| {"id": "bank_statement_fin_001_p1_classify", "task": "classify", "class": "bank_statement", "doc": "bank_statement_fin_001.pdf", "images": ["images/val/bank_statement/bank_statement_fin_001_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"bank_statement\", \"confidence\": 1.0, \"issuer\": \"HSBC\", \"holder\": \"ORLANDO DEVONTRE REAMES\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_001_extract", "task": "extract", "class": "bank_statement", "doc": "bank_statement_fin_001.pdf", "images": ["images/val/bank_statement/bank_statement_fin_001_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('bank_statement', 'The document class.')\nfields = (['account_holder_name', 'bank_name', 'statement_period_start', 'statement_period_end', 'ending_balance', 'address', 'bank_account_type', 'bank_account_number', 'transaction_amount', 'transaction_date', 'transaction_type', 'transaction_sender'], 'The exact field names to extract.')\nhints = ({'account_holder_name': 'Name on the account', 'bank_name': 'Name of the bank', 'statement_period_start': 'Start of statement period', 'statement_period_end': 'End of statement period', 'ending_balance': 'Closing balance for the period', 'address': 'Address of the account holder', 'bank_account_type': 'Type of bank account - Checking/Saving', 'bank_account_number': 'Bank account number', 'transaction_amount': 'Transaction amount', 'transaction_date': 'Transaction date', 'transaction_type': 'Transaction type', 'transaction_sender': 'Transaction sender'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"account_holder_name\", \"value\": \"ORLANDO DEVONTRE REAMES\"}, {\"field\": \"bank_name\", \"value\": \"HSBC\"}, {\"field\": \"statement_period_start\", \"value\": \"2024-08-11\"}, {\"field\": \"statement_period_end\", \"value\": \"2024-08-22\"}, {\"field\": \"ending_balance\", \"value\": \"3100.0\"}, {\"field\": \"address\", \"value\": \"5509 Birch St Schofield WI 54476\"}, {\"field\": \"bank_account_type\", \"value\": \"CURRENT / EUROPEAN CURRENCY\"}, {\"field\": \"bank_account_number\", \"value\": \"00990274\"}, {\"field\": \"transaction_amount\", \"value\": \"1000.0\"}, {\"field\": \"transaction_date\", \"value\": \"2024-08-11\"}, {\"field\": \"transaction_type\", \"value\": \"Credit\"}, {\"field\": \"transaction_sender\", \"value\": \"IBM Uk\"}]}"}]} | |
| {"id": "bank_statement_fin_014_p1_classify", "task": "classify", "class": "bank_statement", "doc": "bank_statement_fin_014.pdf", "images": ["images/val/bank_statement/bank_statement_fin_014_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"bank_statement\", \"confidence\": 1.0, \"issuer\": \"HSBC\", \"holder\": \"ANTHONY CEDRONE\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_014_extract", "task": "extract", "class": "bank_statement", "doc": "bank_statement_fin_014.pdf", "images": ["images/val/bank_statement/bank_statement_fin_014_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('bank_statement', 'The document class.')\nfields = (['account_holder_name', 'bank_name', 'statement_period_start', 'statement_period_end', 'ending_balance', 'address', 'bank_account_type', 'bank_account_number', 'transaction_amount', 'transaction_date', 'transaction_type', 'transaction_sender'], 'The exact field names to extract.')\nhints = ({'account_holder_name': 'Name on the account', 'bank_name': 'Name of the bank', 'statement_period_start': 'Start of statement period', 'statement_period_end': 'End of statement period', 'ending_balance': 'Closing balance for the period', 'address': 'Address of the account holder', 'bank_account_type': 'Type of bank account - Checking/Saving', 'bank_account_number': 'Bank account number', 'transaction_amount': 'Transaction amount', 'transaction_date': 'Transaction date', 'transaction_type': 'Transaction type', 'transaction_sender': 'Transaction sender'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"account_holder_name\", \"value\": \"ANTHONY CEDRONE\"}, {\"field\": \"bank_name\", \"value\": \"HSBC\"}, {\"field\": \"statement_period_start\", \"value\": \"\"}, {\"field\": \"statement_period_end\", \"value\": \"\"}, {\"field\": \"ending_balance\", \"value\": \"3345.0\"}, {\"field\": \"address\", \"value\": \"1415 MADRID TRACE, SAN MARCOS, TX 78666\"}, {\"field\": \"bank_account_type\", \"value\": \"Checking\"}, {\"field\": \"bank_account_number\", \"value\": \"00884516\"}, {\"field\": \"transaction_amount\", \"value\": \"3.56\"}, {\"field\": \"transaction_date\", \"value\": \"2024-11-11\"}, {\"field\": \"transaction_type\", \"value\": \"Credit\"}, {\"field\": \"transaction_sender\", \"value\": \"AMAZON DIGITAL SER\"}]}"}]} | |
| {"id": "bank_statement_fin_015_p1_classify", "task": "classify", "class": "bank_statement", "doc": "bank_statement_fin_015.pdf", "images": ["images/val/bank_statement/bank_statement_fin_015_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"bank_statement\", \"confidence\": 1.0, \"issuer\": \"DBS\", \"holder\": \"KUMAR KULDEEP\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_015_extract", "task": "extract", "class": "bank_statement", "doc": "bank_statement_fin_015.pdf", "images": ["images/val/bank_statement/bank_statement_fin_015_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('bank_statement', 'The document class.')\nfields = (['account_holder_name', 'bank_name', 'statement_period_start', 'statement_period_end', 'ending_balance', 'address', 'bank_account_type', 'bank_account_number', 'transaction_amount', 'transaction_date', 'transaction_type', 'transaction_sender'], 'The exact field names to extract.')\nhints = ({'account_holder_name': 'Name on the account', 'bank_name': 'Name of the bank', 'statement_period_start': 'Start of statement period', 'statement_period_end': 'End of statement period', 'ending_balance': 'Closing balance for the period', 'address': 'Address of the account holder', 'bank_account_type': 'Type of bank account - Checking/Saving', 'bank_account_number': 'Bank account number', 'transaction_amount': 'Transaction amount', 'transaction_date': 'Transaction date', 'transaction_type': 'Transaction type', 'transaction_sender': 'Transaction sender'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"account_holder_name\", \"value\": \"KUMAR KULDEEP\"}, {\"field\": \"bank_name\", \"value\": \"DBS\"}, {\"field\": \"statement_period_start\", \"value\": \"\"}, {\"field\": \"statement_period_end\", \"value\": \"2022-01-31\"}, {\"field\": \"ending_balance\", \"value\": \"9754.64\"}, {\"field\": \"address\", \"value\": \"BLK 59 STRATHMORE AVE #24-97 SINGAPORE 142059\"}, {\"field\": \"bank_account_type\", \"value\": \"Saving\"}, {\"field\": \"bank_account_number\", \"value\": \"271-301841-7\"}, {\"field\": \"transaction_amount\", \"value\": \"\"}, {\"field\": \"transaction_date\", \"value\": \"\"}, {\"field\": \"transaction_type\", \"value\": \"\"}, {\"field\": \"transaction_sender\", \"value\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_020_p1_classify", "task": "classify", "class": "bank_statement", "doc": "bank_statement_fin_020.pdf", "images": ["images/val/bank_statement/bank_statement_fin_020_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"bank_statement\", \"confidence\": 1.0, \"issuer\": \"FIRST CITIZENS BANK\", \"holder\": \"John Smith\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_020_extract", "task": "extract", "class": "bank_statement", "doc": "bank_statement_fin_020.pdf", "images": ["images/val/bank_statement/bank_statement_fin_020_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('bank_statement', 'The document class.')