{"items":[{"id":"7ad1c7d5-5793-4f5e-b0e0-53122141cd58","tournament_id":"66f9e369-ebeb-46c0-9849-c4dce40ce7d3","tournament_name":"task-leatherback-lidar v1.2","agent_id":"2f6213a3-848b-4352-bd9f-f1a2fa3d6417","miner_hotkey":"5GRA8BBQobvZokdqwwQpmceW6D5eA3p6jMnFGDaT5PG8WnAY","miner_uid":null,"task_name":"task-leatherback-lidar","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"public","score":null,"metadata":{},"summary":null,"log_file_path":null,"status":"in_progress","evaluated_at":"2026-07-12T12:15:37.035369"},{"id":"dd025dd4-b5fc-439f-9b34-0649d9cc298a","tournament_id":"66f9e369-ebeb-46c0-9849-c4dce40ce7d3","tournament_name":"task-leatherback-lidar v1.2","agent_id":"1d44cb23-c43c-4a51-a1f0-2bc8cbc12725","miner_hotkey":"5DyvfTEMLsYjn5oRH3LbSouJq9cK1CmDg8F7uTRGHkCFKtj2","miner_uid":null,"task_name":"task-leatherback-lidar","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"public","score":0.8209739146568157,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/leatherback-lidar-maze/eval_run_20260712_120059","category":"navigation","num_envs":150,"task_name":"Nepher-Leatherback-Lidar-Maze-Envhub-Play-v0","task_type":"navigation.leatherback","env_config":{},"env_scenes":[{"scene":0,"env_id":"leatherback-maze-v3"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"leatherback_lidar","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":450,"max_episode_time_s":30.0},"scenes":["leatherback-maze-v3:0"],"task_name":"Nepher-Leatherback-Lidar-Maze-Envhub-Play-v0","task_type":"navigation.leatherback","env_scenes":[{"scene":0,"env_id":"leatherback-maze-v3"}],"num_episodes":3,"elapsed_seconds":862.9157121181488,"scoring_version":"v2","max_episode_steps":450,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.8210 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 450\n  Successful: 431\n  Failed: 19\n  Timeouts: 1\n  Success Rate: 95.78%\n  Mean Completion Time: 11.17 s\n  Std Completion Time: 4.85 s\n  Mean Steps: 166.09\n  Std Steps: 75.09\n  Step dt: 0.0667 s\n\nLocomotion Quality:\n------------------------------------------------------------\n  Mean Speed: 2.204 m/s\n  Max Speed: 2.540 m/s\n  Speed Std: 0.644 m/s\n  Mean Vertical Speed: 0.030 m/s\n  Mean Angular Speed: 1.238 rad/s\n  Angular Speed Std: 0.637 rad/s\n  Mean Roll/Pitch Rate: 0.194 rad/s\n  Mean Lateral Speed: 0.198 m/s\n  Max Lateral Speed: 0.414 m/s\n  Walking (not running): NO — speed exceeds walking threshold\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Leatherback-Lidar-Maze-Envhub-Play-v0\n  Scoring Version: v2\n  Scenes: ['leatherback-maze-v3:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 862.92 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Excellent performance! High success rate and fast completion.\n\n============================================================","log_file_path":"evaluations/66f9e369-ebeb-46c0-9849-c4dce40ce7d3/1d44cb23-c43c-4a51-a1f0-2bc8cbc12725/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T12:15:25.497518"},{"id":"856d8f94-0cb1-438f-b29d-f9cfedfcce6e","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"9e84d275-937f-400c-af70-48a3a33c9d69","miner_hotkey":"5DPz76uobJLTfjaSiWkrBbsWktrLQ6s7kAHWm7Pb9B17zZRn","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"private","score":0.22617407407407406,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_115348","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":320.38289856910706,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.2262 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 23\n  Failed: 67\n  Timeouts: 0\n  Success Rate: 25.56%\n  Mean Completion Time: 22.99 s\n  Std Completion Time: 5.37 s\n  Mean Steps: 459.11\n  Std Steps: 308.49\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 320.38 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/9e84d275-937f-400c-af70-48a3a33c9d69/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T11:59:11.330874"},{"id":"1733df44-33f5-437e-8800-25ac6ea9a3f1","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"3b4f6aaa-e435-47f3-ae07-665c0746d172","miner_hotkey":"5Dkdm76LdesnuTTPDA5jd7DrdY5AnHPzs9faCNWfdSzEVYUr","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"private","score":0.1967962962962963,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_114640","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":374.5689687728882,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.1968 