Publish codex SIMPLE seed-0 evaluation evidence

README.md

@@ -20,7 +20,7 @@ pinned: false
 | RoboDojo | 42 / 42 | 31 / 42 |
 | SIMPLE G1 | 8 / 12 | 2 / 8 |
 
-SIMPLE uses GPT-6 Astra with high reasoning effort and default service tier, one fresh seed-0 episode per task, 10000 native control intervals at 50 Hz, stepped MuJoCo physics with Isaac rendering, domain randomization level 0, arm gravity compensation, stop-on-success, recording and an 8-hour wall-clock timeout. Request retries remain within the same session; whole episodes are never retried automatically.
+SIMPLE uses GPT-6 Astra with high reasoning effort and default service tier, one fresh seed-0 episode per task, 10000 native control intervals for retained slots 01-08 and 15000 for restarted slots 09-12, at 50 Hz, stepped MuJoCo physics with Isaac rendering, domain randomization level 0, arm gravity compensation, stop-on-success, recording and an 8-hour wall-clock timeout. Request retries remain within the same session; whole episodes are never retried automatically.
 
 Native task instructions and success predicates are unchanged. Full local source snapshots, package hashes and image digests identify the measured runtime. Existing episodes retain their original provenance. Original stereo observations are 640 by 360 pixels per view; displayed videos concatenate both views at 4x speed and do not claim higher spatial resolution, exact wall-time alignment, replay, or a new simulation run. Valid native failures remain benchmark results. Single-seed results do not estimate multi-seed reliability.
 

REPORT.md

@@ -10,7 +10,7 @@
 | RoboDojo | 42 / 42 | 31 / 42 |
 | SIMPLE G1 | 8 / 12 | 2 / 8 |
 
-SIMPLE uses GPT-6 Astra with high reasoning effort and default service tier, one fresh seed-0 episode per task, 10000 native control intervals at 50 Hz, stepped MuJoCo physics with Isaac rendering, domain randomization level 0, arm gravity compensation, stop-on-success, recording and an 8-hour wall-clock timeout. Request retries remain within the same session; whole episodes are never retried automatically.
+SIMPLE uses GPT-6 Astra with high reasoning effort and default service tier, one fresh seed-0 episode per task, 10000 native control intervals for retained slots 01-08 and 15000 for restarted slots 09-12, at 50 Hz, stepped MuJoCo physics with Isaac rendering, domain randomization level 0, arm gravity compensation, stop-on-success, recording and an 8-hour wall-clock timeout. Request retries remain within the same session; whole episodes are never retried automatically.
 
 Native task instructions and success predicates are unchanged. Full local source snapshots, package hashes and image digests identify the measured runtime. Existing episodes retain their original provenance. Original stereo observations are 640 by 360 pixels per view; displayed videos concatenate both views at 4x speed and do not claim higher spatial resolution, exact wall-time alignment, replay, or a new simulation run. Valid native failures remain benchmark results. Single-seed results do not estimate multi-seed reliability.
 

catalog/task06/09-open-oven/task.yaml

@@ -10,3 +10,4 @@ backend_kwargs:
   sim_mode: mujoco_isaac
   dr_level: 0
   arm_gravity_compensation: true
+  max_steps: 15000

catalog/task06/10-open-faucet/task.yaml

@@ -10,3 +10,4 @@ backend_kwargs:
   sim_mode: mujoco_isaac
   dr_level: 0
   arm_gravity_compensation: true
+  max_steps: 15000

catalog/task06/11-push-office-chair/task.yaml

@@ -10,3 +10,4 @@ backend_kwargs:
   sim_mode: mujoco_isaac
   dr_level: 0
   arm_gravity_compensation: true
+  max_steps: 15000

catalog/task06/12-open-trash-can/task.yaml

@@ -10,3 +10,4 @@ backend_kwargs:
   sim_mode: mujoco_isaac
   dr_level: 0
   arm_gravity_compensation: true
+  max_steps: 15000

comparison.json

@@ -3181,6 +3181,7 @@
         "kinex_success": true,
         "codex_success": true,
         "same_instruction": true,
+        "same_budget": true,
         "same_roboenv_source": true,
         "kinex_steps": 2001,
         "codex_steps": 1647,
@@ -3265,6 +3266,7 @@
         "kinex_success": false,
         "codex_success": false,
         "same_instruction": true,
+        "same_budget": true,
         "same_roboenv_source": true,
         "kinex_steps": 8574,
         "codex_steps": 1283,
@@ -3349,6 +3351,7 @@
         "kinex_success": true,
         "codex_success": false,
         "same_instruction": true,
+        "same_budget": true,
         "same_roboenv_source": true,
         "kinex_steps": 1162,
         "codex_steps": 9768,
@@ -3433,6 +3436,7 @@
         "kinex_success": true,
         "codex_success": false,
         "same_instruction": true,
+        "same_budget": true,
         "same_roboenv_source": true,
         "kinex_steps": 5252,
         "codex_steps": 8560,
@@ -3517,6 +3521,7 @@
         "kinex_success": true,
         "codex_success": false,
         "same_instruction": true,
+        "same_budget": true,
         "same_roboenv_source": true,
         "kinex_steps": 1700,
         "codex_steps": 9150,

