[
{
"id": "agibot_683_868633-train-bf_001397-af_001824-plus-0000341",
"task": "Serve the meal",
"image": [
"images/agibotworld/683/868698/cam_high/frame_000000.jpg",
"images/agibotworld/683/868698/cam_high/frame_001879.jpg",
"images/agibotworld/683/868633/cam_high/frame_001397.jpg",
"images/agibotworld/683/868633/cam_left_wrist/frame_001397.jpg",
"images/agibotworld/683/868633/cam_right_wrist/frame_001397.jpg",
"images/agibotworld/683/868633/cam_high/frame_001824.jpg",
"images/agibotworld/683/868633/cam_left_wrist/frame_001824.jpg",
"images/agibotworld/683/868633/cam_right_wrist/frame_001824.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Serve the meal`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Serve the meal`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 42.9,
"hop_absolute_value": 42.9,
"hop_category": {
"absolute_category": "medium",
"direction": "progress",
"combined_category": "progress_medium"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_375_694775-train-bf_000737-af_000822-plus-0000723",
"task": "Brew tea",
"image": [
"images/agibotworld/375/695466/cam_high/frame_000000.jpg",
"images/agibotworld/375/695466/cam_high/frame_001814.jpg",
"images/agibotworld/375/694775/cam_high/frame_000737.jpg",
"images/agibotworld/375/694775/cam_left_wrist/frame_000737.jpg",
"images/agibotworld/375/694775/cam_right_wrist/frame_000737.jpg",
"images/agibotworld/375/694775/cam_high/frame_000822.jpg",
"images/agibotworld/375/694775/cam_left_wrist/frame_000822.jpg",
"images/agibotworld/375/694775/cam_right_wrist/frame_000822.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Brew tea`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Brew tea`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 6.7,
"hop_absolute_value": 6.7,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_431_782894-train-bf_000199-af_001933-plus-0000560",
"task": "Brew coffee with a capsule machine",
"image": [
"images/agibotworld/431/787084/cam_high/frame_000000.jpg",
"images/agibotworld/431/787084/cam_high/frame_001467.jpg",
"images/agibotworld/431/782894/cam_high/frame_000199.jpg",
"images/agibotworld/431/782894/cam_left_wrist/frame_000199.jpg",
"images/agibotworld/431/782894/cam_right_wrist/frame_000199.jpg",
"images/agibotworld/431/782894/cam_high/frame_001933.jpg",
"images/agibotworld/431/782894/cam_left_wrist/frame_001933.jpg",
"images/agibotworld/431/782894/cam_right_wrist/frame_001933.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Brew coffee with a capsule machine`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Brew coffee with a capsule machine`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 100.0,
"hop_absolute_value": 100.0,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_388_690677-train-bf_000076-af_000384-plus-0000785",
"task": "Pickup in the supermarket",
"image": [
"images/agibotworld/388/691251/cam_high/frame_000039.jpg",
"images/agibotworld/388/691251/cam_high/frame_001435.jpg",
"images/agibotworld/388/690677/cam_high/frame_000076.jpg",
"images/agibotworld/388/690677/cam_left_wrist/frame_000076.jpg",
"images/agibotworld/388/690677/cam_right_wrist/frame_000076.jpg",
"images/agibotworld/388/690677/cam_high/frame_000384.jpg",
"images/agibotworld/388/690677/cam_left_wrist/frame_000384.jpg",
"images/agibotworld/388/690677/cam_right_wrist/frame_000384.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Pickup in the supermarket`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Pickup in the supermarket`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 22.9,
"hop_absolute_value": 22.9,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_609_832750-train-bf_000093-af_000140-plus-0000470",
"task": "Restock the hanging basket area",
"image": [
"images/agibotworld/609/832750/cam_high/frame_000000.jpg",
"images/agibotworld/609/832750/cam_high/frame_001012.jpg",
"images/agibotworld/609/832750/cam_high/frame_000093.jpg",
"images/agibotworld/609/832750/cam_left_wrist/frame_000093.jpg",
"images/agibotworld/609/832750/cam_right_wrist/frame_000093.jpg",
"images/agibotworld/609/832750/cam_high/frame_000140.jpg",
"images/agibotworld/609/832750/cam_left_wrist/frame_000140.jpg",
"images/agibotworld/609/832750/cam_right_wrist/frame_000140.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Restock the hanging basket area`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Restock the hanging basket area`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 4.5,
"hop_absolute_value": 4.5,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_580_862866-train-bf_000592-af_004163-plus-0000447",
