": "3f0130f10e3e267822b9a61208378de4da3f76a0",
+    "revision": "19000defaa156236c058f1e7a778dc663d19c609",
     "prefix": "research/text-target-hard50-20261106",
     "complete": false
   }