data.json

@@ -6,7 +6,7 @@
   "benchmark_complete": false,
   "edition": "codex-simple-astra-high-seed0",
   "created_at": "2026-10-09T00:09:42.989838+00:00",
-  "updated_at": "2026-10-10T01:24:39.237016+00:00",
+  "updated_at": "2026-10-10T01:36:44.778308+00:00",
   "model": "gpt-6-astra",
   "effort": "high",
   "seed": 0,
@@ -112,7 +112,21 @@
         "success_rate": 0.25,
         "usage_complete": 8,
         "control_frequency_hz": 50,
-        "max_control_steps": 10000,
+        "max_control_steps": null,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "preflight_results": 0,
         "formal_results": 8,
         "modified_results": 0,
@@ -124,17 +138,23 @@
     ],
     "interrupted_attempts": 4,
     "usage_incomplete_tasks": [],
-    "execution_incomplete_tasks": [],
+    "execution_incomplete_tasks": [
+      "task06/09",
+      "task06/10",
+      "task06/11"
+    ],
     "deferred_tasks": [],
     "new_evaluations": 8,
     "progress": {
       "finished": 80,
-      "running": 3,
-      "queued": 1,
+      "running": 0,
+      "queued": 0,
       "needs_review": 0,
-      "interrupted": 0,
+      "interrupted": 3,
       "native_successes": 51,
-      "native_failures": 29
+      "native_failures": 29,
+      "not_started": 1,
+      "stopped_by_user": true
     },
     "simple_campaign": {
       "planned": 12,
@@ -239,7 +259,21 @@
       "success_rate": 0.25,
       "usage_complete": 8,
       "control_frequency_hz": 50,
-      "max_control_steps": 10000,
+      "max_control_steps": null,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "preflight_results": 0,
       "formal_results": 8,
       "modified_results": 0,
@@ -6312,6 +6346,20 @@
         "seed": 0,
         "control_frequency_hz": 50,
         "max_control_steps": 10000,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "timeout_s": 28800,
         "mode": "stepped",
         "instruction_policy": "original_native"
@@ -6342,6 +6390,20 @@
         "seed": 0,
         "control_frequency_hz": 50,
         "max_control_steps": 10000,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "timeout_s": 28800,
         "mode": "stepped",
         "instruction_policy": "original_native"
@@ -6372,6 +6434,20 @@
         "seed": 0,
         "control_frequency_hz": 50,
         "max_control_steps": 10000,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "timeout_s": 28800,
         "mode": "stepped",
         "instruction_policy": "original_native"
@@ -6402,6 +6478,20 @@
         "seed": 0,
         "control_frequency_hz": 50,
         "max_control_steps": 10000,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "timeout_s": 28800,
         "mode": "stepped",
         "instruction_policy": "original_native"
@@ -6432,6 +6522,20 @@
         "seed": 0,
         "control_frequency_hz": 50,
         "max_control_steps": 10000,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "timeout_s": 28800,
         "mode": "stepped",
         "instruction_policy": "original_native"
@@ -6462,6 +6566,20 @@
         "seed": 0,
         "control_frequency_hz": 50,
         "max_control_steps": 10000,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "timeout_s": 28800,
         "mode": "stepped",
         "instruction_policy": "original_native"
@@ -6492,6 +6610,20 @@
         "seed": 0,
         "control_frequency_hz": 50,
         "max_control_steps": 10000,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "timeout_s": 28800,
         "mode": "stepped",
         "instruction_policy": "original_native"
@@ -6522,6 +6654,20 @@
         "seed": 0,
         "control_frequency_hz": 50,
         "max_control_steps": 10000,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "timeout_s": 28800,
         "mode": "stepped",
         "instruction_policy": "original_native"
@@ -6545,13 +6691,27 @@
       "instruction_source": "Unchanged native SIMPLE instruction for the effective default task configuration.",
       "status": "pending",
       "episode_id": null,
-      "run_status": "running",
-      "status_note": "Authorized episode is queued, running, or awaiting evidence review.",
+      "run_status": "interrupted",