\nfields = (['account_holder_name', 'bank_name', 'statement_period_start', 'statement_period_end', 'ending_balance', 'address', 'bank_account_type', 'bank_account_number', 'transaction_amount', 'transaction_date', 'transaction_type', 'transaction_sender'], 'The exact field names to extract.')\nhints = ({'account_holder_name': 'Name on the account', 'bank_name': 'Name of the bank', 'statement_period_start': 'Start of statement period', 'statement_period_end': 'End of statement period', 'ending_balance': 'Closing balance for the period', 'address': 'Address of the account holder', 'bank_account_type': 'Type of bank account - Checking/Saving', 'bank_account_number': 'Bank account number', 'transaction_amount': 'Transaction amount', 'transaction_date': 'Transaction date', 'transaction_type': 'Transaction type', 'transaction_sender': 'Transaction sender'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"account_holder_name\", \"value\": \"John Smith\"}, {\"field\": \"bank_name\", \"value\": \"FIRST CITIZENS BANK\"}, {\"field\": \"statement_period_start\", \"value\": \"\"}, {\"field\": \"statement_period_end\", \"value\": \"\"}, {\"field\": \"ending_balance\", \"value\": \"591800.0\"}, {\"field\": \"address\", \"value\": \"2450 Courage St, STE 108, Brownsville, TX 78521\"}, {\"field\": \"bank_account_type\", \"value\": \"\"}, {\"field\": \"bank_account_number\", \"value\": \"111-234-567-890\"}, {\"field\": \"transaction_amount\", \"value\": \"\"}, {\"field\": \"transaction_date\", \"value\": \"\"}, {\"field\": \"transaction_type\", \"value\": \"\"}, {\"field\": \"transaction_sender\", \"value\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_021_p1_classify", "task": "classify", "class": "bank_statement", "doc": "bank_statement_fin_021.pdf", "images": ["images/val/bank_statement/bank_statement_fin_021_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"bank_statement\", \"confidence\": 1.0, \"issuer\": \"Bickslow Bank\", \"holder\": \"Bit Manufacturing Ltd\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_021_extract", "task": "extract", "class": "bank_statement", "doc": "bank_statement_fin_021.pdf", "images": ["images/val/bank_statement/bank_statement_fin_021_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('bank_statement', 'The document class.')\nfields = (['account_holder_name', 'bank_name', 'statement_period_start', 'statement_period_end', 'ending_balance', 'address', 'bank_account_type', 'bank_account_number', 'transaction_amount', 'transaction_date', 'transaction_type', 'transaction_sender'], 'The exact field names to extract.')\nhints = ({'account_holder_name': 'Name on the account', 'bank_name': 'Name of the bank', 'statement_period_start': 'Start of statement period', 'statement_period_end': 'End of statement period', 'ending_balance': 'Closing balance for the period', 'address': 'Address of the account holder', 'bank_account_type': 'Type of bank account - Checking/Saving', 'bank_account_number': 'Bank account number', 'transaction_amount': 'Transaction amount', 'transaction_date': 'Transaction date', 'transaction_type': 'Transaction type', 'transaction_sender': 'Transaction sender'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"account_holder_name\", \"value\": \"Bit Manufacturing Ltd\"}, {\"field\": \"bank_name\", \"value\": \"Bickslow Bank\"}, {\"field\": \"statement_period_start\", \"value\": \"\"}, {\"field\": \"statement_period_end\", \"value\": \"\"}, {\"field\": \"ending_balance\", \"value\": \"5799.64\"}, {\"field\": \"address\", \"value\": \"2450 Courage St, STE 108, Brownsville, TX 78521\"}, {\"field\": \"bank_account_type\", \"value\": \"\"}, {\"field\": \"bank_account_number\", \"value\": \"111-234-567-890\"}, {\"field\": \"transaction_amount\", \"value\": \"\"}, {\"field\": \"transaction_date\", \"value\": \"\"}, {\"field\": \"transaction_type\", \"value\": \"\"}, {\"field\": \"transaction_sender\", \"value\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_027_p1_classify", "task": "classify", "class": "bank_statement", "doc": "bank_statement_fin_027.pdf", "images": ["images/val/bank_statement/bank_statement_fin_027_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"bank_statement\", \"confidence\": 1.0, \"issuer\": \"DBS Bank Ltd\", \"holder\": \"JOHN CITIZEN\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_027_extract", "task": "extract", "class": "bank_statement", "doc": "bank_statement_fin_027.pdf", "images": ["images/val/bank_statement/bank_statement_fin_027_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('bank_statement', 'The document class.')\nfields = (['account_holder_name', 'bank_name', 'statement_period_start', 'statement_period_end', 'ending_balance', 'address', 'bank_account_type', 'bank_account_number', 'transaction_amount', 'transaction_date', 'transaction_type', 'transaction_sender'], 'The exact field names to extract.')\nhints = ({'account_holder_name': 'Name on the account', 'bank_name': 'Name of the bank', 'statement_period_start': 'Start of statement period', 'statement_period_end': 'End of statement period', 'ending_balance': 'Closing balance for the period', 'address': 'Address of the account holder', 'bank_account_type': 'Type of bank account - Checking/Saving', 'bank_account_number': 'Bank account number', 'transaction_amount': 'Transaction amount', 'transaction_date': 'Transaction date', 'transaction_type': 'Transaction type', 'transaction_sender': 'Transaction sender'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"account_holder_name\", \"value\": \"JOHN CITIZEN\"}, {\"field\": \"bank_name\", \"value\": \"DBS Bank Ltd\"}, {\"field\": \"statement_period_start\", \"value\": \"\"}, {\"field\": \"statement_period_end\", \"value\": \"2021-07-31\"}, {\"field\": \"ending_balance\", \"value\": \"440.0\"}, {\"field\": \"address\", \"value\": \"100 CHOA CHU KANG DRIVE #04-392 SINGAPORE 681687\"}, {\"field\": \"bank_account_type\", \"value\": \"Saving\"}, {\"field\": \"bank_account_number\", \"value\": \"421-41200-6\"}, {\"field\": \"transaction_amount\", \"value\": \"30.0\"}, {\"field\": \"transaction_date\", \"value\": \"2021-07-07\"}, {\"field\": \"transaction_type\", \"value\": \"FAST Payment / Receipt\"}, {\"field\": \"transaction_sender\", \"value\": \"ALAN\"}]}"}]} | |