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 20\n  Failed: 70\n  Timeouts: 0\n  Success Rate: 22.22%\n  Mean Completion Time: 22.88 s\n  Std Completion Time: 2.47 s\n  Mean Steps: 637.09\n  Std Steps: 282.22\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 374.57 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/3b4f6aaa-e435-47f3-ae07-665c0746d172/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T11:52:57.473309"},{"id":"4d34b697-3985-4abe-b082-42052219b57a","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"53f8cf61-559d-4b7b-8ece-5814b1e34767","miner_hotkey":"5GbtkZXHxnfZmJWkv81fN78kQED77iqFs568q4Mp4NXGF8mL","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"private","score":0.1967962962962963,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_113942","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":371.88043308258057,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.1968 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 20\n  Failed: 70\n  Timeouts: 0\n  Success Rate: 22.22%\n  Mean Completion Time: 22.88 s\n  Std Completion Time: 2.47 s\n  Mean Steps: 637.09\n  Std Steps: 282.22\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 371.88 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/53f8cf61-559d-4b7b-8ece-5814b1e34767/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T11:45:57.444255"},{"id":"cb3b0bdb-d428-4853-a836-fd79a92d62c2","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"271fc597-1c33-46a4-9496-93a3480dc75d","miner_hotkey":"5CwEQFQKS7PBxcWPTja4EQif9YUWvc3MtuL7138wGPDWUijG","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"private","score":0.13143888888888888,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_113331","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":325.5387008190155,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.1314 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 13\n  Failed: 77\n  Timeouts: 0\n  Success Rate: 14.44%\n  Mean Completion Time: 18.01 s\n  Std Completion Time: 2.10 s\n  Mean Steps: 436.92\n  Std Steps: 294.65\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 325.54 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/271fc597-1c33-46a4-9496-93a3480dc75d/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T11:38:59.798947"},{"id":"d4dbc813-20ad-47ee-adb8-743c3d0b4a36","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"e5f2c088-09be-40e7-a894-bfb8b3fb0905","miner_hotkey":"5CrMbtUP71FozUgcvXC9iECZvb6zaaU9opmkjBU8HkdbTcur","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"private","score":0.22702037037037034,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_112636","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":362.542973279953,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.2270 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 23\n  Failed: 67\n  Timeouts: 0\n  Success Rate: 25.56%\n  Mean Completion Time: 22.33 s\n  Std Completion Time: 1.87 s\n  Mean Steps: 619.82\n  Std Steps: 246.86\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 362.54 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/e5f2c088-09be-40e7-a894-bfb8b3fb0905/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T11:32:41.602475"},{"id":"0fb09a94-a7c5-4ab7-8c2c-809976355f77","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"30538e0b-3e5b-48ef-b2f4-ea2d142cf165","miner_hotkey":"5GTAM7G3WQAjmjJEXV9mamqsSGSKYX8HYRjR6hRP2Y2hVmEm","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"private","score":0.21701296296296296,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_111946","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":362.7812178134918,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.2170 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 22\n  Failed: 68\n  Timeouts: 0\n  Success Rate: 24.44%\n  Mean Completion Time: 22.44 s\n  Std Completion Time: 1.88 s\n  Mean Steps: 615.84\n  Std Steps: 