"task": "Make juice",
"image": [
"images/agibotworld/580/867528/cam_high/frame_000000.jpg",
"images/agibotworld/580/867528/cam_high/frame_007072.jpg",
"images/agibotworld/580/862866/cam_high/frame_000592.jpg",
"images/agibotworld/580/862866/cam_left_wrist/frame_000592.jpg",
"images/agibotworld/580/862866/cam_right_wrist/frame_000592.jpg",
"images/agibotworld/580/862866/cam_high/frame_004163.jpg",
"images/agibotworld/580/862866/cam_left_wrist/frame_004163.jpg",
"images/agibotworld/580/862866/cam_right_wrist/frame_004163.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Make juice`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Make juice`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 56.2,
"hop_absolute_value": 56.2,
"hop_category": {
"absolute_category": "medium",
"direction": "progress",
"combined_category": "progress_medium"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_621_880091-train-bf_002112-af_003938-plus-0000497",
"task": "Add the seasoning to the pot.",
"image": [
"images/agibotworld/621/872985/cam_high/frame_000126.jpg",
"images/agibotworld/621/872985/cam_high/frame_005272.jpg",
"images/agibotworld/621/880091/cam_high/frame_002112.jpg",
"images/agibotworld/621/880091/cam_left_wrist/frame_002112.jpg",
"images/agibotworld/621/880091/cam_right_wrist/frame_002112.jpg",
"images/agibotworld/621/880091/cam_high/frame_003938.jpg",
"images/agibotworld/621/880091/cam_left_wrist/frame_003938.jpg",
"images/agibotworld/621/880091/cam_right_wrist/frame_003938.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Add the seasoning to the pot.`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Add the seasoning to the pot.`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 73.9,
"hop_absolute_value": 73.9,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_774_925510-train-bf_000107-af_000780-plus-0000294",
"task": "Insert the key and open the door",
"image": [
"images/agibotworld/774/889716/cam_high/frame_000000.jpg",
"images/agibotworld/774/889716/cam_high/frame_000785.jpg",
"images/agibotworld/774/925510/cam_high/frame_000107.jpg",
"images/agibotworld/774/925510/cam_left_wrist/frame_000107.jpg",
"images/agibotworld/774/925510/cam_right_wrist/frame_000107.jpg",
"images/agibotworld/774/925510/cam_high/frame_000780.jpg",
"images/agibotworld/774/925510/cam_left_wrist/frame_000780.jpg",
"images/agibotworld/774/925510/cam_right_wrist/frame_000780.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Insert the key and open the door`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Insert the key and open the door`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 43.5,
"hop_absolute_value": 43.5,
"hop_category": {
"absolute_category": "medium",
"direction": "progress",
"combined_category": "progress_medium"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_487_720041-train-bf_002090-af_003768-plus-0000545",
"task": "Remove bottled water from the carton and arrange neatly on the table.",
"image": [
"images/agibotworld/487/719828/cam_high/frame_000039.jpg",
"images/agibotworld/487/719828/cam_high/frame_003576.jpg",
"images/agibotworld/487/720041/cam_high/frame_002090.jpg",
"images/agibotworld/487/720041/cam_left_wrist/frame_002090.jpg",
"images/agibotworld/487/720041/cam_right_wrist/frame_002090.jpg",
"images/agibotworld/487/720041/cam_high/frame_003768.jpg",
"images/agibotworld/487/720041/cam_left_wrist/frame_003768.jpg",
"images/agibotworld/487/720041/cam_right_wrist/frame_003768.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Remove bottled water from the carton and arrange neatly on the table.`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Remove bottled water from the carton and arrange neatly on the table.`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 91.9,
"hop_absolute_value": 91.9,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_521_763453-train-bf_000943-af_001206-plus-0000464",
"task": "Dispose of the trash on the desk.",
"image": [
"images/agibotworld/521/757938/cam_high/frame_000033.jpg",
"images/agibotworld/521/757938/cam_high/frame_001643.jpg",
"images/agibotworld/521/763453/cam_high/frame_000943.jpg",
"images/agibotworld/521/763453/cam_left_wrist/frame_000943.jpg",
"images/agibotworld/521/763453/cam_right_wrist/frame_000943.jpg",
"images/agibotworld/521/763453/cam_high/frame_001206.jpg",
"images/agibotworld/521/763453/cam_left_wrist/frame_001206.jpg",