| {"id": "bank_statement_fin_060_p1_classify", "task": "classify", "class": "bank_statement", "doc": "bank_statement_fin_060.pdf", "images": ["images/val/bank_statement/bank_statement_fin_060_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"bank_statement\", \"confidence\": 1.0, \"issuer\": \"Commonwealth Bank\", \"holder\": \"Wiley Kuhic\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_060_extract", "task": "extract", "class": "bank_statement", "doc": "bank_statement_fin_060.pdf", "images": ["images/val/bank_statement/bank_statement_fin_060_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('bank_statement', 'The document class.')\nfields = (['account_holder_name', 'bank_name', 'statement_period_start', 'statement_period_end', 'ending_balance', 'address', 'bank_account_type', 'bank_account_number', 'transaction_amount', 'transaction_date', 'transaction_type', 'transaction_sender'], 'The exact field names to extract.')\nhints = ({'account_holder_name': 'Name on the account', 'bank_name': 'Name of the bank', 'statement_period_start': 'Start of statement period', 'statement_period_end': 'End of statement period', 'ending_balance': 'Closing balance for the period', 'address': 'Address of the account holder', 'bank_account_type': 'Type of bank account - Checking/Saving', 'bank_account_number': 'Bank account number', 'transaction_amount': 'Transaction amount', 'transaction_date': 'Transaction date', 'transaction_type': 'Transaction type', 'transaction_sender': 'Transaction sender'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"account_holder_name\", \"value\": \"Wiley Kuhic\"}, {\"field\": \"bank_name\", \"value\": \"Commonwealth Bank\"}, {\"field\": \"statement_period_start\", \"value\": \"2023-08-01\"}, {\"field\": \"statement_period_end\", \"value\": \"2023-08-31\"}, {\"field\": \"ending_balance\", \"value\": \"43.62\"}, {\"field\": \"address\", \"value\": \"78652 Carolanne Hills, Jefferson City, MO 65101\"}, {\"field\": \"bank_account_type\", \"value\": \"Visa Debit\"}, {\"field\": \"bank_account_number\", \"value\": \"4288 52xx xxxx 8694\"}, {\"field\": \"transaction_amount\", \"value\": \"899.0\"}, {\"field\": \"transaction_date\", \"value\": \"2023-08-01\"}, {\"field\": \"transaction_type\", \"value\": \"Transfer\"}, {\"field\": \"transaction_sender\", \"value\": \"xx0979 NetBank\"}]}"}]} | |
| {"id": "bank_statement_fin_067_p1_classify", "task": "classify", "class": "bank_statement", "doc": "bank_statement_fin_067.pdf", "images": ["images/val/bank_statement/bank_statement_fin_067_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"bank_statement\", \"confidence\": 1.0, \"issuer\": \"Barclays\", \"holder\": \"O DO OG U MIC A L\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_067_extract", "task": "extract", "class": "bank_statement", "doc": "bank_statement_fin_067.pdf", "images": ["images/val/bank_statement/bank_statement_fin_067_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('bank_statement', 'The document class.')\nfields = (['account_holder_name', 'bank_name', 'statement_period_start', 'statement_period_end', 'ending_balance', 'address', 'bank_account_type', 'bank_account_number', 'transaction_amount', 'transaction_date', 'transaction_type', 'transaction_sender'], 'The exact field names to extract.')\nhints = ({'account_holder_name': 'Name on the account', 'bank_name': 'Name of the bank', 'statement_period_start': 'Start of statement period', 'statement_period_end': 'End of statement period', 'ending_balance': 'Closing balance for the period', 'address': 'Address of the account holder', 'bank_account_type': 'Type of bank account - Checking/Saving', 'bank_account_number': 'Bank account number', 'transaction_amount': 'Transaction amount', 'transaction_date': 'Transaction date', 'transaction_type': 'Transaction type', 'transaction_sender': 'Transaction sender'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"account_holder_name\", \"value\": \"O DO OG U MIC A L\"}, {\"field\": \"bank_name\", \"value\": \"Barclays\"}, {\"field\": \"statement_period_start\", \"value\": \"2025-01-05\"}, {\"field\": \"statement_period_end\", \"value\": \"\"}, {\"field\": \"ending_balance\", \"value\": \"4378.1\"}, {\"field\": \"address\", \"value\": \"432 C URC STR T LONDON N\"}, {\"field\": \"bank_account_type\", \"value\": \"Checking\"}, {\"field\": \"bank_account_number\", \"value\": \"83605973\"}, {\"field\": \"transaction_amount\", \"value\": \"394.24\"}, {\"field\": \"transaction_date\", \"value\": \"2025-01-05\"}, {\"field\": \"transaction_type\", \"value\": \"Bank Giro\"}, {\"field\": \"transaction_sender\", \"value\": \"Decora Blinds\"}]}"}]} | |
| {"id": "bank_statement_fin_068_p1_classify", "task": "classify", "class": "bank_statement", "doc": "bank_statement_fin_068.pdf", "images": ["images/val/bank_statement/bank_statement_fin_068_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"bank_statement\", \"confidence\": 1.0, \"issuer\": \"HSBC\", \"holder\": \"Mr Edward Cullen\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_068_extract", "task": "extract", "class": "bank_statement", "doc": "bank_statement_fin_068.pdf", "images": ["images/val/bank_statement/bank_statement_fin_068_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('bank_statement', 'The document class.')\nfields = (['account_holder_name', 'bank_name', 'statement_period_start', 'statement_period_end', 'ending_balance', 'address', 'bank_account_type', 'bank_account_number', 'transaction_amount', 'transaction_date', 'transaction_type', 'transaction_sender'], 'The exact field names to extract.')\nhints = ({'account_holder_name': 'Name on the account', 'bank_name': 'Name of the bank', 'statement_period_start': 'Start of statement period', 'statement_period_end': 'End of statement period', 'ending_balance': 'Closing balance for the period', 'address': 'Address of the account holder', 'bank_account_type': 'Type of bank account - Checking/Saving', 'bank_account_number': 'Bank account number', 'transaction_amount': 'Transaction amount', 'transaction_date': 'Transaction date', 'transaction_type': 'Transaction type', 'transaction_sender': 'Transaction sender'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"account_holder_name\", \"value\": \"Mr Edward Cullen\"}, {\"field\": \"bank_name\", \"value\": \"HSBC\"}, {\"field\": \"statement_period_start\", \"value\": \"2019-04-01\"}, {\"field\": \"statement_period_end\", \"value\": \"2019-04-30\"}, {\"field\": \"ending_balance\", \"value\": \"3150.16\"}, {\"field\": \"address\", \"value\": \"47B BOW ARROW LANE, DARTFORD, KENT, DA2 6PA\"}, {\"field\": \"bank_account_type\", \"value\": \"\"}, {\"field\": \"bank_account_number\", \"value\": \"22820244\"}, {\"field\": \"transaction_amount\", \"value\": \"50.0\"}, {\"field\": \"transaction_date\", \"value\": \"2019-04-04\"}, {\"field\": \"transaction_type\", \"value\": \"CR\"}, {\"field\": \"transaction_sender\", \"value\": \"JAMIE U\"}]}"}]} | |