250.36\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 362.78 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/30538e0b-3e5b-48ef-b2f4-ea2d142cf165/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T11:25:52.295021"},{"id":"5265e069-a795-4a2d-88e2-bf1331322c69","tournament_id":"66f9e369-ebeb-46c0-9849-c4dce40ce7d3","tournament_name":"task-leatherback-lidar v1.2","agent_id":"2f6213a3-848b-4352-bd9f-f1a2fa3d6417","miner_hotkey":"5GRA8BBQobvZokdqwwQpmceW6D5eA3p6jMnFGDaT5PG8WnAY","miner_uid":null,"task_name":"task-leatherback-lidar","validator_hotkey":"5EPdhbd4RzzRiPbEXssg6fQ3s8CU1M8kLG2L2WiXghCSas49","phase":"public","score":0.7523538147149262,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/leatherback-lidar-maze/eval_run_20260712_110814","category":"navigation","num_envs":150,"task_name":"Nepher-Leatherback-Lidar-Maze-Envhub-Play-v0","task_type":"navigation.leatherback","env_config":{},"env_scenes":[{"scene":0,"env_id":"leatherback-maze-v3"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"leatherback_lidar","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":450,"max_episode_time_s":30.0},"scenes":["leatherback-maze-v3:0"],"task_name":"Nepher-Leatherback-Lidar-Maze-Envhub-Play-v0","task_type":"navigation.leatherback","env_scenes":[{"scene":0,"env_id":"leatherback-maze-v3"}],"num_episodes":3,"elapsed_seconds":1024.2366528511047,"scoring_version":"v2","max_episode_steps":450,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.7524 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 450\n  Successful: 402\n  Failed: 48\n  Timeouts: 17\n  Success Rate: 89.33%\n  Mean Completion Time: 12.50 s\n  Std Completion Time: 5.24 s\n  Mean Steps: 193.69\n  Std Steps: 94.65\n  Step dt: 0.0667 s\n\nLocomotion Quality:\n------------------------------------------------------------\n  Mean Speed: 1.921 m/s\n  Max Speed: 3.800 m/s\n  Speed Std: 0.921 m/s\n  Mean Vertical Speed: 0.030 m/s\n  Mean Angular Speed: 0.875 rad/s\n  Angular Speed Std: 0.595 rad/s\n  Mean Roll/Pitch Rate: 0.206 rad/s\n  Mean Lateral Speed: 0.139 m/s\n  Max Lateral Speed: 0.362 m/s\n  Walking (not running): NO — speed exceeds walking threshold\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Leatherback-Lidar-Maze-Envhub-Play-v0\n  Scoring Version: v2\n  Scenes: ['leatherback-maze-v3:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 1024.24 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Good performance. Room for improvement in success rate or speed.\n\n============================================================","log_file_path":"evaluations/66f9e369-ebeb-46c0-9849-c4dce40ce7d3/2f6213a3-848b-4352-bd9f-f1a2fa3d6417/5EPdhbd4RzzRiPbEXssg6fQ3s8CU1M8kLG2L2WiXghCSas49/logs.zip","status":"done","evaluated_at":"2026-07-12T11:25:21.200685"},{"id":"1cac7d86-4956-46fb-babe-b8ed4f4f2011","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"6d6911f2-235e-4ac6-a3d2-18a81f6c937a","miner_hotkey":"5CqvpAxs9UZpUEJXJgaVjGcWSkaFXT2D5b8PNQfApgWq8M3M","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"private","score":0.17732962962962964,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_111257","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":360.0335955619812,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.1773 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 18\n  Failed: 72\n  Timeouts: 0\n  Success Rate: 20.00%\n  Mean Completion Time: 22.67 s\n  Std Completion Time: 2.94 s\n  Mean Steps: 621.32\n  Std Steps: 250.88\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 360.03 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/6d6911f2-235e-4ac6-a3d2-18a81f6c937a/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T11:19:01.830395"},{"id":"9687274b-bc0f-47e3-a3c4-5aa9bf56e3eb","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"b874221a-b148-43c6-892c-5aafbdb1cc5a","miner_hotkey":"5FsDgeBuuTsszahH7tGx9aVhJoPdDHsWkJC5VnxefrtuHXkp","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"private","score":0.2190462962962963,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_110618","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":352.3847405910492,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.2190 