id
stringlengths 24
37
| image
imagewidth (px) 270
720
| conversations
listlengths 2
2
|
|---|---|---|
aitw_9441457734724982598_8 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: delete location history\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [UP]\nStep 2: Tap [SETTINGS Icon]\nStep 3: Tap [Location On-4 apps have access to location]\nStep 4: Tap [Advanced Emergency Location Service, Google Location Accuracy, Google Location Histo.]\nStep 5: Tap [Google Location History]\nStep 6: Tap [Auto-delete (On) activity older than Deleting 18 months]\nStep 7: Tap [Next]\n\nCurrent screenshot is labeled with 16 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 8) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 14}}"
}
]
|
|
aitw_9441457734724982598_9 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: delete location history\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [UP]\nStep 2: Tap [SETTINGS Icon]\nStep 3: Tap [Location On-4 apps have access to location]\nStep 4: Tap [Advanced Emergency Location Service, Google Location Accuracy, Google Location Histo.]\nStep 5: Tap [Google Location History]\nStep 6: Tap [Auto-delete (On) activity older than Deleting 18 months]\nStep 7: Tap [Next]\nStep 8: Tap [Got it]\n\nCurrent screenshot is labeled with 14 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 9) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"SET_TASK_STATUS\": \"COMPLETE\"}"
}
]
|
|
aitw_8350718829877308340_0 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: What's the weather going to be this weekend?\n\nPrevious actions:\nNone\n\nCurrent screenshot is labeled with 5 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 0) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"PRESS\": \"HOME\"}"
}
]
|
|
aitw_8350718829877308340_1 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: What's the weather going to be this weekend?\n\nPrevious actions:\nStep 0: Press [HOME]\n\nCurrent screenshot is labeled with 5 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 1) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"SWIPE\": \"RIGHT\"}"
}
]
|
|
aitw_8350718829877308340_2 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: What's the weather going to be this weekend?\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [RIGHT]\n\nCurrent screenshot is labeled with 9 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 2) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"PRESS\": \"HOME\"}"
}
]
|
|
aitw_8350718829877308340_3 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: What's the weather going to be this weekend?\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [RIGHT]\nStep 2: Press [HOME]\n\nCurrent screenshot is labeled with 5 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 3) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"NORMALIZED_COORDINATE\": [0.35, 0.95]}}"
}
]
|
|
aitw_8350718829877308340_4 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: What's the weather going to be this weekend?\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [RIGHT]\nStep 2: Press [HOME]\nStep 3: Tap [somewhere on the screen]\n\nCurrent screenshot is labeled with 18 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 4) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 9}}"
}
]
|
|
aitw_8350718829877308340_5 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: What's the weather going to be this weekend?\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [RIGHT]\nStep 2: Press [HOME]\nStep 3: Tap [somewhere on the screen]\nStep 4: Tap [weather]\n\nCurrent screenshot is labeled with 42 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 5) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 26}}"
}
]
|
|
aitw_8350718829877308340_6 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: What's the weather going to be this weekend?\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [RIGHT]\nStep 2: Press [HOME]\nStep 3: Tap [somewhere on the screen]\nStep 4: Tap [weather]\nStep 5: Tap [10 days]\n\nCurrent screenshot is labeled with 32 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 6) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 23}}"
}
]
|
|
aitw_8350718829877308340_7 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: What's the weather going to be this weekend?\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [RIGHT]\nStep 2: Press [HOME]\nStep 3: Tap [somewhere on the screen]\nStep 4: Tap [weather]\nStep 5: Tap [10 days]\nStep 6: Tap [Saturday. Jul 23 Partly cloudy]\n\nCurrent screenshot is labeled with 42 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 7) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"SET_TASK_STATUS\": \"COMPLETE\"}"