+      "status_note": "The prior attempt was interrupted at the user request; no valid native verdict. Execution remains stopped. Retained separately from native failures.",
       "planned_protocol": {
         "episodes": 1,
         "seed": 0,
         "control_frequency_hz": 50,
-        "max_control_steps": 10000,
+        "max_control_steps": 15000,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "timeout_s": 28800,
         "mode": "stepped",
         "instruction_policy": "original_native"
@@ -6575,13 +6735,27 @@
       "instruction_source": "Unchanged native SIMPLE instruction for the effective default task configuration.",
       "status": "pending",
       "episode_id": null,
-      "run_status": "running",
-      "status_note": "Authorized episode is queued, running, or awaiting evidence review.",
+      "run_status": "interrupted",
+      "status_note": "The prior attempt was interrupted at the user request; no valid native verdict. Execution remains stopped. Retained separately from native failures.",
       "planned_protocol": {
         "episodes": 1,
         "seed": 0,
         "control_frequency_hz": 50,
-        "max_control_steps": 10000,
+        "max_control_steps": 15000,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "timeout_s": 28800,
         "mode": "stepped",
         "instruction_policy": "original_native"
@@ -6605,13 +6779,27 @@
       "instruction_source": "Unchanged native SIMPLE instruction for the effective default task configuration.",
       "status": "pending",
       "episode_id": null,
-      "run_status": "running",
-      "status_note": "Authorized episode is queued, running, or awaiting evidence review.",
+      "run_status": "interrupted",
+      "status_note": "The prior attempt was interrupted at the user request; no valid native verdict. Execution remains stopped. Retained separately from native failures.",
       "planned_protocol": {
         "episodes": 1,
         "seed": 0,
         "control_frequency_hz": 50,
-        "max_control_steps": 10000,
+        "max_control_steps": 15000,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "timeout_s": 28800,
         "mode": "stepped",
         "instruction_policy": "original_native"
@@ -6635,13 +6823,27 @@
       "instruction_source": "Unchanged native SIMPLE instruction for the effective default task configuration.",
       "status": "pending",
       "episode_id": null,
-      "run_status": "queued",
-      "status_note": "Authorized episode is queued, running, or awaiting evidence review.",
+      "run_status": "not_started",
+      "status_note": "Stopped at the user request before this task started.",
       "planned_protocol": {
         "episodes": 1,
         "seed": 0,
         "control_frequency_hz": 50,
-        "max_control_steps": 10000,
+        "max_control_steps": 15000,
+        "max_control_steps_by_task": {
+          "task06/01": 10000,
+          "task06/02": 10000,
+          "task06/03": 10000,
+          "task06/04": 10000,
+          "task06/05": 10000,
+          "task06/06": 10000,
+          "task06/07": 10000,
+          "task06/08": 10000,
+          "task06/09": 15000,
+          "task06/10": 15000,
+          "task06/11": 15000,
+          "task06/12": 15000
+        },
         "timeout_s": 28800,
         "mode": "stepped",
         "instruction_policy": "original_native"
@@ -27285,5 +27487,14 @@
   "instruction_review": {
     "policy": "Lift pot uses native RoboTwin TCP frames after the RoboEnv correction, with the existing reviewed instruction, unchanged native verifier, seed 0, 7500 action frames at 25 Hz, and one fresh stock Codex 0.160.0 / GPT-6 Astra high episode. Other results retain their historical runtime and protocol."
   },
-  "authorized_selection_complete": false
+  "authorized_selection_complete": false,
+  "execution_stop": {
+    "time": "2026-10-10T01:32:09.008817+00:00",
+    "reason": "User confirmed the runs were stopped from another session and requested keeping them stopped; finish Space publication only.",
+    "dispatch": false,
+    "resume_or_replace_episodes": false,
+    "completed_results_retained": 16,
+    "interrupted_attempts_retained": 7,
+    "never_started": 1
+  }
 }