"images/agibotworld/521/763453/cam_right_wrist/frame_001206.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Dispose of the trash on the desk.`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Dispose of the trash on the desk.`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 83.3,
"hop_absolute_value": 83.3,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_480_728736-train-bf_000974-af_001066-plus-0000949",
"task": "Make sandwiches with salad dressing 1213 edition",
"image": [
"images/agibotworld/480/728736/cam_high/frame_000000.jpg",
"images/agibotworld/480/728736/cam_high/frame_002388.jpg",
"images/agibotworld/480/728736/cam_high/frame_000974.jpg",
"images/agibotworld/480/728736/cam_left_wrist/frame_000974.jpg",
"images/agibotworld/480/728736/cam_right_wrist/frame_000974.jpg",
"images/agibotworld/480/728736/cam_high/frame_001066.jpg",
"images/agibotworld/480/728736/cam_left_wrist/frame_001066.jpg",
"images/agibotworld/480/728736/cam_right_wrist/frame_001066.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Make sandwiches with salad dressing 1213 edition`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Make sandwiches with salad dressing 1213 edition`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 7.7,
"hop_absolute_value": 7.7,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_782_914994-train-bf_000604-af_000690-plus-0000784",
"task": "Tidy the bar counter",
"image": [
"images/agibotworld/782/914693/cam_high/frame_000064.jpg",
"images/agibotworld/782/914693/cam_high/frame_001915.jpg",
"images/agibotworld/782/914994/cam_high/frame_000604.jpg",
"images/agibotworld/782/914994/cam_left_wrist/frame_000604.jpg",
"images/agibotworld/782/914994/cam_right_wrist/frame_000604.jpg",
"images/agibotworld/782/914994/cam_high/frame_000690.jpg",
"images/agibotworld/782/914994/cam_left_wrist/frame_000690.jpg",
"images/agibotworld/782/914994/cam_right_wrist/frame_000690.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Tidy the bar counter`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Tidy the bar counter`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 5.4,
"hop_absolute_value": 5.4,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_550_821460-train-bf_000265-af_000362-plus-0000654",
"task": "Peel fruits and vegetables",
"image": [
"images/agibotworld/550/832819/cam_high/frame_000046.jpg",
"images/agibotworld/550/832819/cam_high/frame_001720.jpg",
"images/agibotworld/550/821460/cam_high/frame_000265.jpg",
"images/agibotworld/550/821460/cam_left_wrist/frame_000265.jpg",
"images/agibotworld/550/821460/cam_right_wrist/frame_000265.jpg",
"images/agibotworld/550/821460/cam_high/frame_000362.jpg",
"images/agibotworld/550/821460/cam_left_wrist/frame_000362.jpg",
"images/agibotworld/550/821460/cam_right_wrist/frame_000362.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Peel fruits and vegetables`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Peel fruits and vegetables`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 10.7,
"hop_absolute_value": 10.7,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_454_692968-train-bf_002827-af_003299-plus-0000565",
"task": "Make a sandwich",
"image": [
"images/agibotworld/454/688896/cam_high/frame_000035.jpg",
"images/agibotworld/454/688896/cam_high/frame_003001.jpg",
"images/agibotworld/454/692968/cam_high/frame_002827.jpg",
"images/agibotworld/454/692968/cam_left_wrist/frame_002827.jpg",
"images/agibotworld/454/692968/cam_right_wrist/frame_002827.jpg",
"images/agibotworld/454/692968/cam_high/frame_003299.jpg",
"images/agibotworld/454/692968/cam_left_wrist/frame_003299.jpg",
"images/agibotworld/454/692968/cam_right_wrist/frame_003299.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Make a sandwich`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Make a sandwich`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 93.8,
"hop_absolute_value": 93.8,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_543_808768-train-bf_000273-af_000304-plus-0000476",
"task": "Packing washing detergent",
"image": [
"images/agibotworld/543/808768/cam_high/frame_000116.jpg",
"images/agibotworld/543/808768/cam_high/frame_000761.jpg",
"images/agibotworld/543/808768/cam_high/frame_000273.jpg",
"images/agibotworld/543/808768/cam_left_wrist/frame_000273.jpg",
"images/agibotworld/543/808768/cam_right_wrist/frame_000273.jpg",
"images/agibotworld/543/808768/cam_high/frame_000304.jpg",
"images/agibotworld/543/808768/cam_left_wrist/frame_000304.jpg",