| {"id": "bank_statement_fin_090_p1_classify", "task": "classify", "class": "bank_statement", "doc": "bank_statement_fin_090.pdf", "images": ["images/val/bank_statement/bank_statement_fin_090_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"bank_statement\", \"confidence\": 1.0, \"issuer\": \"HSBC\", \"holder\": \"MST BEAUTI BEGUM\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "bank_statement_fin_090_extract", "task": "extract", "class": "bank_statement", "doc": "bank_statement_fin_090.pdf", "images": ["images/val/bank_statement/bank_statement_fin_090_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('bank_statement', 'The document class.')\nfields = (['account_holder_name', 'bank_name', 'statement_period_start', 'statement_period_end', 'ending_balance', 'address', 'bank_account_type', 'bank_account_number', 'transaction_amount', 'transaction_date', 'transaction_type', 'transaction_sender'], 'The exact field names to extract.')\nhints = ({'account_holder_name': 'Name on the account', 'bank_name': 'Name of the bank', 'statement_period_start': 'Start of statement period', 'statement_period_end': 'End of statement period', 'ending_balance': 'Closing balance for the period', 'address': 'Address of the account holder', 'bank_account_type': 'Type of bank account - Checking/Saving', 'bank_account_number': 'Bank account number', 'transaction_amount': 'Transaction amount', 'transaction_date': 'Transaction date', 'transaction_type': 'Transaction type', 'transaction_sender': 'Transaction sender'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"account_holder_name\", \"value\": \"MST BEAUTI BEGUM\"}, {\"field\": \"bank_name\", \"value\": \"HSBC\"}, {\"field\": \"statement_period_start\", \"value\": \"2020-11-01\"}, {\"field\": \"statement_period_end\", \"value\": \"2020-11-29\"}, {\"field\": \"ending_balance\", \"value\": \"413.47\"}, {\"field\": \"address\", \"value\": \"Ballymount Industrial Estate, Dublin, D12 WPKS, Ireland\"}, {\"field\": \"bank_account_type\", \"value\": \"\"}, {\"field\": \"bank_account_number\", \"value\": \"54329861\"}, {\"field\": \"transaction_amount\", \"value\": \"\"}, {\"field\": \"transaction_date\", \"value\": \"\"}, {\"field\": \"transaction_type\", \"value\": \"\"}, {\"field\": \"transaction_sender\", \"value\": \"\"}]}"}]} | |
| {"id": "drivers_license_fin_004_p1_classify", "task": "classify", "class": "drivers_license", "doc": "drivers_license_fin_004.pdf", "images": ["images/val/drivers_license/drivers_license_fin_004_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"drivers_license\", \"confidence\": 1.0, \"issuer\": \"Idaho\", \"holder\": \"PARKER STANLEY SAMPLE\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "drivers_license_fin_004_extract", "task": "extract", "class": "drivers_license", "doc": "drivers_license_fin_004.pdf", "images": ["images/val/drivers_license/drivers_license_fin_004_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('drivers_license', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"PARKER STANLEY SAMPLE\"}, {\"field\": \"date_of_birth\", \"value\": \"1991-01-01\"}, {\"field\": \"address\", \"value\": \"123 W STATE ST, BOISE ID 83703\"}, {\"field\": \"issue_date\", \"value\": \"2016-01-01\"}, {\"field\": \"expiration_date\", \"value\": \"2020-01-01\"}, {\"field\": \"state\", \"value\": \"Idaho\"}]}"}]} | |
| {"id": "drivers_license_fin_011_p1_classify", "task": "classify", "class": "drivers_license", "doc": "drivers_license_fin_011.pdf", "images": ["images/val/drivers_license/drivers_license_fin_011_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"drivers_license\", \"confidence\": 1.0, \"issuer\": \"Pennsylvania\", \"holder\": \"idpapa org\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "drivers_license_fin_011_extract", "task": "extract", "class": "drivers_license", "doc": "drivers_license_fin_011.pdf", "images": ["images/val/drivers_license/drivers_license_fin_011_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('drivers_license', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"idpapa org\"}, {\"field\": \"date_of_birth\", \"value\": \"2003-10-09\"}, {\"field\": \"address\", \"value\": \"2807 SILVER MAPLE DR, HARRISBURG, PA 17112\"}, {\"field\": \"issue_date\", \"value\": \"2024-10-10\"}, {\"field\": \"expiration_date\", \"value\": \"2028-10-10\"}, {\"field\": \"state\", \"value\": \"Pennsylvania\"}]}"}]} | |
| {"id": "drivers_license_fin_014_p1_classify", "task": "classify", "class": "drivers_license", "doc": "drivers_license_fin_014.pdf", "images": ["images/val/drivers_license/drivers_license_fin_014_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"drivers_license\", \"confidence\": 1.0, \"issuer\": \"CALIFORNIA\", \"holder\": \"JANE MITCHELL\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "drivers_license_fin_014_extract", "task": "extract", "class": "drivers_license", "doc": "drivers_license_fin_014.pdf", "images": ["images/val/drivers_license/drivers_license_fin_014_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('drivers_license', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"JANE MITCHELL\"}, {\"field\": \"date_of_birth\", \"value\": \"1971-09-15\"}, {\"field\": \"address\", \"value\": \"2 BERRIMOOR ST. BONNVILLE, CA 95415\"}, {\"field\": \"issue_date\", \"value\": \"\"}, {\"field\": \"expiration_date\", \"value\": \"1992-08-14\"}, {\"field\": \"state\", \"value\": \"CALIFORNIA\"}]}"}]} | |