index.html

@@ -1,5 +1,5 @@
 <!doctype html>
 <html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1"><meta name="description" content="Codex robotics benchmark: original and revised instructions, seed 0, GPT-6 Astra high. Explore task videos, sessions and evidence across simulator families, including SIMPLE G1."><title>Codex Benchmark · RLE-Bench</title><link rel="icon" href="favicon.svg"><link rel="stylesheet" href="style.css"><script defer src="app.js"></script></head>
 <body><header class="hero"><div class="wrap"><div class="topbar"><a class="brand" href="#"><span class="brand-icon" aria-hidden="true">◇</span> RLE-Bench</a><nav aria-label="Primary"><a href="#tasks">Tasks</a><a href="https://huggingface.co/datasets/RLE-Bench/codex-benchmark" target="_blank" rel="noopener">Dataset ↗</a><a href="REPORT.md" target="_blank" rel="noopener">Report ↗</a></nav></div><div class="hero-content"><div class="eyebrow">ROBOTICS EVALUATION / STOCK CODEX</div><h1>Codex Benchmark</h1><p>GPT-6 Astra · high · seed 0 · original &amp; modified instructions</p><div class="hero-bottom"><span>84 selected tasks across 5 simulator families. Native success criteria.</span><a class="hero-button" href="#task04">Explore the results <span>↗</span></a></div></div></div></header>
-<main class="wrap"><div id="loading" role="status">Loading benchmark…</div><div id="browse" hidden><div class="edition"><span id="edition-count">Loading results…</span><span class="chip" id="edition-label">Benchmark results</span></div><section aria-labelledby="overview-heading"><div class="section-top"><h2 id="overview-heading">Task overview</h2><a href="summary.json" target="_blank" rel="noopener">Summary JSON ↗</a></div><div class="table-wrap"><table><thead><tr><th>Environment</th><th>Coverage</th><th>Native success</th><th>Input tokens</th><th>Output tokens</th><th>Usage coverage</th></tr></thead><tbody id="overview"></tbody></table></div><p class="footnote">Current recorded result per task · Seed 0 · Native success criteria. Each task shows its latest result and the instruction used for that recording. Rates include valid completed results only; pending tasks are excluded. No pooled score across environments. Input includes cached tokens; output includes reasoning tokens.</p></section><section id="failure-overview" lang="zh-CN" aria-label="失败原因"></section><p id="readiness-note" class="readiness-note" hidden></p><div id="tasks" class="task-controls"><nav id="family-nav" aria-label="Task families"></nav><div class="filters"><label class="search-label"><span class="sr-only">Search tasks</span><input id="search" type="search" placeholder="Search 84 tasks…"></label><label><span class="sr-only">Filter by status</span><select id="status-filter"><option value="all">All tasks</option><option value="completed">Results available</option><option value="pending">Pending</option></select></label><label><span class="sr-only">Filter by failure category</span><select id="failure-filter" aria-label="Filter by failure category"><option value="all">All failure categories</option></select></label><span id="filter-count" aria-live="polite"></span></div></div><div id="families"></div><p id="empty" hidden>No tasks match this search.</p><section class="protocol-box"><h2>The evaluation protocol</h2><div class="protocol-grid"><div><b>Instruction versions</b><p>Modified instructions are labeled, with changes highlighted. Each recording retains the instruction it used; native success predicates are unchanged.</p></div><div><b>Single seed</b><p>One independent episode, seed 0. GPT-6 Astra with high reasoning effort. Stock Codex CLI 0.160.0; each task starts with a fresh workspace and no inherited trajectory.</p></div><div><b>Native control budgets</b><p>RoboCasa and LIBERO: 6,000 steps at 20 Hz. RoboTwin and RoboDojo: 7,500 frames at 25 Hz. SIMPLE G1: 10,000 control frames at 50 Hz. Stepped simulation, with an eight-hour wall-clock limit.</p></div></div></section></div><article id="detail" hidden></article></main>
+<main class="wrap"><div id="loading" role="status">Loading benchmark…</div><div id="browse" hidden><div class="edition"><span id="edition-count">Loading results…</span><span class="chip" id="edition-label">Benchmark results</span></div><section aria-labelledby="overview-heading"><div class="section-top"><h2 id="overview-heading">Task overview</h2><a href="summary.json" target="_blank" rel="noopener">Summary JSON ↗</a></div><div class="table-wrap"><table><thead><tr><th>Environment</th><th>Coverage</th><th>Native success</th><th>Input tokens</th><th>Output tokens</th><th>Usage coverage</th></tr></thead><tbody id="overview"></tbody></table></div><p class="footnote">Current recorded result per task · Seed 0 · Native success criteria. Each task shows its latest result and the instruction used for that recording. Rates include valid completed results only; pending tasks are excluded. No pooled score across environments. Input includes cached tokens; output includes reasoning tokens.</p></section><section id="failure-overview" lang="zh-CN" aria-label="失败原因"></section><p id="readiness-note" class="readiness-note" hidden></p><div id="tasks" class="task-controls"><nav id="family-nav" aria-label="Task families"></nav><div class="filters"><label class="search-label"><span class="sr-only">Search tasks</span><input id="search" type="search" placeholder="Search 84 tasks…"></label><label><span class="sr-only">Filter by status</span><select id="status-filter"><option value="all">All tasks</option><option value="completed">Results available</option><option value="pending">Pending</option></select></label><label><span class="sr-only">Filter by failure category</span><select id="failure-filter" aria-label="Filter by failure category"><option value="all">All failure categories</option></select></label><span id="filter-count" aria-live="polite"></span></div></div><div id="families"></div><p id="empty" hidden>No tasks match this search.</p><section class="protocol-box"><h2>The evaluation protocol</h2><div class="protocol-grid"><div><b>Instruction versions</b><p>Modified instructions are labeled, with changes highlighted. Each recording retains the instruction it used; native success predicates are unchanged.</p></div><div><b>Single seed</b><p>One independent episode, seed 0. GPT-6 Astra with high reasoning effort. Stock Codex CLI 0.160.0; each task starts with a fresh workspace and no inherited trajectory.</p></div><div><b>Native control budgets</b><p>RoboCasa and LIBERO: 6,000 steps at 20 Hz. RoboTwin and RoboDojo: 7,500 frames at 25 Hz. SIMPLE G1: 10,000 or 15,000 control frames at 50 Hz; see each task protocol. Stepped simulation, with an eight-hour wall-clock limit.</p></div></div></section></div><article id="detail" hidden></article></main>
 <footer class="wrap"><span>RLE-Bench · Codex Benchmark</span><nav aria-label="Downloads"><a href="data.json">Data JSON</a><a href="episodes.csv">CSV</a><a href="DATA_FORMAT.md">Data format</a><a href="THIRD_PARTY_NOTICES.md">Attribution</a><a href="https://huggingface.co/datasets/RLE-Bench/codex-benchmark">Dataset ↗</a></nav></footer></body></html>