}
]
|
|
aitw_4498076626533904079_0 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: turn vacation reply on in the gmail app\n\nPrevious actions:\nNone\n\nCurrent screenshot is labeled with 25 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 0) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"PRESS\": \"HOME\"}"
}
]
|
|
aitw_4498076626533904079_1 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: turn vacation reply on in the gmail app\n\nPrevious actions:\nStep 0: Press [HOME]\n\nCurrent screenshot is labeled with 10 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 1) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"NORMALIZED_COORDINATE\": [0.5, 0.78]}}"
}
]
|
|
aitw_4498076626533904079_2 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: turn vacation reply on in the gmail app\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\n\nCurrent screenshot is labeled with 9 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 2) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 0}}"
}
]
|
|
aitw_4498076626533904079_3 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: turn vacation reply on in the gmail app\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\nStep 2: Tap [ARROW_BACKWARD Icon]\n\nCurrent screenshot is labeled with 15 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 3) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 0}}"
}
]
|
|
aitw_4498076626533904079_4 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: turn vacation reply on in the gmail app\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\nStep 2: Tap [ARROW_BACKWARD Icon]\nStep 3: Tap [ARROW_BACKWARD Icon]\n\nCurrent screenshot is labeled with 19 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 4) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 1}}"
}
]
|
|
aitw_4498076626533904079_5 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: turn vacation reply on in the gmail app\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\nStep 2: Tap [ARROW_BACKWARD Icon]\nStep 3: Tap [ARROW_BACKWARD Icon]\nStep 4: Tap [ARROW_BACKWARD Icon]\n\nCurrent screenshot is labeled with 9 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 5) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 7}}"
}
]
|
|
aitw_4498076626533904079_6 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: turn vacation reply on in the gmail app\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\nStep 2: Tap [ARROW_BACKWARD Icon]\nStep 3: Tap [ARROW_BACKWARD Icon]\nStep 4: Tap [ARROW_BACKWARD Icon]\nStep 5: Tap [tau.karenbrennan. [email protected]]\n\nCurrent screenshot is labeled with 19 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 6) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"SWIPE\": \"UP\"}"
}
]
|
|
aitw_4498076626533904079_7 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: turn vacation reply on in the gmail app\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\nStep 2: Tap [ARROW_BACKWARD Icon]\nStep 3: Tap [ARROW_BACKWARD Icon]\nStep 4: Tap [ARROW_BACKWARD Icon]\nStep 5: Tap [tau.karenbrennan. [email protected]]\nStep 6: Swipe [UP]\n\nCurrent screenshot is labeled with 18 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 7) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"SWIPE\": \"UP\"}"
}
]
|
|
aitw_4498076626533904079_8 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: turn vacation reply on in the gmail app\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\nStep 2: Tap [ARROW_BACKWARD Icon]\nStep 3: Tap [ARROW_BACKWARD Icon]\nStep 4: Tap [ARROW_BACKWARD Icon]\nStep 5: Tap [tau.karenbrennan. [email protected]]\nStep 6: Swipe [UP]\nStep 7: Swipe [UP]\n\nCurrent screenshot is labeled with 19 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 8) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 16}}"
}
]
|
|
aitw_4498076626533904079_9 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: turn vacation reply on in the gmail app\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\nStep 2: Tap [ARROW_BACKWARD Icon]\nStep 3: Tap [ARROW_BACKWARD Icon]\nStep 4: Tap [ARROW_BACKWARD Icon]\nStep 5: Tap [tau.karenbrennan. [email protected]]\nStep 6: Swipe [UP]\nStep 7: Swipe [UP]\nStep 8: Tap [Vacation responder On, from Jul Jul 8 to 15]\n\nCurrent screenshot is labeled with 18 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 9) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 8}}"
}
]
|
|