| {"id": "drivers_license_fin_023_p1_classify", "task": "classify", "class": "drivers_license", "doc": "drivers_license_fin_023.pdf", "images": ["images/val/drivers_license/drivers_license_fin_023_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"drivers_license\", \"confidence\": 1.0, \"issuer\": \"COLORADO\", \"holder\": \"SAMPLE\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "drivers_license_fin_023_extract", "task": "extract", "class": "drivers_license", "doc": "drivers_license_fin_023.pdf", "images": ["images/val/drivers_license/drivers_license_fin_023_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('drivers_license', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"SAMPLE\"}, {\"field\": \"date_of_birth\", \"value\": \"1976-04-24\"}, {\"field\": \"address\", \"value\": \"1881 PIERCE ST, LAKEWOOD, CO 80214-1249\"}, {\"field\": \"issue_date\", \"value\": \"2015-08-27\"}, {\"field\": \"expiration_date\", \"value\": \"2018-04-24\"}, {\"field\": \"state\", \"value\": \"COLORADO\"}]}"}]} | |
| {"id": "drivers_license_fin_030_p1_classify", "task": "classify", "class": "drivers_license", "doc": "drivers_license_fin_030.pdf", "images": ["images/val/drivers_license/drivers_license_fin_030_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"drivers_license\", \"confidence\": 1.0, \"issuer\": \"NEW YORK\", \"holder\": \"DOCUMENT SAMPLE, LICENSE\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "drivers_license_fin_030_extract", "task": "extract", "class": "drivers_license", "doc": "drivers_license_fin_030.pdf", "images": ["images/val/drivers_license/drivers_license_fin_030_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('drivers_license', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"DOCUMENT SAMPLE, LICENSE\"}, {\"field\": \"date_of_birth\", \"value\": \"1985-06-09\"}, {\"field\": \"address\", \"value\": \"2345 ANYPLACE AVE, ANYTOWN NY 12345\"}, {\"field\": \"issue_date\", \"value\": \"2008-09-30\"}, {\"field\": \"expiration_date\", \"value\": \"2016-10-01\"}, {\"field\": \"state\", \"value\": \"NEW YORK\"}]}"}]} | |
| {"id": "drivers_license_fin_041_p1_classify", "task": "classify", "class": "drivers_license", "doc": "drivers_license_fin_041.pdf", "images": ["images/val/drivers_license/drivers_license_fin_041_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"drivers_license\", \"confidence\": 1.0, \"issuer\": \"Texas\", \"holder\": \"ROMAN ELSA\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "drivers_license_fin_041_extract", "task": "extract", "class": "drivers_license", "doc": "drivers_license_fin_041.pdf", "images": ["images/val/drivers_license/drivers_license_fin_041_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('drivers_license', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"ROMAN ELSA\"}, {\"field\": \"date_of_birth\", \"value\": \"1968-05-09\"}, {\"field\": \"address\", \"value\": \"13218 W COUNTY ROAD 124 TRLR 5, ODESSA TX 79765-8950\"}, {\"field\": \"issue_date\", \"value\": \"2020-02-03\"}, {\"field\": \"expiration_date\", \"value\": \"2026-05-09\"}, {\"field\": \"state\", \"value\": \"Texas\"}]}"}]} | |
| {"id": "drivers_license_fin_049_p1_classify", "task": "classify", "class": "drivers_license", "doc": "drivers_license_fin_049.pdf", "images": ["images/val/drivers_license/drivers_license_fin_049_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"drivers_license\", \"confidence\": 1.0, \"issuer\": \"California\", \"holder\": \"IMA CARDHOLDER\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "drivers_license_fin_049_extract", "task": "extract", "class": "drivers_license", "doc": "drivers_license_fin_049.pdf", "images": ["images/val/drivers_license/drivers_license_fin_049_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('drivers_license', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"IMA CARDHOLDER\"}, {\"field\": \"date_of_birth\", \"value\": \"1977-08-31\"}, {\"field\": \"address\", \"value\": \"2570 24TH STREET, ANYTOWN, CA 95818\"}, {\"field\": \"issue_date\", \"value\": \"2021-08-31\"}, {\"field\": \"expiration_date\", \"value\": \"2026-08-31\"}, {\"field\": \"state\", \"value\": \"California\"}]}"}]} | |
| {"id": "drivers_license_fin_071_p1_classify", "task": "classify", "class": "drivers_license", "doc": "drivers_license_fin_071.pdf", "images": ["images/val/drivers_license/drivers_license_fin_071_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"drivers_license\", \"confidence\": 1.0, \"issuer\": \"Ontario\", \"holder\": \"SILVERTHORNE, DAVID,SHANNON\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "drivers_license_fin_071_extract", "task": "extract", "class": "drivers_license", "doc": "drivers_license_fin_071.pdf", "images": ["images/val/drivers_license/drivers_license_fin_071_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('drivers_license', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"SILVERTHORNE, DAVID,SHANNON\"}, {\"field\": \"date_of_birth\", \"value\": \"1964-09-20\"}, {\"field\": \"address\", \"value\": \"5-837 AUGUSTUS ST, CORNWALL, ON, K6J 3X6\"}, {\"field\": \"issue_date\", \"value\": \"2021-10-28\"}, {\"field\": \"expiration_date\", \"value\": \"2026-09-20\"}, {\"field\": \"state\", \"value\": \"Ontario\"}]}"}]} | |
| {"id": "drivers_license_fin_082_p1_classify", "task": "classify", "class": "drivers_license", "doc": "drivers_license_fin_082.pdf", "images": ["images/val/drivers_license/drivers_license_fin_082_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"drivers_license\", \"confidence\": 1.0, \"issuer\": \"CA\", \"holder\": \"VKOOHFAR ALIREZA\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "drivers_license_fin_082_extract", "task": "extract", "class": "drivers_license", "doc": "drivers_license_fin_082.pdf", "images": ["images/val/drivers_license/drivers_license_fin_082_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('drivers_license', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"VKOOHFAR ALIREZA\"}, {\"field\": \"date_of_birth\", \"value\": \"1977-07-16\"}, {\"field\": \"address\", \"value\": \"52850 MAIN ST, LOS ANGELES, CA, 77598\"}, {\"field\": \"issue_date\", \"value\": \"2013-03-07\"}, {\"field\": \"expiration_date\", \"value\": \"2018-03-07\"}, {\"field\": \"state\", \"value\": \"CA\"}]}"}]} | |
| {"id": "monthly_bill_fin_013_p1_classify", "task": "classify", "class": "monthly_bill", "doc": "monthly_bill_fin_013.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_013_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"monthly_bill\", \"confidence\": 1.0, \"issuer\": \"GAS SOUTH\", \"holder\": \"Timothy Anderson\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "monthly_bill_fin_013_extract", "task": "extract", "class": "monthly_bill", "doc": "monthly_bill_fin_013.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_013_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('monthly_bill', 'The document class.')\nfields = (['full_name', 'address', 'issue_date', 'company_name', 'account_number'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name on the bill', 'address': 'Address', 'issue_date': 'Issued date', 'company_name': 'Name of the issuing company', 'account_number': 'Account number'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"Timothy Anderson\"}, {\"field\": \"address\", \"value\": \"1736 Stone Meadow Rd LOT 31, Lithonia GA 30058\"}, {\"field\": \"issue_date\", \"value\": \"2024-10-11\"}, {\"field\": \"company_name\", \"value\": \"GAS SOUTH\"}, {\"field\": \"account_number\", \"value\": \"2110797186\"}]}"}]} | |