manifest.json

@@ -1,8 +1,8 @@
 {
   ".gitattributes": "51dec59a208c8656ce7d6614b7b547022f7a4720b1cdad6a20aeeda717ec090b",
   "DATA_FORMAT.md": "e2fd4f6b5c8be9d9e008db7d0c1f5d52b419d68328a1c86625c9f67c49b03403",
-  "README.md": "a69c662b67b32d762b71db8bfb458f33823a2ac65814cb13bf998f99c90cf53a",
-  "REPORT.md": "e8c55b5928c2ded32606f1552fd73634247d7921658cab0edbc320e0ffc84445",
+  "README.md": "0aaa99224afa8f13792b0b660b15ce64e0136462f24d6ea1c49a2aa385552b13",
+  "REPORT.md": "8c17bef9e5375c500e37443a8eb10ebebb98f2aae17d9438fef09583e80ec4bc",
   "THIRD_PARTY_NOTICES.md": "8aa8e3db100d7a570931c5d87f44f78705b42cf17e8147016b35e9aeddb06bba",
   "app.js": "eb013cc9d24382410953a1a8c81e446a6592a81b32887749d17bfc863936556b",
   "attempt-history.json": "8555f458c1dd362f5a07447342994fddf265ff23bbc40e9bd6f9984a892ddb4e",
@@ -14,24 +14,24 @@
   "catalog/task06/06-handover/task.yaml": "0886cf342aedacb9804788244ad06c3a21ba785785ba137a21752ac28d3e619a",
   "catalog/task06/07-pick-and-place-and-hug-container/task.yaml": "b3f1c7c8a55afcd246b79fb3b046a6dec56f3d98a377108b0ad5181c4414da58",
   "catalog/task06/08-close-door/task.yaml": "a0256216150b375a5ba091179411e6a15ea3a455e50e793a5e479bb1355028b3",
-  "catalog/task06/09-open-oven/task.yaml": "a012876d87c531b17adfa480a830c93a4d38a17b499ee2005f5f262bee60910f",
-  "catalog/task06/10-open-faucet/task.yaml": "6752776b0ebe55a237ee8cc08c4341cbb8561936afd1b63079e800f7add1f91c",
-  "catalog/task06/11-push-office-chair/task.yaml": "ab19bf9b7cec8992e2dcc1fb30ad9f6ce0f8343063b44777b2b68afc39d7f426",
-  "catalog/task06/12-open-trash-can/task.yaml": "8d8b4b0ec848f91283e73416d257f5b0f816ac4b872fccd10b213e74d953085c",
-  "comparison.json": "487d479f3d03e72efaf3c19c1e63f5894bcfea2954cb1cc46327c379b5315ad3",
-  "data.json": "ac940eeb5e78302389d387aff8cccde4e81ecdf4ccea4d6fbb7b54f43e1ccd51",
+  "catalog/task06/09-open-oven/task.yaml": "f7126ed4aa03c922f3b7fbef567be75d9f5080b9219c673b941fa2d03cabb91e",
+  "catalog/task06/10-open-faucet/task.yaml": "dcdd2228bfd8de298da36798856f5ff59b523c7104118103530eb7a641b52197",
+  "catalog/task06/11-push-office-chair/task.yaml": "0e2de1c50619b0c58fd939f58362dfc0630f34d4e19587fe4927a2c4e5c1d785",
+  "catalog/task06/12-open-trash-can/task.yaml": "e02833927892caa9c40ed193348aab1858e6ae6208c4c04892dec8eae4ad45f0",
+  "comparison.json": "55202006828502b083284dee5a70ad74a8af369afa34e258419ddb5fd2702c01",
+  "data.json": "6be970685887538176ef38cfdd0b01b3108316712bb02b588d4daae9070b054e",
   "episodes.csv": "7f4d5f46d65689ff303609a98ffa8a34ad875e7cc9b6018628fc368e87070ec9",
   "episodes.json": "41c1c467c7c36745454b1f1da54e2cbd25823af225581cfa168472878f4ea0f9",
   "failure-reviews.json": "c66a997c9ecd6f7f43f130a8a33cd64c7a5b2049033e9ccde653ee30e4796f23",
   "favicon.svg": "46063791218655f70c828ef71a1232a34fd38181da938338badec929ad226819",
-  "index.html": "524b3f71cc36152a08125212ad1c9ae2ca30601907b378f69cce4d34390d0ee3",
+  "index.html": "d29e3b0133b9af6378b8b3ab7a6bc04f8f985eff46a409078c4f8e6a521edfc2",
   "licenses/LIBERO-LICENSE.txt": "e2885fd30a08381b799c4a33385522b23d637b4051b8f9a7f9f2519944b68ff6",
   "licenses/RoboDojo-LICENSE.txt": "7794bb06af8fe5485ca912454ad1665ccd7846c45f9c2b1258658e480948cdbe",
   "licenses/RoboTwin-LICENSE.txt": "c695d421718e54e6f3a60858f0c601125c3ecc60c199332c15947360561e2a9f",
   "licenses/robocasa-LICENSE.txt": "5da18670b3f00c59847b1ded9c28dee59940d963b1e03b528b0108d9c5a09885",
   "licenses/robosuite-LICENSE.txt": "177978cbece0a4c454c2aaec5b3f145b39270814874c43109da9e829c39d9cba",
-  "protocol.json": "96be82ffa28eedefaa70bff4f7d4daa9e56f70fed407c1beac1ce8b725a00861",
+  "protocol.json": "205b330174d7930ec9d503ffd9f8d957716a5e72357902ba3352b09bd3824781",
   "style.css": "dd31b30951c220ebb82bc96224b5e640913945679e42b2e0a42e2c373a329e6c",
-  "summary.json": "dbb20c916a74b687e14aece840ffe67138889d90d3bd4b7d389593d497c9aede",
-  "task-index.json": "1f9542d87396e5e80c842c021f081077ab3f8cbace59c1bf61593b587d9020bc"
+  "summary.json": "d0c28a28c57588bc7cf5f244a20a82cd15d621fb3d390534daa72e24a45c1ec8",
+  "task-index.json": "e915eae26307309d95c71da154a5b8cad575b26768e4da97220a28c498a0c3b4"
 }