aitw_4498076626533904079_10 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: turn vacation reply on in the gmail app\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\nStep 2: Tap [ARROW_BACKWARD Icon]\nStep 3: Tap [ARROW_BACKWARD Icon]\nStep 4: Tap [ARROW_BACKWARD Icon]\nStep 5: Tap [tau.karenbrennan. [email protected]]\nStep 6: Swipe [UP]\nStep 7: Swipe [UP]\nStep 8: Tap [Vacation responder On, from Jul Jul 8 to 15]\nStep 9: Tap [DONE]\n\nCurrent screenshot is labeled with 19 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 10) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"SET_TASK_STATUS\": \"COMPLETE\"}"
}
]
|
|
aitw_10392700132576331581_0 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open internet settings\n\nPrevious actions:\nNone\n\nCurrent screenshot is labeled with 12 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 0) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"PRESS\": \"HOME\"}"
}
]
|
|
aitw_10392700132576331581_1 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open internet settings\n\nPrevious actions:\nStep 0: Press [HOME]\n\nCurrent screenshot is labeled with 5 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 1) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"SWIPE\": \"UP\"}"
}
]
|
|
aitw_10392700132576331581_2 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open internet settings\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [UP]\n\nCurrent screenshot is labeled with 11 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 2) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"NORMALIZED_COORDINATE\": [0.52, 0.55]}}"
}
]
|
|
aitw_10392700132576331581_3 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open internet settings\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [UP]\nStep 2: Tap [somewhere on the screen]\n\nCurrent screenshot is labeled with 7 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 3) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"SWIPE\": \"UP\"}"
}
]
|
|
aitw_10392700132576331581_4 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open internet settings\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [UP]\nStep 2: Tap [somewhere on the screen]\nStep 3: Swipe [UP]\n\nCurrent screenshot is labeled with 32 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 4) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 2}}"
}
]
|
|
aitw_10392700132576331581_5 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open internet settings\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [UP]\nStep 2: Tap [somewhere on the screen]\nStep 3: Swipe [UP]\nStep 4: Tap [SETTINGS Icon]\n\nCurrent screenshot is labeled with 21 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 5) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 8}}"
}
]
|
|
aitw_10392700132576331581_6 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open internet settings\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [UP]\nStep 2: Tap [somewhere on the screen]\nStep 3: Swipe [UP]\nStep 4: Tap [SETTINGS Icon]\nStep 5: Tap [Network 8 internet W-F, mabile data usage, and hotspat]\n\nCurrent screenshot is labeled with 10 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 6) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"NORMALIZED_COORDINATE\": [0.46, 0.16]}}"
}
]
|
|
aitw_10392700132576331581_7 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open internet settings\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Swipe [UP]\nStep 2: Tap [somewhere on the screen]\nStep 3: Swipe [UP]\nStep 4: Tap [SETTINGS Icon]\nStep 5: Tap [Network 8 internet W-F, mabile data usage, and hotspat]\nStep 6: Tap [somewhere on the screen]\n\nCurrent screenshot is labeled with 16 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 7) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"SET_TASK_STATUS\": \"COMPLETE\"}"
}
]
|
|
aitw_4296210948433018711_0 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Do I have any events this weekend?\n\nPrevious actions:\nNone\n\nCurrent screenshot is labeled with 6 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 0) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"SWIPE\": \"UP\"}"
}
]
|
|
aitw_4296210948433018711_1 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Do I have any events this weekend?\n\nPrevious actions:\nStep 0: Swipe [UP]\n\nCurrent screenshot is labeled with 5 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 1) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"PRESS\": \"HOME\"}"
}
]
|
|
aitw_4296210948433018711_2 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Do I have any events this weekend?\n\nPrevious actions:\nStep 0: Swipe [UP]\nStep 1: Press [HOME]\n\nCurrent screenshot is labeled with 6 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 2) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 4}}"