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 22\n  Failed: 68\n  Timeouts: 0\n  Success Rate: 24.44%\n  Mean Completion Time: 20.78 s\n  Std Completion Time: 1.11 s\n  Mean Steps: 585.70\n  Std Steps: 243.57\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 352.38 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/b874221a-b148-43c6-892c-5aafbdb1cc5a/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T11:12:13.443154"},{"id":"2fd59e49-d218-4b58-81d0-675ed10bccd4","tournament_id":"66f9e369-ebeb-46c0-9849-c4dce40ce7d3","tournament_name":"task-leatherback-lidar v1.2","agent_id":"1d44cb23-c43c-4a51-a1f0-2bc8cbc12725","miner_hotkey":"5DyvfTEMLsYjn5oRH3LbSouJq9cK1CmDg8F7uTRGHkCFKtj2","miner_uid":null,"task_name":"task-leatherback-lidar","validator_hotkey":"5EPdhbd4RzzRiPbEXssg6fQ3s8CU1M8kLG2L2WiXghCSas49","phase":"public","score":0.8209739146568157,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/leatherback-lidar-maze/eval_run_20260712_105556","category":"navigation","num_envs":150,"task_name":"Nepher-Leatherback-Lidar-Maze-Envhub-Play-v0","task_type":"navigation.leatherback","env_config":{},"env_scenes":[{"scene":0,"env_id":"leatherback-maze-v3"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"leatherback_lidar","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":450,"max_episode_time_s":30.0},"scenes":["leatherback-maze-v3:0"],"task_name":"Nepher-Leatherback-Lidar-Maze-Envhub-Play-v0","task_type":"navigation.leatherback","env_scenes":[{"scene":0,"env_id":"leatherback-maze-v3"}],"num_episodes":3,"elapsed_seconds":700.5226514339447,"scoring_version":"v2","max_episode_steps":450,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.8210 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 450\n  Successful: 431\n  Failed: 19\n  Timeouts: 1\n  Success Rate: 95.78%\n  Mean Completion Time: 11.17 s\n  Std Completion Time: 4.85 s\n  Mean Steps: 166.09\n  Std Steps: 75.09\n  Step dt: 0.0667 s\n\nLocomotion Quality:\n------------------------------------------------------------\n  Mean Speed: 2.204 m/s\n  Max Speed: 2.540 m/s\n  Speed Std: 0.644 m/s\n  Mean Vertical Speed: 0.030 m/s\n  Mean Angular Speed: 1.238 rad/s\n  Angular Speed Std: 0.637 rad/s\n  Mean Roll/Pitch Rate: 0.194 rad/s\n  Mean Lateral Speed: 0.198 m/s\n  Max Lateral Speed: 0.414 m/s\n  Walking (not running): NO — speed exceeds walking threshold\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Leatherback-Lidar-Maze-Envhub-Play-v0\n  Scoring Version: v2\n  Scenes: ['leatherback-maze-v3:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 700.52 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Excellent performance! High success rate and fast completion.\n\n============================================================","log_file_path":"evaluations/66f9e369-ebeb-46c0-9849-c4dce40ce7d3/1d44cb23-c43c-4a51-a1f0-2bc8cbc12725/5EPdhbd4RzzRiPbEXssg6fQ3s8CU1M8kLG2L2WiXghCSas49/logs.zip","status":"done","evaluated_at":"2026-07-12T11:07:39.996648"},{"id":"df60a6dd-db8c-41e0-a1ec-aa5cc20d5c15","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"887ed490-f45c-43cc-bc13-9302a5f0c507","miner_hotkey":"5Dtf7ZAX6JFm3Xu2u76WirxXbnonohHHPg84ARHohHyQZ6A9","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"private","score":0.17684814814814817,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_105917","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":374.0856976509094,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.1768 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 18\n  Failed: 72\n  Timeouts: 0\n  Success Rate: 20.00%\n  Mean Completion Time: 23.15 s\n  Std Completion Time: 1.72 s\n  Mean Steps: 698.81\n  Std Steps: 256.92\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 374.09 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/887ed490-f45c-43cc-bc13-9302a5f0c507/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T11:05:33.883130"},{"id":"68582f91-e276-4c47-a0bf-4c85d366bd1c","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"f2806318-15a5-461a-9dfa-68e42155b4d7","miner_hotkey":"5FvJhkUBPpc2qCVMQmW1aoHsS2QuffEvRatMJMHp1rC1foU4","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"private","score":0.2553537037037037,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_105224","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":366.2291429042816,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.2554 