| {"id": "monthly_bill_fin_030_p1_classify", "task": "classify", "class": "monthly_bill", "doc": "monthly_bill_fin_030.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_030_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"monthly_bill\", \"confidence\": 1.0, \"issuer\": \"T-Mobile\", \"holder\": \"FIRST NAME LAST NAME\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "monthly_bill_fin_030_extract", "task": "extract", "class": "monthly_bill", "doc": "monthly_bill_fin_030.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_030_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('monthly_bill', 'The document class.')\nfields = (['full_name', 'address', 'issue_date', 'company_name', 'account_number'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name on the bill', 'address': 'Address', 'issue_date': 'Issued date', 'company_name': 'Name of the issuing company', 'account_number': 'Account number'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"FIRST NAME LAST NAME\"}, {\"field\": \"address\", \"value\": \"ADDRESS, CITY, STATE, ZIP CODE\"}, {\"field\": \"issue_date\", \"value\": \"2024-02-14\"}, {\"field\": \"company_name\", \"value\": \"T-Mobile\"}, {\"field\": \"account_number\", \"value\": \"100469352\"}]}"}]} | |
| {"id": "monthly_bill_fin_034_p1_classify", "task": "classify", "class": "monthly_bill", "doc": "monthly_bill_fin_034.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_034_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"monthly_bill\", \"confidence\": 1.0, \"issuer\": \"Tesco Mobile\", \"holder\": \"Mr. Eamon O'Connor\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "monthly_bill_fin_034_extract", "task": "extract", "class": "monthly_bill", "doc": "monthly_bill_fin_034.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_034_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('monthly_bill', 'The document class.')\nfields = (['full_name', 'address', 'issue_date', 'company_name', 'account_number'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name on the bill', 'address': 'Address', 'issue_date': 'Issued date', 'company_name': 'Name of the issuing company', 'account_number': 'Account number'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"Mr. Eamon O'Connor\"}, {\"field\": \"address\", \"value\": \"1 High Street, Waterfield, Co Dublin\"}, {\"field\": \"issue_date\", \"value\": \"2021-05-08\"}, {\"field\": \"company_name\", \"value\": \"Tesco Mobile\"}, {\"field\": \"account_number\", \"value\": \"1.1234567\"}]}"}]} | |
| {"id": "monthly_bill_fin_036_p1_classify", "task": "classify", "class": "monthly_bill", "doc": "monthly_bill_fin_036.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_036_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"monthly_bill\", \"confidence\": 1.0, \"issuer\": \"Tesco Mobile\", \"holder\": \"Mr. John Smith\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "monthly_bill_fin_036_extract", "task": "extract", "class": "monthly_bill", "doc": "monthly_bill_fin_036.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_036_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('monthly_bill', 'The document class.')\nfields = (['full_name', 'address', 'issue_date', 'company_name', 'account_number'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name on the bill', 'address': 'Address', 'issue_date': 'Issued date', 'company_name': 'Name of the issuing company', 'account_number': 'Account number'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"Mr. John Smith\"}, {\"field\": \"address\", \"value\": \"1 High Street, Address Line 2, Co Dublin\"}, {\"field\": \"issue_date\", \"value\": \"2016-12-08\"}, {\"field\": \"company_name\", \"value\": \"Tesco Mobile\"}, {\"field\": \"account_number\", \"value\": \"1.6570827\"}]}"}]} | |
| {"id": "monthly_bill_fin_037_p1_classify", "task": "classify", "class": "monthly_bill", "doc": "monthly_bill_fin_037.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_037_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"monthly_bill\", \"confidence\": 1.0, \"issuer\": \"Telstra Corporation Limited\", \"holder\": \"Mr John Sample\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "monthly_bill_fin_037_extract", "task": "extract", "class": "monthly_bill", "doc": "monthly_bill_fin_037.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_037_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('monthly_bill', 'The document class.')\nfields = (['full_name', 'address', 'issue_date', 'company_name', 'account_number'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name on the bill', 'address': 'Address', 'issue_date': 'Issued date', 'company_name': 'Name of the issuing company', 'account_number': 'Account number'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"Mr John Sample\"}, {\"field\": \"address\", \"value\": \"123 Main Street, SUBURBIA NSW 2200\"}, {\"field\": \"issue_date\", \"value\": \"2008-01-27\"}, {\"field\": \"company_name\", \"value\": \"Telstra Corporation Limited\"}, {\"field\": \"account_number\", \"value\": \"9874 65432 1041\"}]}"}]} | |
| {"id": "monthly_bill_fin_042_p1_classify", "task": "classify", "class": "monthly_bill", "doc": "monthly_bill_fin_042.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_042_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"monthly_bill\", \"confidence\": 1.0, \"issuer\": \"INDRAPRASTHA GAS LIMITED\", \"holder\": \"CHIRAG Shar\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "monthly_bill_fin_042_extract", "task": "extract", "class": "monthly_bill", "doc": "monthly_bill_fin_042.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_042_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('monthly_bill', 'The document class.')\nfields = (['full_name', 'address', 'issue_date', 'company_name', 'account_number'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name on the bill', 'address': 'Address', 'issue_date': 'Issued date', 'company_name': 'Name of the issuing company', 'account_number': 'Account number'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"CHIRAG Shar\"}, {\"field\": \"address\", \"value\": \"E-711, PIYUSH HEIGHTS, SECTOR 89, FARIDABAD, HARYANA-121002, INDIA\"}, {\"field\": \"issue_date\", \"value\": \"2025-02-21\"}, {\"field\": \"company_name\", \"value\": \"INDRAPRASTHA GAS LIMITED\"}, {\"field\": \"account_number\", \"value\": \"5090142631\"}]}"}]} | |