"images/agibotworld/543/808768/cam_right_wrist/frame_000304.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Packing washing detergent`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Packing washing detergent`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 5.3,
"hop_absolute_value": 5.3,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_452_715411-train-bf_000333-af_000376-plus-0000277",
"task": "Slice a lemon to make lemon water.",
"image": [
"images/agibotworld/452/714273/cam_high/frame_000020.jpg",
"images/agibotworld/452/714273/cam_high/frame_001388.jpg",
"images/agibotworld/452/715411/cam_high/frame_000333.jpg",
"images/agibotworld/452/715411/cam_left_wrist/frame_000333.jpg",
"images/agibotworld/452/715411/cam_right_wrist/frame_000333.jpg",
"images/agibotworld/452/715411/cam_high/frame_000376.jpg",
"images/agibotworld/452/715411/cam_left_wrist/frame_000376.jpg",
"images/agibotworld/452/715411/cam_right_wrist/frame_000376.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Slice a lemon to make lemon water.`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Slice a lemon to make lemon water.`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 5.9,
"hop_absolute_value": 5.9,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_708_900178-train-bf_000975-af_005027-plus-0000566",
"task": "Place name tags",
"image": [
"images/agibotworld/708/910844/cam_high/frame_000000.jpg",
"images/agibotworld/708/910844/cam_high/frame_004089.jpg",
"images/agibotworld/708/900178/cam_high/frame_000975.jpg",
"images/agibotworld/708/900178/cam_left_wrist/frame_000975.jpg",
"images/agibotworld/708/900178/cam_right_wrist/frame_000975.jpg",
"images/agibotworld/708/900178/cam_high/frame_005027.jpg",
"images/agibotworld/708/900178/cam_left_wrist/frame_005027.jpg",
"images/agibotworld/708/900178/cam_right_wrist/frame_005027.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Place name tags`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Place name tags`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 89.7,
"hop_absolute_value": 89.7,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_372_664533-train-bf_000731-af_000925-plus-0000307",
"task": "Packing in the supermarket",
"image": [
"images/agibotworld/372/664533/cam_high/frame_000019.jpg",
"images/agibotworld/372/664533/cam_high/frame_002140.jpg",
"images/agibotworld/372/664533/cam_high/frame_000731.jpg",
"images/agibotworld/372/664533/cam_left_wrist/frame_000731.jpg",
"images/agibotworld/372/664533/cam_right_wrist/frame_000731.jpg",
"images/agibotworld/372/664533/cam_high/frame_000925.jpg",
"images/agibotworld/372/664533/cam_left_wrist/frame_000925.jpg",
"images/agibotworld/372/664533/cam_right_wrist/frame_000925.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Packing in the supermarket`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Packing in the supermarket`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 11.1,
"hop_absolute_value": 11.1,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_504_769603-train-bf_000849-af_001043-plus-0000351",
"task": "Restock supermarket snacks",
"image": [
"images/agibotworld/504/727913/cam_high/frame_000000.jpg",
"images/agibotworld/504/727913/cam_high/frame_002251.jpg",
"images/agibotworld/504/769603/cam_high/frame_000849.jpg",
"images/agibotworld/504/769603/cam_left_wrist/frame_000849.jpg",
"images/agibotworld/504/769603/cam_right_wrist/frame_000849.jpg",
"images/agibotworld/504/769603/cam_high/frame_001043.jpg",
"images/agibotworld/504/769603/cam_left_wrist/frame_001043.jpg",
"images/agibotworld/504/769603/cam_right_wrist/frame_001043.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Restock supermarket snacks`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Restock supermarket snacks`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 42.9,
"hop_absolute_value": 42.9,
"hop_category": {
"absolute_category": "medium",
"direction": "progress",
"combined_category": "progress_medium"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_582_803488-train-bf_000381-af_000591-plus-0000317",
"task": "Discard the trash on the coffee table.",
"image": [
"images/agibotworld/582/803503/cam_high/frame_000000.jpg",
"images/agibotworld/582/803503/cam_high/frame_000664.jpg",
"images/agibotworld/582/803488/cam_high/frame_000381.jpg",
"images/agibotworld/582/803488/cam_left_wrist/frame_000381.jpg",
"images/agibotworld/582/803488/cam_right_wrist/frame_000381.jpg",
"images/agibotworld/582/803488/cam_high/frame_000591.jpg",
"images/agibotworld/582/803488/cam_left_wrist/frame_000591.jpg",