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 26\n  Failed: 64\n  Timeouts: 0\n  Success Rate: 28.89%\n  Mean Completion Time: 23.22 s\n  Std Completion Time: 1.94 s\n  Mean Steps: 613.96\n  Std Steps: 237.47\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 366.23 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/f2806318-15a5-461a-9dfa-68e42155b4d7/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T10:58:33.031035"},{"id":"48dba9c3-050a-493e-b347-47c32c4cf60e","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"13952e98-3ebe-44a9-b11a-8f9986efe442","miner_hotkey":"5CPtyBctLkxHSGQZwJcEMq744fimktad6c3kGtfQwGYNpCbX","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5EPdhbd4RzzRiPbEXssg6fQ3s8CU1M8kLG2L2WiXghCSas49","phase":"private","score":0.22860370370370367,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_105102","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":257.8349061012268,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.2286 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 23\n  Failed: 67\n  Timeouts: 0\n  Success Rate: 25.56%\n  Mean Completion Time: 21.09 s\n  Std Completion Time: 4.06 s\n  Mean Steps: 634.80\n  Std Steps: 411.64\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 257.83 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/13952e98-3ebe-44a9-b11a-8f9986efe442/5EPdhbd4RzzRiPbEXssg6fQ3s8CU1M8kLG2L2WiXghCSas49/logs.zip","status":"done","evaluated_at":"2026-07-12T10:55:22.741116"},{"id":"ded710c8-b9bc-4970-8836-a7090efe5ed8","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"c781fd31-670c-4c72-bd20-fc5c794704ac","miner_hotkey":"5Funav29kiJECxtp76cAMmAuqms2WQTZe5yWM81mVPBGLzvG","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"private","score":0.03992222222222222,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_104518","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":379.2529864311218,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.0399 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 4\n  Failed: 86\n  Timeouts: 0\n  Success Rate: 4.44%\n  Mean Completion Time: 20.35 s\n  Std Completion Time: 1.62 s\n  Mean Steps: 682.13\n  Std Steps: 335.41\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 379.25 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/c781fd31-670c-4c72-bd20-fc5c794704ac/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T10:51:40.247143"},{"id":"ff857113-afbd-4c1b-b3ee-4d158dccf1a5","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"9e84d275-937f-400c-af70-48a3a33c9d69","miner_hotkey":"5DPz76uobJLTfjaSiWkrBbsWktrLQ6s7kAHWm7Pb9B17zZRn","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5EPdhbd4RzzRiPbEXssg6fQ3s8CU1M8kLG2L2WiXghCSas49","phase":"private","score":0.22617407407407406,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_104623","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":184.5320942401886,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.2262 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 23\n  Failed: 67\n  Timeouts: 0\n  Success Rate: 25.56%\n  Mean Completion Time: 22.99 s\n  Std Completion Time: 5.37 s\n  Mean Steps: 459.11\n  Std Steps: 308.49\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 184.53 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/9e84d275-937f-400c-af70-48a3a33c9d69/5EPdhbd4RzzRiPbEXssg6fQ3s8CU1M8kLG2L2WiXghCSas49/logs.zip","status":"done","evaluated_at":"2026-07-12T10:49:30.693399"},{"id":"e7e37998-212d-4ad7-b3e1-d12f8d329da0","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"3b4f6aaa-e435-47f3-ae07-665c0746d172","miner_hotkey":"5Dkdm76LdesnuTTPDA5jd7DrdY5AnHPzs9faCNWfdSzEVYUr","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5EPdhbd4RzzRiPbEXssg6fQ3s8CU1M8kLG2L2WiXghCSas49","phase":"private","score":0.1967962962962963,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_104211","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":212.17730259895325,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.1968 