Show input-required Kinex + VLA results on the Hard panel

hard/app.js

@@ -25,7 +25,7 @@ const compact = v => v == null ? '—' : Math.abs(v) >= 1e9 ? (v/1e9).toFixed(2)
 const pct = v => v == null ? '—' : (v*100).toFixed(1)+'%';
 const elapsed = v => v == null ? '—' : v >= 3600 ? (v/3600).toFixed(1)+' h' : v >= 60 ? (v/60).toFixed(1)+' min' : v.toFixed(1)+' s';
 const arrow = '<span aria-hidden="true">↗</span>';
-const colors = {'kinex-vla-autonomous':'#367d96','kinex-vla-input-guided':'#96703b','standalone-oft-all140k':'#547a36','standalone-vlact-clean':'#a75f7f','standalone-vlact-all':'#bd733b','standalone-official':'#39819c','standalone':'#39819c','kinex_policy':'#756ee4','kinex':'#27847a','codex-astra-spectator':'#a76a34','codex-astra':'#39819c','kinex-astra':'#756ee4','cc-opus':'#b48566','kinex-opus':'#958bc8','cc-opus-vertex-high':'#c9875a','cc-opus-vertex-xhigh':'#8c5a3a','kinex-opus-vertex-high':'#5b8bd8','kinex-opus-vertex-xhigh':'#3a5ba6','cc-opus-vertex-high-run2':'#e0a37a','cc-opus-vertex-xhigh-run2':'#a8704a','kinex-opus-vertex-high-run2':'#86aae6','kinex-opus-vertex-xhigh-run2':'#5876c0'};
+const colors = {'kinex-vla-input-required':'#b35349','kinex-vla-autonomous':'#367d96','kinex-vla-input-guided':'#96703b','standalone-oft-all140k':'#547a36','standalone-vlact-clean':'#a75f7f','standalone-vlact-all':'#bd733b','standalone-official':'#39819c','standalone':'#39819c','kinex_policy':'#756ee4','kinex':'#27847a','codex-astra-spectator':'#a76a34','codex-astra':'#39819c','kinex-astra':'#756ee4','cc-opus':'#b48566','kinex-opus':'#958bc8','cc-opus-vertex-high':'#c9875a','cc-opus-vertex-xhigh':'#8c5a3a','kinex-opus-vertex-high':'#5b8bd8','kinex-opus-vertex-xhigh':'#3a5ba6','cc-opus-vertex-high-run2':'#e0a37a','cc-opus-vertex-xhigh-run2':'#a8704a','kinex-opus-vertex-high-run2':'#86aae6','kinex-opus-vertex-xhigh-run2':'#5876c0'};
 let data, epoch = 0, current = {}, matrixMetric = 'success';
 let filters = {query:'',family:'',status:'',variant:'standalone-vlact-clean',sort:'catalog'};
 let sessionState = {filter:'all',query:'',count:40,view:'timeline'};
@@ -110,7 +110,7 @@ function opusPilotProgress(){
  return `<section class="panel" style="padding:18px 24px;margin-bottom:24px" aria-label="Claude Code campaign"><strong>Claude Code · Opus 5.5 / high</strong><p>${number(n.finished||0)} / ${number(c.planned_episodes)} episodes completed · ${number(n.running||0)} running · ${number(n.queued||0)} pending${n.needs_review?' · '+number(n.needs_review)+' under review':''}${n.interrupted?' · '+number(n.interrupted)+' interrupted':''}.</p><p class="source-note">${c.quota_waiting?'Waiting for model-service quota recovery · ':''}${number(c.published_episodes)} episode records published · <a href="${esc(c.status_url)}" target="_blank" rel="noopener">Results and protocol ↗</a></p></section>`;
 }
 function methodology() {
- return `<details class="panel methodology" id="methodology"><summary><span><span class="eyebrow">Reading the Hard benchmark</span><strong>Protocol, metrics & provenance</strong></span><span class="summary-plus">+</span></summary><div class="method-grid"><div><h3>Full-suite baselines and paired 10-task study</h3><p>RoboTwin 2.0 Hard, ALOHA AgileX, demo_randomized. The five original conditions cover 50 tasks each. Kinex + VLA autonomous and input-guided cover the first 10 RLE tasks each; completion and denominators are shown separately. Successes and valid failures are both retained; no completed, protocol-valid agent outcome was retried. This is RoboTwin 2.0 Hard, not RoboTwin 2.0-Plus.</p></div><div><h3>Instruction protocols</h3><p>Pure Kinex and both new Kinex + VLA conditions use the revised RLE Hard templates and public scene bindings. VLA checkpoints and archived Kinex results retain original upstream unseen instructions. Each episode records the exact measured instruction and its authorship policy.