protocol.json

@@ -102,7 +102,21 @@
       "success_rate": 0.25,
       "usage_complete": 8,
       "control_frequency_hz": 50,
-      "max_control_steps": 10000,
+      "max_control_steps": null,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "preflight_results": 0,
       "formal_results": 8,
       "modified_results": 0,
@@ -152,11 +166,25 @@
       "episodes": 1,
       "seed": 0,
       "control_frequency_hz": 50,
-      "max_control_steps": 10000,
+      "max_control_steps": null,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native",
-      "max_steps": 10000,
+      "max_steps": null,
       "execution_mode": "stepped",
       "stop_on_success": true,
       "sim_mode": "mujoco_isaac",
@@ -173,5 +201,5 @@
   },
   "robotwin_harness": "Stock Codex CLI 0.160.0, gpt-6-astra, high, default service tier; current RoboEnv SDK/CLI; no Kinex agent runtime.",
   "native_tcp_repair_note": "Lift pot uses native RoboTwin TCP frames after the RoboEnv correction, with the existing reviewed instruction, unchanged native verifier, seed 0, 7500 action frames at 25 Hz, and one fresh stock Codex 0.160.0 / GPT-6 Astra high episode. Other results retain their historical runtime and protocol.",
-  "simple_comparability": "Kinex 0.10.3 and ordinary Codex CLI 0.160.0 share the frozen RoboEnv source, native task instructions, seed and protocol. One independent attempt per task; no inherited trajectories or resources. Wall time is not a controlled speed comparison."
+  "simple_comparability": "Kinex 0.10.3 and ordinary Codex CLI 0.160.0 share the frozen RoboEnv source, native task instructions, seed and protocol. Completed slots 01-08 retain 10000 steps; slots 09-12 use 15000 steps after an explicit user-requested restart. Each task pair shares its budget and measured runtime. Prior interrupted attempts are retained separately; fresh sessions inherit no trajectories or resources. Wall time is not a controlled speed comparison."
 }