"images/agibotworld/582/803488/cam_right_wrist/frame_000591.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Discard the trash on the coffee table.`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Discard the trash on the coffee table.`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 58.3,
"hop_absolute_value": 58.3,
"hop_category": {
"absolute_category": "medium",
"direction": "progress",
"combined_category": "progress_medium"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_547_843250-train-bf_002496-af_002574-plus-0000914",
"task": "Sort light and dark clothes",
"image": [
"images/agibotworld/547/843250/cam_high/frame_000000.jpg",
"images/agibotworld/547/843250/cam_high/frame_003381.jpg",
"images/agibotworld/547/843250/cam_high/frame_002496.jpg",
"images/agibotworld/547/843250/cam_left_wrist/frame_002496.jpg",
"images/agibotworld/547/843250/cam_right_wrist/frame_002496.jpg",
"images/agibotworld/547/843250/cam_high/frame_002574.jpg",
"images/agibotworld/547/843250/cam_left_wrist/frame_002574.jpg",
"images/agibotworld/547/843250/cam_right_wrist/frame_002574.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Sort light and dark clothes`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Sort light and dark clothes`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 6.2,
"hop_absolute_value": 6.2,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_542_775271-train-bf_000491-af_000538-plus-0000589",
"task": "Boil water with a kettle",
"image": [
"images/agibotworld/542/775271/cam_high/frame_000000.jpg",
"images/agibotworld/542/775271/cam_high/frame_001632.jpg",
"images/agibotworld/542/775271/cam_high/frame_000491.jpg",
"images/agibotworld/542/775271/cam_left_wrist/frame_000491.jpg",
"images/agibotworld/542/775271/cam_right_wrist/frame_000491.jpg",
"images/agibotworld/542/775271/cam_high/frame_000538.jpg",
"images/agibotworld/542/775271/cam_left_wrist/frame_000538.jpg",
"images/agibotworld/542/775271/cam_right_wrist/frame_000538.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Boil water with a kettle`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Boil water with a kettle`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 3.6,
"hop_absolute_value": 3.6,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_694_881865-train-bf_000430-af_001945-plus-0000547",
"task": "Twist the bottle cap",
"image": [
"images/agibotworld/694/882504/cam_high/frame_000000.jpg",
"images/agibotworld/694/882504/cam_high/frame_002115.jpg",
"images/agibotworld/694/881865/cam_high/frame_000430.jpg",
"images/agibotworld/694/881865/cam_left_wrist/frame_000430.jpg",
"images/agibotworld/694/881865/cam_right_wrist/frame_000430.jpg",
"images/agibotworld/694/881865/cam_high/frame_001945.jpg",
"images/agibotworld/694/881865/cam_left_wrist/frame_001945.jpg",
"images/agibotworld/694/881865/cam_right_wrist/frame_001945.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Twist the bottle cap`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Twist the bottle cap`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 93.1,
"hop_absolute_value": 93.1,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_543_823616-train-bf_000741-af_000972-plus-0000428",
"task": "Packing washing detergent",
"image": [
"images/agibotworld/543/823616/cam_high/frame_000078.jpg",
"images/agibotworld/543/823616/cam_high/frame_000972.jpg",
"images/agibotworld/543/823616/cam_high/frame_000741.jpg",
"images/agibotworld/543/823616/cam_left_wrist/frame_000741.jpg",
"images/agibotworld/543/823616/cam_right_wrist/frame_000741.jpg",
"images/agibotworld/543/823616/cam_high/frame_000972.jpg",
"images/agibotworld/543/823616/cam_left_wrist/frame_000972.jpg",
"images/agibotworld/543/823616/cam_right_wrist/frame_000972.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Packing washing detergent`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Packing washing detergent`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 100.0,
"hop_absolute_value": 100.0,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_424_690833-train-bf_001188-af_001557-plus-0000525",
"task": "Clear the countertop waste",
"image": [
"images/agibotworld/424/700548/cam_high/frame_000000.jpg",
"images/agibotworld/424/700548/cam_high/frame_001767.jpg",
"images/agibotworld/424/690833/cam_high/frame_001188.jpg",
"images/agibotworld/424/690833/cam_left_wrist/frame_001188.jpg",
"images/agibotworld/424/690833/cam_right_wrist/frame_001188.jpg",
"images/agibotworld/424/690833/cam_high/frame_001557.jpg",
"images/agibotworld/424/690833/cam_left_wrist/frame_001557.jpg",