</p></div><div><h3>Checkpoint identity</h3><p>Base 40k: StarVLA/Qwen3-VL-OFT-Robotwin2. VLAct Clean 50k: StarVLA/VLAct_Qwen3OFT_Robotwin_Finetune. VLAct All 100k: StarVLA/VLAct_Qwen3OFT_Robotwin_all_Finetune. Non-VLAct All 140k: StarVLA/Qwen3-VL-OFT-RoboTwin2-All, trained on 27,500 clean and randomized demonstrations. Full revisions and weight checksums are linked below. Pure Kinex uses GPT-6 Astra / high. The two new Kinex + VLA conditions add the same All 140k checkpoint; only input-guided appends optional context/target suggestions to the inference description. Task prompts are identical, JSON is optional, and zero VLA calls are valid.</p></div><div><h3>Execution and seeds</h3><p>Standalone VLA uses official expert admission from scene seed 100000 and official take_action with full predicted chunks. Current pure Kinex uses rosbridge at 25 Hz and the authored RLE manifest seeds and overrides, frozen before model use. No seed substitution or expert-success filtering is performed during this campaign. Seeds, admission rules and physical durations are not matched across the interfaces; this is not a paired causal comparison. Per-episode seeds and budgets are retained. Two preliminary guided attempts were native successes but are excluded because a profile serialization defect corrupted their interface; their diagnostics are retained in the protocol report. Two further attempts were interrupted by provider quota exhaustion (HTTP 429) and restarted with unchanged seeds and budgets after quota recovery; both interruption records are preserved. The new 10-task pair shares RLE instructions, authored seeds, budgets and the nominal 60 ms data clock resampled to 40 ms controls; prefixes and other control choices belong to the agent. Historical standalone results use native TOPP and are not an execution-matched baseline for this pair.</p></div><div><h3>Initialization provenance</h3><p>Five infrastructure startup attempts produced no completed model response and are excluded from the original 200 valid outcomes. For hanging_mug, a minimal runtime repair retains native language bindings if the expert path fails before finishing. Selected seed 0, task physics and the native verifier are preserved.</p></div><div><h3>Usage and costs</h3><p>Estimated API-equivalent costs use recorded Pi session values. Actual account charges and GPU costs are not measured. Standalone VLA has zero language-agent API calls, not zero compute cost.</p></div></div><div class="method-links"><a href="${esc(evidenceURL('research/agent-protocols-20261105/REPORT.md'))}">Kinex + VLA protocol study ↗</a><a href="${esc(evidenceURL('research/oft-all140k-20261103/REPORT.md'))}">All 140k results & validation ↗</a><a href="${esc(evidenceURL('research/oft-all140k-20261103/protocol.json'))}">All 140k protocol & checkpoint ↗</a><a href="${esc(resultURL('sources.json'))}" target="_blank">Data sources ↗</a><a href="${esc(evidenceURL('research/robotwin-hard-20261101/REPORT.md'))}">Report ↗</a><a href="${esc(evidenceURL('research/robotwin-hard-20261101/protocol.json'))}">Protocol & checkpoints ↗</a><a href="${esc(evidenceURL('research/robotwin-hard-20261101/execution-audit.json'))}">200-episode audit ↗</a><a href="../index.html#overview">Retained Easy results ↗</a><button class="text-button" data-export="all">Download comparison CSV ↓</button></div></details>`;
+ return `<details class="panel methodology" id="methodology"><summary><span><span class="eyebrow">Reading the Hard benchmark</span><strong>Protocol, metrics & provenance</strong></span><span class="summary-plus">+</span></summary><div class="method-grid"><div><h3>Full-suite baselines and paired 10-task study</h3><p>RoboTwin 2.0 Hard, ALOHA AgileX, demo_randomized. The five original conditions cover 50 tasks each. Kinex + VLA autonomous, input-guided and input-required cover the first 10 RLE tasks each; completion and denominators are shown separately. Successes and valid failures are both retained; no completed, protocol-valid agent outcome was retried. This is RoboTwin 2.0 Hard, not RoboTwin 2.0-Plus.