Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed
Error code: DatasetGenerationError
Exception: TypeError
Message: Couldn't cast array of type
struct<trajectory_id: string, task_id: string, source: string, run: string, success: bool, score: double, num_steps: int64, split: string, replica: int64, step: int64>
to
{'trajectory_id': Value('string'), 'task_id': Value('string'), 'source': Value('string'), 'run': Value('string'), 'success': Value('bool'), 'score': Value('float64'), 'num_steps': Value('int64'), 'split': Value('string'), 'replica': Value('int64')}
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1827, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 613, in wrapped
for item in generator(*args, **kwargs):
~~~~~~~~~^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 343, in _generate_tables
self._cast_table(pa_table, json_field_paths=json_field_paths),
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 132, in _cast_table
pa_table = table_cast(pa_table, self.info.features.arrow_schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2378, in table_cast
return cast_table_to_schema(table, schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2312, in cast_table_to_schema
cast_array_to_feature(
~~~~~~~~~~~~~~~~~~~~~^
table[name] if name in table_column_names else pa.array([None] * len(table), type=schema.field(name).type),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
feature,
^^^^^^^^
)
^
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 1861, in wrapper
return pa.chunked_array([func(chunk, *args, **kwargs) for chunk in array.chunks])
~~~~^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2158, in cast_array_to_feature
raise TypeError(f"Couldn't cast array of type\n{_short_str(array.type)}\nto\n{_short_str(feature)}")
TypeError: Couldn't cast array of type
struct<trajectory_id: string, task_id: string, source: string, run: string, success: bool, score: double, num_steps: int64, split: string, replica: int64, step: int64>
to
{'trajectory_id': Value('string'), 'task_id': Value('string'), 'source': Value('string'), 'run': Value('string'), 'success': Value('bool'), 'score': Value('float64'), 'num_steps': Value('int64'), 'split': Value('string'), 'replica': Value('int64')}
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1369, in compute_config_parquet_and_info_response
parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
~~~~~~~~~~~~~~~~~~~~~~~~~^
builder, max_dataset_size_bytes=max_dataset_size_bytes
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 948, in stream_convert_to_parquet
builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1694, in _prepare_split
for job_id, done, content in self._prepare_split_single(
~~~~~~~~~~~~~~~~~~~~~~~~~~^
gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
):
^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1880, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.exceptions.DatasetGenerationError: An error occurred while generating the datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
id string | messages list | images list | label float64 | metadata dict |
|---|---|---|---|---|
nothinking/run_1/AcceptMeetingTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/AcceptMeetingTask/AcceptMeetingTask-0-5.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/AcceptMeetingTask",
"task_id": "AcceptMeetingTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 5,
"split": "train",
"replica": 0
} |
nothinking/run_1/AdjustBrightnessMaximumTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/AdjustBrightnessMaximumTask/AdjustBrightnessMaximumTask-0-5.png"
] | 1 | {
"trajectory_id": "nothinking/run_1/AdjustBrightnessMaximumTask",
"task_id": "AdjustBrightnessMaximumTask",
"source": "nothinking",
"run": "run_1",
"success": true,
"score": 1,
"num_steps": 5,
"split": "train",
"replica": 0
} |
nothinking/run_1/AdjustBrightnessMinimumTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/AdjustBrightnessMinimumTask/AdjustBrightnessMinimumTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/AdjustBrightnessMinimumTask",
"task_id": "AdjustBrightnessMinimumTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/AdjustFontIconMaximumTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/AdjustFontIconMaximumTask/AdjustFontIconMaximumTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/AdjustFontIconMaximumTask",
"task_id": "AdjustFontIconMaximumTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/AdjustFontIconMinimumTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/AdjustFontIconMinimumTask/AdjustFontIconMinimumTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/AdjustFontIconMinimumTask",
"task_id": "AdjustFontIconMinimumTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/BidFileRenameAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/BidFileRenameAskUserTask/BidFileRenameAskUserTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/BidFileRenameAskUserTask",
"task_id": "BidFileRenameAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/BuyBlackTennisShoesBrotherAddressAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/BuyBlackTennisShoesBrotherAddressAskUserTask/BuyBlackTennisShoesBrotherAddressAskUserTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/BuyBlackTennisShoesBrotherAddressAskUserTask",
"task_id": "BuyBlackTennisShoesBrotherAddressAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/BuySugarFreeColaWorkAddressAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/BuySugarFreeColaWorkAddressAskUserTask/BuySugarFreeColaWorkAddressAskUserTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/BuySugarFreeColaWorkAddressAskUserTask",