"images/agibotworld/424/690833/cam_right_wrist/frame_001557.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Clear the countertop waste`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Clear the countertop waste`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 88.9,
"hop_absolute_value": 88.9,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_465_738953-train-bf_000920-af_002452-plus-0000546",
"task": "Wash clothes in the washing machine.",
"image": [
"images/agibotworld/465/742238/cam_high/frame_000000.jpg",
"images/agibotworld/465/742238/cam_high/frame_002820.jpg",
"images/agibotworld/465/738953/cam_high/frame_000920.jpg",
"images/agibotworld/465/738953/cam_left_wrist/frame_000920.jpg",
"images/agibotworld/465/738953/cam_right_wrist/frame_000920.jpg",
"images/agibotworld/465/738953/cam_high/frame_002452.jpg",
"images/agibotworld/465/738953/cam_left_wrist/frame_002452.jpg",
"images/agibotworld/465/738953/cam_right_wrist/frame_002452.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Wash clothes in the washing machine.`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Wash clothes in the washing machine.`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 89.7,
"hop_absolute_value": 89.7,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_735_903144-train-bf_001082-af_001119-plus-0000750",
"task": "Roll away stains with a lint roller",
"image": [
"images/agibotworld/735/908091/cam_high/frame_000000.jpg",
"images/agibotworld/735/908091/cam_high/frame_001798.jpg",
"images/agibotworld/735/903144/cam_high/frame_001082.jpg",
"images/agibotworld/735/903144/cam_left_wrist/frame_001082.jpg",
"images/agibotworld/735/903144/cam_right_wrist/frame_001082.jpg",
"images/agibotworld/735/903144/cam_high/frame_001119.jpg",
"images/agibotworld/735/903144/cam_left_wrist/frame_001119.jpg",
"images/agibotworld/735/903144/cam_right_wrist/frame_001119.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Roll away stains with a lint roller`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Roll away stains with a lint roller`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 6.7,
"hop_absolute_value": 6.7,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_366_657006-train-bf_000134-af_001115-plus-0000498",
"task": "Sort food",
"image": [
"images/agibotworld/366/669950/cam_high/frame_000025.jpg",
"images/agibotworld/366/669950/cam_high/frame_001145.jpg",
"images/agibotworld/366/657006/cam_high/frame_000134.jpg",
"images/agibotworld/366/657006/cam_left_wrist/frame_000134.jpg",
"images/agibotworld/366/657006/cam_right_wrist/frame_000134.jpg",
"images/agibotworld/366/657006/cam_high/frame_001115.jpg",
"images/agibotworld/366/657006/cam_left_wrist/frame_001115.jpg",
"images/agibotworld/366/657006/cam_right_wrist/frame_001115.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Sort food`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Sort food`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 88.9,
"hop_absolute_value": 88.9,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_359_693937-train-bf_000048-af_000559-plus-0000381",
"task": "Sort in the warehouse",
"image": [
"images/agibotworld/359/693937/cam_high/frame_000000.jpg",
"images/agibotworld/359/693937/cam_high/frame_000833.jpg",
"images/agibotworld/359/693937/cam_high/frame_000048.jpg",
"images/agibotworld/359/693937/cam_left_wrist/frame_000048.jpg",
"images/agibotworld/359/693937/cam_right_wrist/frame_000048.jpg",
"images/agibotworld/359/693937/cam_high/frame_000559.jpg",
"images/agibotworld/359/693937/cam_left_wrist/frame_000559.jpg",
"images/agibotworld/359/693937/cam_right_wrist/frame_000559.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Sort in the warehouse`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Sort in the warehouse`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 58.6,
"hop_absolute_value": 58.6,
"hop_category": {
"absolute_category": "medium",
"direction": "progress",
"combined_category": "progress_medium"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_525_766236-train-bf_000868-af_001099-plus-0000911",
"task": "Place cutlery in the restaurant",
"image": [
"images/agibotworld/525/771244/cam_high/frame_000000.jpg",
"images/agibotworld/525/771244/cam_high/frame_001628.jpg",
"images/agibotworld/525/766236/cam_high/frame_000868.jpg",
"images/agibotworld/525/766236/cam_left_wrist/frame_000868.jpg",
"images/agibotworld/525/766236/cam_right_wrist/frame_000868.jpg",
"images/agibotworld/525/766236/cam_high/frame_001099.jpg",
"images/agibotworld/525/766236/cam_left_wrist/frame_001099.jpg",