publication-manifest.json

@@ -10,12 +10,12 @@
       "bytes": 1129
     },
     "README.md": {
-      "sha256": "a69c662b67b32d762b71db8bfb458f33823a2ac65814cb13bf998f99c90cf53a",
-      "bytes": 1544
+      "sha256": "0aaa99224afa8f13792b0b660b15ce64e0136462f24d6ea1c49a2aa385552b13",
+      "bytes": 1606
     },
     "REPORT.md": {
-      "sha256": "e8c55b5928c2ded32606f1552fd73634247d7921658cab0edbc320e0ffc84445",
-      "bytes": 1421
+      "sha256": "8c17bef9e5375c500e37443a8eb10ebebb98f2aae17d9438fef09583e80ec4bc",
+      "bytes": 1483
     },
     "THIRD_PARTY_NOTICES.md": {
       "sha256": "8aa8e3db100d7a570931c5d87f44f78705b42cf17e8147016b35e9aeddb06bba",
@@ -62,28 +62,28 @@
       "bytes": 308
     },
     "catalog/task06/09-open-oven/task.yaml": {
-      "sha256": "a012876d87c531b17adfa480a830c93a4d38a17b499ee2005f5f262bee60910f",
-      "bytes": 305
+      "sha256": "f7126ed4aa03c922f3b7fbef567be75d9f5080b9219c673b941fa2d03cabb91e",
+      "bytes": 324
     },
     "catalog/task06/10-open-faucet/task.yaml": {
-      "sha256": "6752776b0ebe55a237ee8cc08c4341cbb8561936afd1b63079e800f7add1f91c",
-      "bytes": 288
+      "sha256": "dcdd2228bfd8de298da36798856f5ff59b523c7104118103530eb7a641b52197",
+      "bytes": 307
     },
     "catalog/task06/11-push-office-chair/task.yaml": {
-      "sha256": "ab19bf9b7cec8992e2dcc1fb30ad9f6ce0f8343063b44777b2b68afc39d7f426",
-      "bytes": 341
+      "sha256": "0e2de1c50619b0c58fd939f58362dfc0630f34d4e19587fe4927a2c4e5c1d785",
+      "bytes": 360
     },
     "catalog/task06/12-open-trash-can/task.yaml": {
-      "sha256": "8d8b4b0ec848f91283e73416d257f5b0f816ac4b872fccd10b213e74d953085c",
-      "bytes": 319
+      "sha256": "e02833927892caa9c40ed193348aab1858e6ae6208c4c04892dec8eae4ad45f0",
+      "bytes": 338
     },
     "comparison.json": {
-      "sha256": "487d479f3d03e72efaf3c19c1e63f5894bcfea2954cb1cc46327c379b5315ad3",
-      "bytes": 134701
+      "sha256": "55202006828502b083284dee5a70ad74a8af369afa34e258419ddb5fd2702c01",
+      "bytes": 134846
     },
     "data.json": {
-      "sha256": "ac940eeb5e78302389d387aff8cccde4e81ecdf4ccea4d6fbb7b54f43e1ccd51",
-      "bytes": 1166026
+      "sha256": "6be970685887538176ef38cfdd0b01b3108316712bb02b588d4daae9070b054e",
+      "bytes": 1172466
     },
     "episodes.csv": {
       "sha256": "7f4d5f46d65689ff303609a98ffa8a34ad875e7cc9b6018628fc368e87070ec9",
@@ -102,8 +102,8 @@
       "bytes": 227
     },
     "index.html": {
-      "sha256": "524b3f71cc36152a08125212ad1c9ae2ca30601907b378f69cce4d34390d0ee3",
-      "bytes": 4417
+      "sha256": "d29e3b0133b9af6378b8b3ab7a6bc04f8f985eff46a409078c4f8e6a521edfc2",
+      "bytes": 4451
     },
     "licenses/LIBERO-LICENSE.txt": {
       "sha256": "e2885fd30a08381b799c4a33385522b23d637b4051b8f9a7f9f2519944b68ff6",
@@ -126,23 +126,23 @@
       "bytes": 1474
     },
     "protocol.json": {
-      "sha256": "96be82ffa28eedefaa70bff4f7d4daa9e56f70fed407c1beac1ce8b725a00861",
-      "bytes": 5438
+      "sha256": "205b330174d7930ec9d503ffd9f8d957716a5e72357902ba3352b09bd3824781",
+      "bytes": 6395
     },
     "style.css": {
       "sha256": "dd31b30951c220ebb82bc96224b5e640913945679e42b2e0a42e2c373a329e6c",
       "bytes": 16560
     },
     "summary.json": {
-      "sha256": "dbb20c916a74b687e14aece840ffe67138889d90d3bd4b7d389593d497c9aede",
-      "bytes": 3209
+      "sha256": "d0c28a28c57588bc7cf5f244a20a82cd15d621fb3d390534daa72e24a45c1ec8",
+      "bytes": 3693
     },
     "task-index.json": {
-      "sha256": "1f9542d87396e5e80c842c021f081077ab3f8cbace59c1bf61593b587d9020bc",
-      "bytes": 229780
+      "sha256": "e915eae26307309d95c71da154a5b8cad575b26768e4da97220a28c498a0c3b4",
+      "bytes": 234598
     },
     "manifest.json": {
-      "sha256": "f30322dfb31fe1049111c2bd2c2f026804ce81f9a7d025c7c90904e505fa5261",
+      "sha256": "bd84d8f0740ae7bc81fae5287e36017c3acede88fa10da71bcdd3ee698dbd26d",
       "bytes": 3481
     }
   }