}
]
|
|
aitw_4296210948433018711_3 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Do I have any events this weekend?\n\nPrevious actions:\nStep 0: Swipe [UP]\nStep 1: Press [HOME]\nStep 2: Tap [Tuesday, Jul 12]\n\nCurrent screenshot is labeled with 18 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 3) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 3}}"
}
]
|
|
aitw_4296210948433018711_4 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Do I have any events this weekend?\n\nPrevious actions:\nStep 0: Swipe [UP]\nStep 1: Press [HOME]\nStep 2: Tap [Tuesday, Jul 12]\nStep 3: Tap [V_DOWNWARD Icon]\n\nCurrent screenshot is labeled with 25 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 4) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"NORMALIZED_COORDINATE\": [0.9, 0.25]}}"
}
]
|
|
aitw_4296210948433018711_5 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Do I have any events this weekend?\n\nPrevious actions:\nStep 0: Swipe [UP]\nStep 1: Press [HOME]\nStep 2: Tap [Tuesday, Jul 12]\nStep 3: Tap [V_DOWNWARD Icon]\nStep 4: Tap [somewhere on the screen]\n\nCurrent screenshot is labeled with 29 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 5) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"SET_TASK_STATUS\": \"COMPLETE\"}"
}
]
|
|
aitw_4560029395630734637_0 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open Reddit.com\n\nPrevious actions:\nNone\n\nCurrent screenshot is labeled with 26 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 0) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"PRESS\": \"HOME\"}"
}
]
|
|
aitw_4560029395630734637_1 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open Reddit.com\n\nPrevious actions:\nStep 0: Press [HOME]\n\nCurrent screenshot is labeled with 12 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 1) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"NORMALIZED_COORDINATE\": [0.74, 0.8]}}"
}
]
|
|
aitw_4560029395630734637_2 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open Reddit.com\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\n\nCurrent screenshot is labeled with 13 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 2) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 7}}"
}
]
|
|
aitw_4560029395630734637_3 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open Reddit.com\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\nStep 2: Tap [en.m.wikipedia.org/wiki/Main]\n\nCurrent screenshot is labeled with 11 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 3) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TYPE\": \"reddit.com\"}"
}
]
|
|
aitw_4560029395630734637_4 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open Reddit.com\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\nStep 2: Tap [en.m.wikipedia.org/wiki/Main]\nStep 3: Type [reddit.com]\n\nCurrent screenshot is labeled with 11 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 4) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"TAP\": {\"MARK\": 6}}"
}
]
|
|
aitw_4560029395630734637_5 | [
{
"from": "user",
"value": "<image>\nImagine you are interacting with an Android device step by step. You can see the screen and know the previous actions through recorded history. The screenshots are labeled with bounding boxes and numeric marks to guide your interactions. Your task is to determine the next action to perform. The possible actions include tapping, swiping, navigating, typing, or setting the task status.\n\nUse the following format for your output, selecting the appropriate key-value pair:\n```json\n{\n \"TAP\": dict, // Use {\"MARK\": mark_index} where `mark_index` is an integer corresponding to the bounding box on the screen, or {\"NORMALIZED_COORDINATE\": [x, y]} where `x` and `y` are float numbers between 0 and 1 representing the normalized coordinates on the screen.\n \"SWIPE\": str, // Choose \"UP\", \"DOWN\", \"LEFT\", or \"RIGHT\"\n \"NAVIGATE\": str, // Choose \"BACK\", \"HOME\", or \"ENTER\"\n \"TYPE\": str, // The text to be typed\n \"SET_TASK_STATUS\": str, // Choose \"COMPLETE\" or \"IMPOSSIBLE\"\n}\n```\n\nCurrent task: Open Reddit.com\n\nPrevious actions:\nStep 0: Press [HOME]\nStep 1: Tap [somewhere on the screen]\nStep 2: Tap [en.m.wikipedia.org/wiki/Main]\nStep 3: Type [reddit.com]\nStep 4: Tap [Reddit - Dive into anything reddit.com]\n\nCurrent screenshot is labeled with 31 bounding boxes and numeric marks to guide your interactions. Determine your next action (Step 5) and provide the output in the specified dictionary format."
},
{
"from": "assistant",
"value": "{\"SET_TASK_STATUS\": \"COMPLETE\"}"
}
]
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.