| {"id": "monthly_bill_fin_052_p1_classify", "task": "classify", "class": "monthly_bill", "doc": "monthly_bill_fin_052.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_052_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"monthly_bill\", \"confidence\": 1.0, \"issuer\": \"Your Gas Company\", \"holder\": \"James Coldmeister\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "monthly_bill_fin_052_extract", "task": "extract", "class": "monthly_bill", "doc": "monthly_bill_fin_052.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_052_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('monthly_bill', 'The document class.')\nfields = (['full_name', 'address', 'issue_date', 'company_name', 'account_number'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name on the bill', 'address': 'Address', 'issue_date': 'Issued date', 'company_name': 'Name of the issuing company', 'account_number': 'Account number'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"James Coldmeister\"}, {\"field\": \"address\", \"value\": \"2455 Freezing Lane, Iceville, MN 25489\"}, {\"field\": \"issue_date\", \"value\": \"2013-01-22\"}, {\"field\": \"company_name\", \"value\": \"Your Gas Company\"}, {\"field\": \"account_number\", \"value\": \"5-5541-1855-8777\"}]}"}]} | |
| {"id": "monthly_bill_fin_066_p1_classify", "task": "classify", "class": "monthly_bill", "doc": "monthly_bill_fin_066.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_066_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"monthly_bill\", \"confidence\": 1.0, \"issuer\": \"AT&T\", \"holder\": \"MIGUEL GARCIA\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "monthly_bill_fin_066_extract", "task": "extract", "class": "monthly_bill", "doc": "monthly_bill_fin_066.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_066_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('monthly_bill', 'The document class.')\nfields = (['full_name', 'address', 'issue_date', 'company_name', 'account_number'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name on the bill', 'address': 'Address', 'issue_date': 'Issued date', 'company_name': 'Name of the issuing company', 'account_number': 'Account number'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"MIGUEL GARCIA\"}, {\"field\": \"address\", \"value\": \"99 LINWOOD ST, NASHUA, NH 03060-4414\"}, {\"field\": \"issue_date\", \"value\": \"\"}, {\"field\": \"company_name\", \"value\": \"AT&T\"}, {\"field\": \"account_number\", \"value\": \"155040181184\"}]}"}]} | |
| {"id": "monthly_bill_fin_081_p1_classify", "task": "classify", "class": "monthly_bill", "doc": "monthly_bill_fin_081.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_081_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"monthly_bill\", \"confidence\": 1.0, \"issuer\": \"verizon\", \"holder\": \"JOHN CITIZEN\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "monthly_bill_fin_081_extract", "task": "extract", "class": "monthly_bill", "doc": "monthly_bill_fin_081.pdf", "images": ["images/val/monthly_bill/monthly_bill_fin_081_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('monthly_bill', 'The document class.')\nfields = (['full_name', 'address', 'issue_date', 'company_name', 'account_number'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name on the bill', 'address': 'Address', 'issue_date': 'Issued date', 'company_name': 'Name of the issuing company', 'account_number': 'Account number'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"JOHN CITIZEN\"}, {\"field\": \"address\", \"value\": \"265 MAIN ST, UNIT 1, GORHAM NH 03581\"}, {\"field\": \"issue_date\", \"value\": \"\"}, {\"field\": \"company_name\", \"value\": \"verizon\"}, {\"field\": \"account_number\", \"value\": \"890612125-00089\"}]}"}]} | |
| {"id": "paystub_fin_026_p1_classify", "task": "classify", "class": "paystub", "doc": "paystub_fin_026.pdf", "images": ["images/val/paystub/paystub_fin_026_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"paystub\", \"confidence\": 1.0, \"issuer\": \"Multi-Trade Services\", \"holder\": \"James Wilson\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "paystub_fin_026_extract", "task": "extract", "class": "paystub", "doc": "paystub_fin_026.pdf", "images": ["images/val/paystub/paystub_fin_026_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('paystub', 'The document class.')\nfields = (['pay_date', 'employee_name', 'employer_name', 'gross_pay', 'ytd_gross', 'pay_frequency', 'pay_period_start', 'pay_period_end', 'federal_tax', 'state_tax', 'social_security_tax', 'medicare_tax', 'hire_date', 'direct_deposit_bank_type'], 'The exact field names to extract.')\nhints = ({'pay_date': 'Date the paycheck was issued', 'employee_name': 'Name of Employee', 'employer_name': 'Name of Employer', 'gross_pay': 'Gross pay per period (current period, not YTD)', 'ytd_gross': 'Gross pay on paystub year to date (cumulative, not current period)', 'pay_frequency': 'The frequency if provided: weekly, biweekly, monthly, semi-monthly', 'pay_period_start': 'Pay period start date', 'pay_period_end': 'Pay period end date', 'hire_date': 'Job hire date', 'direct_deposit_bank_type': 'Direct deposit bank type'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"pay_date\", \"value\": \"2024-12-20\"}, {\"field\": \"employee_name\", \"value\": \"James Wilson\"}, {\"field\": \"employer_name\", \"value\": \"Multi-Trade Services\"}, {\"field\": \"gross_pay\", \"value\": \"2488.0\"}, {\"field\": \"ytd_gross\", \"value\": \"59712.0\"}, {\"field\": \"pay_frequency\", \"value\": \"biweekly\"}, {\"field\": \"pay_period_start\", \"value\": \"2024-12-01\"}, {\"field\": \"pay_period_end\", \"value\": \"2024-12-15\"}, {\"field\": \"federal_tax\", \"value\": \"298.56\"}, {\"field\": \"state_tax\", \"value\": \"\"}, {\"field\": \"social_security_tax\", \"value\": \"154.26\"}, {\"field\": \"medicare_tax\", \"value\": \"36.08\"}, {\"field\": \"hire_date\", \"value\": \"\"}, {\"field\": \"direct_deposit_bank_type\", \"value\": \"Direct Deposit\"}]}"}]} | |