"task_id": "BuySugarFreeColaWorkAddressAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/CancelMeetingTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CancelMeetingTask/CancelMeetingTask-0-5.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CancelMeetingTask",
"task_id": "CancelMeetingTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 5,
"split": "train",
"replica": 0
} |
nothinking/run_1/ChangeWallpaperTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/ChangeWallpaperTask/ChangeWallpaperTask-0-6.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/ChangeWallpaperTask",
"task_id": "ChangeWallpaperTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 6,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckConferenceAndSendSmsTask1 | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckConferenceAndSendSmsTask1/CheckConferenceAndSendSmsTask1-0-11.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckConferenceAndSendSmsTask1",
"task_id": "CheckConferenceAndSendSmsTask1",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 11,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckConferenceAndSendSmsTask2 | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckConferenceAndSendSmsTask2/CheckConferenceAndSendSmsTask2-0-11.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckConferenceAndSendSmsTask2",
"task_id": "CheckConferenceAndSendSmsTask2",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 11,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckConferenceLocationTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckConferenceLocationTask/CheckConferenceLocationTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckConferenceLocationTask",
"task_id": "CheckConferenceLocationTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckDistanceAskUserTask1 | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckDistanceAskUserTask1/CheckDistanceAskUserTask1-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckDistanceAskUserTask1",
"task_id": "CheckDistanceAskUserTask1",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckEventAndSetAlarmAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckEventAndSetAlarmAskUserTask/CheckEventAndSetAlarmAskUserTask-0-10.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckEventAndSetAlarmAskUserTask",
"task_id": "CheckEventAndSetAlarmAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 10,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckEventTimeTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckEventTimeTask/CheckEventTimeTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckEventTimeTask",
"task_id": "CheckEventTimeTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckInterviewTimesTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckInterviewTimesTask/CheckInterviewTimesTask-0-16.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckInterviewTimesTask",
"task_id": "CheckInterviewTimesTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 16,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckInvoiceTask1 | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckInvoiceTask1/CheckInvoiceTask1-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckInvoiceTask1",
"task_id": "CheckInvoiceTask1",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckInvoiceTask2 | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckInvoiceTask2/CheckInvoiceTask2-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckInvoiceTask2",
"task_id": "CheckInvoiceTask2",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckInvoiceTask3 | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckInvoiceTask3/CheckInvoiceTask3-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckInvoiceTask3",
"task_id": "CheckInvoiceTask3",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckInvoiceTask4AskUser | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckInvoiceTask4AskUser/CheckInvoiceTask4AskUser-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckInvoiceTask4AskUser",
"task_id": "CheckInvoiceTask4AskUser",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckMealEventAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckMealEventAskUserTask/CheckMealEventAskUserTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckMealEventAskUserTask",
"task_id": "CheckMealEventAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckMeetingEventAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckMeetingEventAskUserTask/CheckMeetingEventAskUserTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CheckMeetingEventAskUserTask",
"task_id": "CheckMeetingEventAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/CheckRegistrationTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CheckRegistrationTask/CheckRegistrationTask-0-12.png"
] | 1 | {
"trajectory_id": "nothinking/run_1/CheckRegistrationTask",
"task_id": "CheckRegistrationTask",
"source": "nothinking",
"run": "run_1",
"success": true,
"score": 1,
"num_steps": 12,
"split": "train",
"replica": 0
} |
nothinking/run_1/ChromeSearchBeijingWeatherAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/ChromeSearchBeijingWeatherAskUserTask/ChromeSearchBeijingWeatherAskUserTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/ChromeSearchBeijingWeatherAskUserTask",
"task_id": "ChromeSearchBeijingWeatherAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/ChromeSearchBeijingWeatherTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/ChromeSearchBeijingWeatherTask/ChromeSearchBeijingWeatherTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/ChromeSearchBeijingWeatherTask",
"task_id": "ChromeSearchBeijingWeatherTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/CloseFlightModeTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CloseFlightModeTask/CloseFlightModeTask-0-5.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CloseFlightModeTask",
"task_id": "CloseFlightModeTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 5,
"split": "train",
"replica": 0
} |
nothinking/run_1/CountFileLinesTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/CountFileLinesTask/CountFileLinesTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/CountFileLinesTask",
"task_id": "CountFileLinesTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/DeleteAllMessagesAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/DeleteAllMessagesAskUserTask/DeleteAllMessagesAskUserTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/DeleteAllMessagesAskUserTask",
"task_id": "DeleteAllMessagesAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/DeleteEventAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/DeleteEventAskUserTask/DeleteEventAskUserTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/DeleteEventAskUserTask",
"task_id": "DeleteEventAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/DeleteItemsAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/DeleteItemsAskUserTask/DeleteItemsAskUserTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/DeleteItemsAskUserTask",
"task_id": "DeleteItemsAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/DeleteMessagesAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/DeleteMessagesAskUserTask/DeleteMessagesAskUserTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/DeleteMessagesAskUserTask",
"task_id": "DeleteMessagesAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/GoogleMapsAlibabaPhoneContactTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/GoogleMapsAlibabaPhoneContactTask/GoogleMapsAlibabaPhoneContactTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/GoogleMapsAlibabaPhoneContactTask",
"task_id": "GoogleMapsAlibabaPhoneContactTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/GoogleMapsAlibabaSouthNeighborAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/GoogleMapsAlibabaSouthNeighborAskUserTask/GoogleMapsAlibabaSouthNeighborAskUserTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/GoogleMapsAlibabaSouthNeighborAskUserTask",
"task_id": "GoogleMapsAlibabaSouthNeighborAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/GoogleMapsAlibabaSouthNeighborTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/GoogleMapsAlibabaSouthNeighborTask/GoogleMapsAlibabaSouthNeighborTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/GoogleMapsAlibabaSouthNeighborTask",
"task_id": "GoogleMapsAlibabaSouthNeighborTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/GraduationMassEmailTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/GraduationMassEmailTask/GraduationMassEmailTask-0-40.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/GraduationMassEmailTask",
"task_id": "GraduationMassEmailTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 40,
"split": "train",
"replica": 0
} |
nothinking/run_1/InvoiceReceiptCopyTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/InvoiceReceiptCopyTask/InvoiceReceiptCopyTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/InvoiceReceiptCopyTask",
"task_id": "InvoiceReceiptCopyTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/LocalFileManagementTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/LocalFileManagementTask/LocalFileManagementTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/LocalFileManagementTask",
"task_id": "LocalFileManagementTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/LocalFileManagementTask2 | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/LocalFileManagementTask2/LocalFileManagementTask2-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/LocalFileManagementTask2",
"task_id": "LocalFileManagementTask2",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonAddBookmarkTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonAddBookmarkTask/MastodonAddBookmarkTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonAddBookmarkTask",
"task_id": "MastodonAddBookmarkTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonAddFeaturedHashtagsTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonAddFeaturedHashtagsTask/MastodonAddFeaturedHashtagsTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonAddFeaturedHashtagsTask",
"task_id": "MastodonAddFeaturedHashtagsTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonAdjustTootsTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonAdjustTootsTask/MastodonAdjustTootsTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonAdjustTootsTask",
"task_id": "MastodonAdjustTootsTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonCalendarMultiMemosTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonCalendarMultiMemosTask/MastodonCalendarMultiMemosTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonCalendarMultiMemosTask",
"task_id": "MastodonCalendarMultiMemosTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonChangeHeaderTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonChangeHeaderTask/MastodonChangeHeaderTask-0-7.png"
] | 1 | {
"trajectory_id": "nothinking/run_1/MastodonChangeHeaderTask",