"images/agibotworld/525/766236/cam_right_wrist/frame_001099.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Place cutlery in the restaurant`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Place cutlery in the restaurant`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 12.1,
"hop_absolute_value": 12.1,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_366_670024-train-bf_000555-af_000902-plus-0000363",
"task": "Sort food",
"image": [
"images/agibotworld/366/669950/cam_high/frame_000025.jpg",
"images/agibotworld/366/669950/cam_high/frame_001145.jpg",
"images/agibotworld/366/670024/cam_high/frame_000555.jpg",
"images/agibotworld/366/670024/cam_left_wrist/frame_000555.jpg",
"images/agibotworld/366/670024/cam_right_wrist/frame_000555.jpg",
"images/agibotworld/366/670024/cam_high/frame_000902.jpg",
"images/agibotworld/366/670024/cam_left_wrist/frame_000902.jpg",
"images/agibotworld/366/670024/cam_right_wrist/frame_000902.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Sort food`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Sort food`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 53.3,
"hop_absolute_value": 53.3,
"hop_category": {
"absolute_category": "medium",
"direction": "progress",
"combined_category": "progress_medium"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_356_654636-train-bf_000415-af_000706-plus-0000453",
"task": "Packing in the supermarket",
"image": [
"images/agibotworld/356/649079/cam_high/frame_000008.jpg",
"images/agibotworld/356/649079/cam_high/frame_000854.jpg",
"images/agibotworld/356/654636/cam_high/frame_000415.jpg",
"images/agibotworld/356/654636/cam_left_wrist/frame_000415.jpg",
"images/agibotworld/356/654636/cam_right_wrist/frame_000415.jpg",
"images/agibotworld/356/654636/cam_high/frame_000706.jpg",
"images/agibotworld/356/654636/cam_left_wrist/frame_000706.jpg",
"images/agibotworld/356/654636/cam_right_wrist/frame_000706.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Packing in the supermarket`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Packing in the supermarket`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 82.4,
"hop_absolute_value": 82.4,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_440_747804-train-bf_000202-af_000486-plus-0000891",
"task": "Iron clothes",
"image": [
"images/agibotworld/440/696613/cam_high/frame_000000.jpg",
"images/agibotworld/440/696613/cam_high/frame_002346.jpg",
"images/agibotworld/440/747804/cam_high/frame_000202.jpg",
"images/agibotworld/440/747804/cam_left_wrist/frame_000202.jpg",
"images/agibotworld/440/747804/cam_right_wrist/frame_000202.jpg",
"images/agibotworld/440/747804/cam_high/frame_000486.jpg",
"images/agibotworld/440/747804/cam_left_wrist/frame_000486.jpg",
"images/agibotworld/440/747804/cam_right_wrist/frame_000486.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Iron clothes`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Iron clothes`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 13.3,
"hop_absolute_value": 13.3,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_508_763112-train-bf_001444-af_001473-plus-0000698",
"task": "Place items in the bag.",
"image": [
"images/agibotworld/508/763112/cam_high/frame_000000.jpg",
"images/agibotworld/508/763112/cam_high/frame_002031.jpg",
"images/agibotworld/508/763112/cam_high/frame_001444.jpg",
"images/agibotworld/508/763112/cam_left_wrist/frame_001444.jpg",
"images/agibotworld/508/763112/cam_right_wrist/frame_001444.jpg",
"images/agibotworld/508/763112/cam_high/frame_001473.jpg",
"images/agibotworld/508/763112/cam_left_wrist/frame_001473.jpg",
"images/agibotworld/508/763112/cam_right_wrist/frame_001473.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Place items in the bag.`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Place items in the bag.`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 5.9,
"hop_absolute_value": 5.9,
"hop_category": {
"absolute_category": "small",
"direction": "progress",
"combined_category": "progress_small"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_352_662346-train-bf_000670-af_001276-plus-0000441",
"task": "Open the fridge to get food.",
"image": [
"images/agibotworld/352/662346/cam_high/frame_000012.jpg",
"images/agibotworld/352/662346/cam_high/frame_001315.jpg",
"images/agibotworld/352/662346/cam_high/frame_000670.jpg",
"images/agibotworld/352/662346/cam_left_wrist/frame_000670.jpg",
"images/agibotworld/352/662346/cam_right_wrist/frame_000670.jpg",
"images/agibotworld/352/662346/cam_high/frame_001276.jpg",