</p></div><div><h3>Instruction protocols</h3><p>Pure Kinex and all three Kinex + VLA conditions use the revised RLE Hard templates and public scene bindings. VLA checkpoints and archived Kinex results retain original upstream unseen instructions. Each episode records the exact measured instruction and its authorship policy.</p></div><div><h3>Checkpoint identity</h3><p>Base 40k: StarVLA/Qwen3-VL-OFT-Robotwin2. VLAct Clean 50k: StarVLA/VLAct_Qwen3OFT_Robotwin_Finetune. VLAct All 100k: StarVLA/VLAct_Qwen3OFT_Robotwin_all_Finetune. Non-VLAct All 140k: StarVLA/Qwen3-VL-OFT-RoboTwin2-All, trained on 27,500 clean and randomized demonstrations. Full revisions and weight checksums are linked below. Pure Kinex uses GPT-6 Astra / high. The three Kinex + VLA protocols use the same All 140k checkpoint. Autonomous leaves input selection unguided; input-guided adds optional context/target suggestions; input-required requires five JSON fields (goal, context, feedback, constraints, target), allowing null, and encourages useful observations, spatial reasoning and calculations. Task prompts are identical and zero VLA calls are valid. Required JSON is validated before inference and remains language text.</p></div><div><h3>Execution and seeds</h3><p>Standalone VLA uses official expert admission from scene seed 100000 and official take_action with full predicted chunks. Current pure Kinex uses rosbridge at 25 Hz and the authored RLE manifest seeds and overrides, frozen before model use. No seed substitution or expert-success filtering is performed during this campaign. Seeds, admission rules and physical durations are not matched across the interfaces; this is not a paired causal comparison. Per-episode seeds and budgets are retained. Two preliminary guided attempts were native successes but are excluded because a profile serialization defect corrupted their interface; their diagnostics are retained in the protocol report. Two further attempts were interrupted by provider quota exhaustion (HTTP 429) and restarted with unchanged seeds and budgets after quota recovery; both interruption records are preserved. The three 10-task protocols share RLE instructions, authored seeds, budgets and the nominal 60 ms data clock resampled to 40 ms controls; prefixes and other control choices belong to the agent. Historical standalone results use native TOPP and are not an execution-matched baseline for this comparison.</p></div><div><h3>Initialization provenance</h3><p>Five infrastructure startup attempts produced no completed model response and are excluded from the original 200 valid outcomes. For hanging_mug, a minimal runtime repair retains native language bindings if the expert path fails before finishing. Selected seed 0, task physics and the native verifier are preserved.</p></div><div><h3>Usage and costs</h3><p>Estimated API-equivalent costs use recorded Pi session values. Actual account charges and GPU costs are not measured. Standalone VLA has zero language-agent API calls, not zero compute cost.</p></div></div><div class="method-links"><a href="${esc(evidenceURL('research/input-required-20261105/REPORT.md'))}">Input-required results & protocol ↗</a><a href="${esc(evidenceURL('research/agent-protocols-20261105/REPORT.md'))}">Kinex + VLA protocol study ↗</a><a href="${esc(evidenceURL('research/oft-all140k-20261103/REPORT.md'))}">All 140k results & validation ↗</a><a href="${esc(evidenceURL('research/oft-all140k-20261103/protocol.json'))}">All 140k protocol & checkpoint ↗</a><a href="${esc(resultURL('sources.json'))}" target="_blank">Data sources ↗</a><a href="${esc(evidenceURL('research/robotwin-hard-20261101/REPORT.md'))}">Report ↗</a><a href="${esc(evidenceURL('research/robotwin-hard-20261101/protocol.json'))}">Protocol & checkpoints ↗</a><a href="${esc(evidenceURL('research/robotwin-hard-20261101/execution-audit.json'))}">200-episode audit ↗</a><a href="../index.html#overview">Retained Easy results ↗</a><button class="text-button" data-export="all">Download comparison CSV ↓</button></div></details>`;