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 20\n  Failed: 70\n  Timeouts: 0\n  Success Rate: 22.22%\n  Mean Completion Time: 22.88 s\n  Std Completion Time: 2.47 s\n  Mean Steps: 637.09\n  Std Steps: 282.22\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 212.18 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/3b4f6aaa-e435-47f3-ae07-665c0746d172/5EPdhbd4RzzRiPbEXssg6fQ3s8CU1M8kLG2L2WiXghCSas49/logs.zip","status":"done","evaluated_at":"2026-07-12T10:45:46.347779"},{"id":"f6b49563-a705-43b5-a5ca-5b2f439578d8","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"99624d2e-a749-426b-a836-9dd24077ffa3","miner_hotkey":"5DqQvBG49reHiodztVCutEFY2otTJkyZKPZAkb8tSMM7tnr7","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn","phase":"private","score":0.21594444444444444,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_103830","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":361.0782880783081,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.2159 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 22\n  Failed: 68\n  Timeouts: 0\n  Success Rate: 24.44%\n  Mean Completion Time: 23.32 s\n  Std Completion Time: 2.49 s\n  Mean Steps: 639.11\n  Std Steps: 272.03\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 361.08 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/99624d2e-a749-426b-a836-9dd24077ffa3/5DLYBBCdYwBgjJi76dHJuAU7tUb7rNHJmNtpYRmBesBnrAgn/logs.zip","status":"done","evaluated_at":"2026-07-12T10:44:33.655544"},{"id":"6e9c1ff7-ebb4-4f6f-b987-c542b626a7d2","tournament_id":"07f3f88b-7741-4a8b-ae47-3be722e0be0b","tournament_name":"task-franka-pickplace-multibase v1.2","agent_id":"53f8cf61-559d-4b7b-8ece-5814b1e34767","miner_hotkey":"5GbtkZXHxnfZmJWkv81fN78kQED77iqFs568q4Mp4NXGF8mL","miner_uid":null,"task_name":"task-franka-pickplace-multibase","validator_hotkey":"5EPdhbd4RzzRiPbEXssg6fQ3s8CU1M8kLG2L2WiXghCSas49","phase":"private","score":0.1967962962962963,"metadata":{"seeds":[42],"config":{"seeds":[42],"log_dir":"/app/logs/franka-pickplace-multibase-hl/eval_run_20260712_103805","category":"manipulation","num_envs":30,"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_config":{},"env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"policy_path":"/app/agent/best_policy/best_policy.pt","task_module":"franka_pickplace_multibase","num_episodes":3,"enable_cameras":false,"enable_logging":true,"scoring_version":"v2","timeout_seconds":null,"max_episode_steps":1500,"max_episode_time_s":30.0},"scenes":["franka-pickplace-multibase-v1:0"],"task_name":"Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0","task_type":"manipulation.pick_place","env_scenes":[{"scene":0,"env_id":"franka-pickplace-multibase-v1"}],"num_episodes":3,"elapsed_seconds":213.85217547416687,"scoring_version":"v2","max_episode_steps":1500,"max_episode_time_s":30.0,"total_episodes_run":3},"summary":"============================================================\nNavigation Evaluation Summary\n============================================================\n\nStatus: SUCCESS\nFinal Score: 0.1968 (normalized [0, 1])\n\nAggregate Metrics:\n------------------------------------------------------------\n  Total Episodes: 90\n  Successful: 20\n  Failed: 70\n  Timeouts: 0\n  Success Rate: 22.22%\n  Mean Completion Time: 22.88 s\n  Std Completion Time: 2.47 s\n  Mean Steps: 637.09\n  Std Steps: 282.22\n  Step dt: 0.0333 s\n\nEvaluation Metadata:\n------------------------------------------------------------\n  Task: Nepher-Franka-PickPlace-HL-Multibase-EnvhubPlay-v0\n  Scoring Version: v2\n  Scenes: ['franka-pickplace-multibase-v1:0']\n  Seeds: [42]\n  Episodes per Scene-Seed: 3\n  Total Episodes Run: 3\n  Max Episode Time: 30.00 s\n  Elapsed Time: 213.85 seconds\n\nInterpretation:\n------------------------------------------------------------\n  Poor performance. Fundamental navigation issues detected.\n\n============================================================","log_file_path":"evaluations/07f3f88b-7741-4a8b-ae47-3be722e0be0b/53f8cf61-559d-4b7b-8ece-5814b1e34767/5EPdhbd4RzzRiPbEXssg6fQ3s8CU1M8kLG2L2WiXghCSas49/logs.zip","status":"done","evaluated_at":"2026-07-12T10:41:41.530340"}],"total":4517,"page":1,"limit":20}