"images/agibotworld/352/662346/cam_left_wrist/frame_001276.jpg",
"images/agibotworld/352/662346/cam_right_wrist/frame_001276.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Open the fridge to get food.`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Open the fridge to get food.`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 93.8,
"hop_absolute_value": 93.8,
"hop_category": {
"absolute_category": "large",
"direction": "progress",
"combined_category": "progress_large"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_510_767554-train-bf_000071-af_001114-plus-0000383",
"task": "Stack dishcloth on the kitchen countertop",
"image": [
"images/agibotworld/510/746437/cam_high/frame_000000.jpg",
"images/agibotworld/510/746437/cam_high/frame_002768.jpg",
"images/agibotworld/510/767554/cam_high/frame_000071.jpg",
"images/agibotworld/510/767554/cam_left_wrist/frame_000071.jpg",
"images/agibotworld/510/767554/cam_right_wrist/frame_000071.jpg",
"images/agibotworld/510/767554/cam_high/frame_001114.jpg",
"images/agibotworld/510/767554/cam_left_wrist/frame_001114.jpg",
"images/agibotworld/510/767554/cam_right_wrist/frame_001114.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Stack dishcloth on the kitchen countertop`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed): \n\n\nBEFORE Observation (Front, Left Wrist, Right Wrist):\n \n\nAFTER Observation (Front, Left Wrist, Right Wrist):\n \n\n### Goal\nCompare the BEFORE and AFTER image sets and judge whether AFTER is physically closer to the task objective than BEFORE, using the REFERENCE images as conceptual anchors.\n\n### Evaluation Criteria (Apply across all views)\n1) **Task Alignment**: Evidence must be directly tied to the objective of `Stack dishcloth on the kitchen countertop`.\n2) **Completeness & Accuracy**: Evaluate the quality of the execution, including correct pose, stable contact, placement accuracy, orientation, grasp quality, and the absence of collisions.\n3) **View-Specific Logic & Consistency**:\n - **Front View**: Use for global layout, object pose, approach path, and scene-level constraints.\n - **Wrist Views**: Use for **fine-grained details** such as gripper/hand engagement, contact area, slippage, micro-misalignment, object deformation, or unintended contact.\n - **Override Rule**: When views disagree, prioritize the view providing **decisive cues** (e.g., wrist views often override the front view for grasp validity or stable contact). \n - **Failure Rule**: If ANY single view shows a failure that invalidates success (e.g., a mis-grasp, a collision, or an unstable pose), this must be judged as regression.\n4) **Robustness**: Ignore irrelevant factors like lighting changes, color shifts, background clutter, or UI/watermarks that do not affect the physical task state.\n\n### Decision Logic\nYou must provide a binary judgment. No intermediate or zero scores are allowed:\n- **Output +1**: If the AFTER state shows clear progress, is more stable, or is physically closer to the objective than the BEFORE state.\n- **Output -1**: If the AFTER state shows regression, an error, a collision, or is physically further from the objective than the BEFORE state.\n\n### Output Format (STRICT)\nReturn ONLY the decision wrapped in tags:\n+1 or -1\n"
},
{
"from": "gpt",
"value": "+1"
}
],
"hop_value": 55.2,
"hop_absolute_value": 55.2,
"hop_category": {
"absolute_category": "medium",
"direction": "progress",
"combined_category": "progress_medium"
},
"image_dataset": "agibotworld"
},
{
"id": "agibot_547_842961-train-bf_001592-af_002567-plus-0000433",
"task": "Sort light and dark clothes",
"image": [
"images/agibotworld/547/845046/cam_high/frame_000000.jpg",
"images/agibotworld/547/845046/cam_high/frame_003406.jpg",
"images/agibotworld/547/842961/cam_high/frame_001592.jpg",
"images/agibotworld/547/842961/cam_left_wrist/frame_001592.jpg",
"images/agibotworld/547/842961/cam_right_wrist/frame_001592.jpg",
"images/agibotworld/547/842961/cam_high/frame_002567.jpg",
"images/agibotworld/547/842961/cam_left_wrist/frame_002567.jpg",
"images/agibotworld/547/842961/cam_right_wrist/frame_002567.jpg"
],
"conversations": [
{
"from": "human",
"value": "You are a rigorous and impartial vision evaluator specializing in physical manipulation tasks. Your goal is to determine the physical progress of a task by comparing two sets of observations.\n\n\n`Sort light and dark clothes`\n\nREFERENCE EXAMPLES (For anchoring the full task scope):\n- REFERENCE START (Task just beginning): \n- REFERENCE END (Task fully completed):