 }
 function taskBrowser(variant=null) {
   return `<section class="task-browser" id="tasks"><div class="section-heading bare"><div><div class="eyebrow">${variant?'Episode index':'Browse the benchmark'}</div><h2>Explore tasks <span class="heading-count">${plannedTasks(variant).length}</span></h2></div><button class="button secondary" data-export="${variant||'all'}">Export CSV ↓</button></div><div class="panel"><div class="filters"><label class="search-field"><span aria-hidden="true">⌕</span><input id="task-search" type="search" aria-label="Search tasks" placeholder="Search task name, instruction or ID" value="${esc(filters.query)}"></label><select id="task-family" aria-label="Environment"><option value="">All environments</option>${data.families.map(f=>`<option value="${f.id}" ${filters.family===f.id?'selected':''}>${f.name}</option>`).join('')}</select>${variant?'':`<select id="task-variant" aria-label="Agent for outcome filter">${data.variants.map(v=>`<option value="${v.id}" ${filters.variant===v.id?'selected':''}>${v.label||v.agent} · ${v.model}</option>`).join('')}</select>`}<select id="task-status" aria-label="Outcome"><option value="">All outcomes</option>${['pass','fail','pending'].map(s=>`<option value="${s}" ${filters.status===s?'selected':''}>${s[0].toUpperCase()+s.slice(1)}</option>`).join('')}</select><select id="task-sort" aria-label="Sort tasks"><option value="catalog" ${filters.sort==='catalog'?'selected':''}>Catalog order</option><option value="tokens" ${filters.sort==='tokens'?'selected':''}>Most fresh input tokens</option><option value="cost" ${filters.sort==='cost'?'selected':''}>Highest cost</option><option value="name" ${filters.sort==='name'?'selected':''}>Task name</option></select></div><div class="table-scroll"><table class="task-table ${variant?'single-variant':''}"><thead><tr><th>Task</th>${variant?'<th>Native result</th><th>Fresh input<small>Excludes read and write</small></th><th>Cache read</th><th>Cache write</th><th>Cache hit</th><th>Output</th><th>Total cost<small>Estimated USD</small></th><th>Action steps</th>':data.variants.map(v=>`<th class="${v.id===filters.variant?'focus-column':''}">${v.label||v.agent}<small>${v.model} · ${v.effort}</small><small>Native result · Estimated USD</small></th>`).join('')}</tr></thead><tbody id="task-rows"></tbody></table></div><div class="table-footer"><span id="task-count" aria-live="polite"></span><span id="filter-context"></span><button class="text-button" id="reset-filters">Reset filters</button></div></div></section>`;

hard/data-source.json

@@ -1,23 +1,23 @@
 {
   "schema": "programvla/dataset-source/1",
   "dataset": "RLE-Bench/programmable-vla",
-  "revision": "709e8b025a79abb5ec0146a549ebc2f3f985e276",
-  "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/709e8b025a79abb5ec0146a549ebc2f3f985e276/",
+  "revision": "5f5be7ac6bf0fec7b4cea054b903c7eeadfa61e3",
+  "evidence_root": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/5f5be7ac6bf0fec7b4cea054b903c7eeadfa61e3/",
   "files": {
     "data.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/709e8b025a79abb5ec0146a549ebc2f3f985e276/research/agent-protocols-20261105/panels/hard/data.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/5f5be7ac6bf0fec7b4cea054b903c7eeadfa61e3/research/input-required-20261105/panels/hard/data.json"
     },
     "cost-data.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/709e8b025a79abb5ec0146a549ebc2f3f985e276/research/agent-protocols-20261105/panels/hard/cost-data.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/5f5be7ac6bf0fec7b4cea054b903c7eeadfa61e3/research/input-required-20261105/panels/hard/cost-data.json"
     },