"task_id": "MastodonChangeHeaderTask",
"source": "nothinking",
"run": "run_1",
"success": true,
"score": 1,
"num_steps": 7,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonChangeLanguageTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonChangeLanguageTask/MastodonChangeLanguageTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonChangeLanguageTask",
"task_id": "MastodonChangeLanguageTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonCreateListTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonCreateListTask/MastodonCreateListTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonCreateListTask",
"task_id": "MastodonCreateListTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonCreateMemoTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonCreateMemoTask/MastodonCreateMemoTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonCreateMemoTask",
"task_id": "MastodonCreateMemoTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonDumpImgAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonDumpImgAskUserTask/MastodonDumpImgAskUserTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonDumpImgAskUserTask",
"task_id": "MastodonDumpImgAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonDumpQcodeAskUserTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonDumpQcodeAskUserTask/MastodonDumpQcodeAskUserTask-0-9.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonDumpQcodeAskUserTask",
"task_id": "MastodonDumpQcodeAskUserTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 9,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonExportFollowsTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonExportFollowsTask/MastodonExportFollowsTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonExportFollowsTask",
"task_id": "MastodonExportFollowsTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonFavoriteTootsTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonFavoriteTootsTask/MastodonFavoriteTootsTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonFavoriteTootsTask",
"task_id": "MastodonFavoriteTootsTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonFilterLanguageTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonFilterLanguageTask/MastodonFilterLanguageTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonFilterLanguageTask",
"task_id": "MastodonFilterLanguageTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonFollowTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonFollowTask/MastodonFollowTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonFollowTask",
"task_id": "MastodonFollowTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonGetServerInfoTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonGetServerInfoTask/MastodonGetServerInfoTask-0-11.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonGetServerInfoTask",
"task_id": "MastodonGetServerInfoTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 11,
"split": "train",
"replica": 0
} |
nothinking/run_1/MastodonImportMutedUsersTask | [
{
"role": "system",
"content": "You are an expert evaluator of mobile-device task execution. Given a task goal,\nthe actions already taken, and the current screenshot, assess the execution\nusing the following criterion:\n\nJudge final task success as a scalar: 0 for failure and 1 for success.\n\nBase the s... | [
"images/nothinking/run_1/MastodonImportMutedUsersTask/MastodonImportMutedUsersTask-0-50.png"
] | 0 | {
"trajectory_id": "nothinking/run_1/MastodonImportMutedUsersTask",
"task_id": "MastodonImportMutedUsersTask",
"source": "nothinking",
"run": "run_1",
"success": false,
"score": 0,
"num_steps": 50,
"split": "train",
"replica": 0
} |
End of preview.
MobileWorld ProgRM Rollouts
Private training release containing multimodal ProgRM and ORM data derived from MobileWorld rollouts. The release is intended for reward-model training and subsequent reinforcement-learning research.
Release
- Version:
v1.0.0 - ProgRM code commit:
875ba94c74a9742e903acaa81895f5685de7eac1on branchmobileworld - Tasks: 161
- Canonical trajectories: 966
- Splits: {"test": 161, "train": 644, "val": 161}
- Screenshot shards: 11
Run scripts/prepare_mobileworld_hf_dataset.py from the ProgRM repository to
download, verify, extract, and materialize absolute image paths for MS-SWIFT.
Contents
data/progrm: step-level progress-regression JSONL.data/orm: trajectory-level outcome-regression JSONL.manifests: selection, rejection, statistics, and data-integrity metadata.source_trajectories.jsonl: canonical trajectories with runtime logs and token metadata removed.shards: deterministictar.zstarchives containing raw screenshots.
Each training row follows the MS-SWIFT multimodal sequence-classification
format with messages, one relative path in images, and a scalar label.
Labels and limitations
Successful ProgRM trajectories use linear labels from 0 to 1. Failed trajectories are labelled 0 at every step because the rollout only provides a terminal binary evaluator result. ORM labels are terminal success values. Forty-eight tasks have only failed trajectories and three have only successful trajectories. Ask-user values and UI contents are generated inside the MobileWorld benchmark; they may resemble email addresses or phone numbers. The dataset is private and must be reviewed before any public release.
License
MobileWorld is distributed under Apache-2.0. This derived rollout release uses the same license and should retain attribution to the MobileWorld project.
- Downloads last month
- 89