summary.json

@@ -95,7 +95,21 @@
       "success_rate": 0.25,
       "usage_complete": 8,
       "control_frequency_hz": 50,
-      "max_control_steps": 10000,
+      "max_control_steps": null,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "preflight_results": 0,
       "formal_results": 8,
       "modified_results": 0,
@@ -107,17 +121,23 @@
   ],
   "interrupted_attempts": 4,
   "usage_incomplete_tasks": [],
-  "execution_incomplete_tasks": [],
+  "execution_incomplete_tasks": [
+    "task06/09",
+    "task06/10",
+    "task06/11"
+  ],
   "deferred_tasks": [],
   "new_evaluations": 8,
   "progress": {
     "finished": 80,
-    "running": 3,
-    "queued": 1,
+    "running": 0,
+    "queued": 0,
     "needs_review": 0,
-    "interrupted": 0,
+    "interrupted": 3,
     "native_successes": 51,
-    "native_failures": 29
+    "native_failures": 29,
+    "not_started": 1,
+    "stopped_by_user": true
   },
   "simple_campaign": {
     "planned": 12,

task-index.json

@@ -6061,6 +6061,20 @@
       "seed": 0,
       "control_frequency_hz": 50,
       "max_control_steps": 10000,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native"
@@ -6091,6 +6105,20 @@
       "seed": 0,
       "control_frequency_hz": 50,
       "max_control_steps": 10000,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native"
@@ -6121,6 +6149,20 @@
       "seed": 0,
       "control_frequency_hz": 50,
       "max_control_steps": 10000,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native"
@@ -6151,6 +6193,20 @@
       "seed": 0,
       "control_frequency_hz": 50,
       "max_control_steps": 10000,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native"
@@ -6181,6 +6237,20 @@
       "seed": 0,
       "control_frequency_hz": 50,
       "max_control_steps": 10000,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native"
@@ -6211,6 +6281,20 @@
       "seed": 0,
       "control_frequency_hz": 50,
       "max_control_steps": 10000,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native"
@@ -6241,6 +6325,20 @@
       "seed": 0,
       "control_frequency_hz": 50,
       "max_control_steps": 10000,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native"
@@ -6271,6 +6369,20 @@
       "seed": 0,
       "control_frequency_hz": 50,
       "max_control_steps": 10000,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native"
@@ -6294,13 +6406,27 @@
     "instruction_source": "Unchanged native SIMPLE instruction for the effective default task configuration.",
     "status": "pending",
     "episode_id": null,
-    "run_status": "running",
-    "status_note": "Authorized episode is queued, running, or awaiting evidence review.",
+    "run_status": "interrupted",
+    "status_note": "The prior attempt was interrupted at the user request; no valid native verdict. Execution remains stopped. Retained separately from native failures.",
     "planned_protocol": {
       "episodes": 1,
       "seed": 0,
       "control_frequency_hz": 50,
-      "max_control_steps": 10000,
+      "max_control_steps": 15000,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native"
@@ -6324,13 +6450,27 @@
     "instruction_source": "Unchanged native SIMPLE instruction for the effective default task configuration.",
     "status": "pending",
     "episode_id": null,
-    "run_status": "running",
-    "status_note": "Authorized episode is queued, running, or awaiting evidence review.",
+    "run_status": "interrupted",
+    "status_note": "The prior attempt was interrupted at the user request; no valid native verdict. Execution remains stopped. Retained separately from native failures.",
     "planned_protocol": {
       "episodes": 1,
       "seed": 0,
       "control_frequency_hz": 50,
-      "max_control_steps": 10000,
+      "max_control_steps": 15000,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native"
@@ -6354,13 +6494,27 @@
     "instruction_source": "Unchanged native SIMPLE instruction for the effective default task configuration.",
     "status": "pending",
     "episode_id": null,
-    "run_status": "running",
-    "status_note": "Authorized episode is queued, running, or awaiting evidence review.",
+    "run_status": "interrupted",
+    "status_note": "The prior attempt was interrupted at the user request; no valid native verdict. Execution remains stopped. Retained separately from native failures.",
     "planned_protocol": {
       "episodes": 1,
       "seed": 0,
       "control_frequency_hz": 50,
-      "max_control_steps": 10000,
+      "max_control_steps": 15000,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native"
@@ -6384,13 +6538,27 @@
     "instruction_source": "Unchanged native SIMPLE instruction for the effective default task configuration.",
     "status": "pending",
     "episode_id": null,
-    "run_status": "queued",
-    "status_note": "Authorized episode is queued, running, or awaiting evidence review.",
+    "run_status": "not_started",
+    "status_note": "Stopped at the user request before this task started.",
     "planned_protocol": {
       "episodes": 1,
       "seed": 0,
       "control_frequency_hz": 50,
-      "max_control_steps": 10000,
+      "max_control_steps": 15000,
+      "max_control_steps_by_task": {
+        "task06/01": 10000,
+        "task06/02": 10000,
+        "task06/03": 10000,
+        "task06/04": 10000,
+        "task06/05": 10000,
+        "task06/06": 10000,
+        "task06/07": 10000,
+        "task06/08": 10000,
+        "task06/09": 15000,
+        "task06/10": 15000,
+        "task06/11": 15000,
+        "task06/12": 15000
+      },
       "timeout_s": 28800,
       "mode": "stepped",
       "instruction_policy": "original_native"