     "measured-instructions.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/709e8b025a79abb5ec0146a549ebc2f3f985e276/research/agent-protocols-20261105/panels/hard/measured-instructions.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/5f5be7ac6bf0fec7b4cea054b903c7eeadfa61e3/research/input-required-20261105/panels/hard/measured-instructions.json"
     },
     "sources.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/709e8b025a79abb5ec0146a549ebc2f3f985e276/research/agent-protocols-20261105/panels/hard/sources.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/5f5be7ac6bf0fec7b4cea054b903c7eeadfa61e3/research/input-required-20261105/panels/hard/sources.json"
     },
     "instruction-audit.json": {
-      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/709e8b025a79abb5ec0146a549ebc2f3f985e276/research/agent-protocols-20261105/panels/hard/instruction-audit.json"
+      "url": "https://huggingface.co/datasets/RLE-Bench/programmable-vla/resolve/5f5be7ac6bf0fec7b4cea054b903c7eeadfa61e3/research/input-required-20261105/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

@@ -10,7 +10,7 @@
 <link rel="stylesheet" href="style.css?v=bd1a59147e1d">
 <script src="usage-metrics.js?v=330e92f8eb96" defer></script>
 <script src="../instruction-audit.js?v=7b5e9a418dec" defer></script>
-<script src="app.js?v=0e5758b9a159" defer></script>
+<script src="app.js?v=a21cb45bd950" defer></script>
 <link rel="stylesheet" href="policy.css">
 <link rel="stylesheet" href="../instruction-audit.css?v=43163fc879ed">
 </head>
@@ -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/709e8b025a79abb5ec0146a549ebc2f3f985e276/research/agent-protocols-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/709e8b025a79abb5ec0146a549ebc2f3f985e276/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/5f5be7ac6bf0fec7b4cea054b903c7eeadfa61e3/research/input-required-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/5f5be7ac6bf0fec7b4cea054b903c7eeadfa61e3/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/709e8b025a79abb5ec0146a549ebc2f3f985e276/research/agent-protocols-20261105/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/5f5be7ac6bf0fec7b4cea054b903c7eeadfa61e3/research/input-required-20261105/panels/hard/data.json">Download the complete results index.</a></p></noscript>
 </body>
 </html>

manifest.json

@@ -99,8 +99,8 @@
       "sha256": "a53108594a23b740fbb08623f6fffdda1d73608b552988a9ffda9f0944ae66a1"
     },
     "hard/app.js": {
-      "bytes": 92796,
-      "sha256": "0e5758b9a15983e4c5e0cfc30d3d425f48a218ebe1f5b6b2f2147ceac628b350"
+      "bytes": 93211,
+      "sha256": "a21cb45bd9509c2f8d092b2c100005ff949085e87d1f6b53ef747c6903c92093"
     },
     "hard/icon.svg": {
       "bytes": 725,
@@ -111,8 +111,8 @@
       "sha256": "330e92f8eb9670cb506f2909a2a47ee8f0bd569199898df3bfa044239ae64161"
     },
     "hard/index.html": {
-      "bytes": 3642,
-      "sha256": "3584809bcaa6ab1b46a746e87568fa497025d44281789293d0e422779991dba8"
+      "bytes": 3640,
+      "sha256": "830afb6073dff835e9e89431db64ff64ca078a03d871957ecb1eb2f767bbab8c"
     },
     "hard/policy.css": {
       "bytes": 1067,
@@ -123,8 +123,8 @@
       "sha256": "bd1a59147e1d5e6c4fc5abd0871fb7b2e5e282a9ee3d15ca4df8a219509af69c"
     },
     "hard/data-source.json": {
-      "bytes": 1617,
-      "sha256": "6b93f6986803a39df7146b1220b68d5d63d36a2153c3062a767c0bbf65ca6f18"
+      "bytes": 1612,
+      "sha256": "3071d07b6bb1c35b9e3c022d52557354fdc11e218c799652432ba64f02c766eb"
     },
     "plus/app.js": {
       "bytes": 93565,
@@ -269,5 +269,11 @@
     "revision": "709e8b025a79abb5ec0146a549ebc2f3f985e276",
     "prefix": "research/agent-protocols-20261105",
     "complete": true
+  },
+  "input_required_dataset": {
+    "repo": "RLE-Bench/programmable-vla",
+    "revision": "5f5be7ac6bf0fec7b4cea054b903c7eeadfa61e3",
+    "prefix": "research/input-required-20261105",
+    "complete": false
   }
 }