| {"id": "paystub_fin_028_p1_classify", "task": "classify", "class": "paystub", "doc": "paystub_fin_028.pdf", "images": ["images/val/paystub/paystub_fin_028_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"paystub\", \"confidence\": 1.0, \"issuer\": \"Acme Corporation\", \"holder\": \"John M. Smith\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "paystub_fin_028_extract", "task": "extract", "class": "paystub", "doc": "paystub_fin_028.pdf", "images": ["images/val/paystub/paystub_fin_028_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('paystub', 'The document class.')\nfields = (['pay_date', 'employee_name', 'employer_name', 'gross_pay', 'ytd_gross', 'pay_frequency', 'pay_period_start', 'pay_period_end', 'federal_tax', 'state_tax', 'social_security_tax', 'medicare_tax', 'hire_date', 'direct_deposit_bank_type'], 'The exact field names to extract.')\nhints = ({'pay_date': 'Date the paycheck was issued', 'employee_name': 'Name of Employee', 'employer_name': 'Name of Employer', 'gross_pay': 'Gross pay per period (current period, not YTD)', 'ytd_gross': 'Gross pay on paystub year to date (cumulative, not current period)', 'pay_frequency': 'The frequency if provided: weekly, biweekly, monthly, semi-monthly', 'pay_period_start': 'Pay period start date', 'pay_period_end': 'Pay period end date', 'hire_date': 'Job hire date', 'direct_deposit_bank_type': 'Direct deposit bank type'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"pay_date\", \"value\": \"2024-12-20\"}, {\"field\": \"employee_name\", \"value\": \"John M. Smith\"}, {\"field\": \"employer_name\", \"value\": \"Acme Corporation\"}, {\"field\": \"gross_pay\", \"value\": \"3000.0\"}, {\"field\": \"ytd_gross\", \"value\": \"\"}, {\"field\": \"pay_frequency\", \"value\": \"\"}, {\"field\": \"pay_period_start\", \"value\": \"\"}, {\"field\": \"pay_period_end\", \"value\": \"\"}, {\"field\": \"federal_tax\", \"value\": \"\"}, {\"field\": \"state_tax\", \"value\": \"\"}, {\"field\": \"social_security_tax\", \"value\": \"\"}, {\"field\": \"medicare_tax\", \"value\": \"\"}, {\"field\": \"hire_date\", \"value\": \"\"}, {\"field\": \"direct_deposit_bank_type\", \"value\": \"Check #4521\"}]}"}]} | |
| {"id": "paystub_fin_029_p1_classify", "task": "classify", "class": "paystub", "doc": "paystub_fin_029.pdf", "images": ["images/val/paystub/paystub_fin_029_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"paystub\", \"confidence\": 1.0, \"issuer\": \"Sample Company Name\", \"holder\": \"Employee Name\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "paystub_fin_029_extract", "task": "extract", "class": "paystub", "doc": "paystub_fin_029.pdf", "images": ["images/val/paystub/paystub_fin_029_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('paystub', 'The document class.')\nfields = (['pay_date', 'employee_name', 'employer_name', 'gross_pay', 'ytd_gross', 'pay_frequency', 'pay_period_start', 'pay_period_end', 'federal_tax', 'state_tax', 'social_security_tax', 'medicare_tax', 'hire_date', 'direct_deposit_bank_type'], 'The exact field names to extract.')\nhints = ({'pay_date': 'Date the paycheck was issued', 'employee_name': 'Name of Employee', 'employer_name': 'Name of Employer', 'gross_pay': 'Gross pay per period (current period, not YTD)', 'ytd_gross': 'Gross pay on paystub year to date (cumulative, not current period)', 'pay_frequency': 'The frequency if provided: weekly, biweekly, monthly, semi-monthly', 'pay_period_start': 'Pay period start date', 'pay_period_end': 'Pay period end date', 'hire_date': 'Job hire date', 'direct_deposit_bank_type': 'Direct deposit bank type'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"pay_date\", \"value\": \"2018-02-14\"}, {\"field\": \"employee_name\", \"value\": \"Employee Name\"}, {\"field\": \"employer_name\", \"value\": \"Sample Company Name\"}, {\"field\": \"gross_pay\", \"value\": \"800.0\"}, {\"field\": \"ytd_gross\", \"value\": \"5600.0\"}, {\"field\": \"pay_frequency\", \"value\": \"\"}, {\"field\": \"pay_period_start\", \"value\": \"2018-02-07\"}, {\"field\": \"pay_period_end\", \"value\": \"2018-02-13\"}, {\"field\": \"federal_tax\", \"value\": \"108.1\"}, {\"field\": \"state_tax\", \"value\": \"40.0\"}, {\"field\": \"social_security_tax\", \"value\": \"49.6\"}, {\"field\": \"medicare_tax\", \"value\": \"11.6\"}, {\"field\": \"hire_date\", \"value\": \"\"}, {\"field\": \"direct_deposit_bank_type\", \"value\": \"\"}]}"}]} | |
| {"id": "paystub_fin_042_p1_classify", "task": "classify", "class": "paystub", "doc": "paystub_fin_042.pdf", "images": ["images/val/paystub/paystub_fin_042_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"paystub\", \"confidence\": 1.0, \"issuer\": \"\", \"holder\": \"Julie Jones\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "paystub_fin_042_extract", "task": "extract", "class": "paystub", "doc": "paystub_fin_042.pdf", "images": ["images/val/paystub/paystub_fin_042_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('paystub', 'The document class.')\nfields = (['pay_date', 'employee_name', 'employer_name', 'gross_pay', 'ytd_gross', 'pay_frequency', 'pay_period_start', 'pay_period_end', 'federal_tax', 'state_tax', 'social_security_tax', 'medicare_tax', 'hire_date', 'direct_deposit_bank_type'], 'The exact field names to extract.')\nhints = ({'pay_date': 'Date the paycheck was issued', 'employee_name': 'Name of Employee', 'employer_name': 'Name of Employer', 'gross_pay': 'Gross pay per period (current period, not YTD)', 'ytd_gross': 'Gross pay on paystub year to date (cumulative, not current period)', 'pay_frequency': 'The frequency if provided: weekly, biweekly, monthly, semi-monthly', 'pay_period_start': 'Pay period start date', 'pay_period_end': 'Pay period end date', 'hire_date': 'Job hire date', 'direct_deposit_bank_type': 'Direct deposit bank type'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"pay_date\", \"value\": \"2012-12-13\"}, {\"field\": \"employee_name\", \"value\": \"Julie Jones\"}, {\"field\": \"employer_name\", \"value\": \"\"}, {\"field\": \"gross_pay\", \"value\": \"1083.0\"}, {\"field\": \"ytd_gross\", \"value\": \"\"}, {\"field\": \"pay_frequency\", \"value\": \"\"}, {\"field\": \"pay_period_start\", \"value\": \"\"}, {\"field\": \"pay_period_end\", \"value\": \"\"}, {\"field\": \"federal_tax\", \"value\": \"122.05\"}, {\"field\": \"state_tax\", \"value\": \"42.27\"}, {\"field\": \"social_security_tax\", \"value\": \"67.15\"}, {\"field\": \"medicare_tax\", \"value\": \"15.7\"}, {\"field\": \"hire_date\", \"value\": \"\"}, {\"field\": \"direct_deposit_bank_type\", \"value\": \"Guardian National Bank\"}]}"}]} | |
| {"id": "paystub_fin_054_p1_classify", "task": "classify", "class": "paystub", "doc": "paystub_fin_054.pdf", "images": ["images/val/paystub/paystub_fin_054_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"paystub\", \"confidence\": 1.0, \"issuer\": \"ABC Company\", \"holder\": \"John Smith\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "paystub_fin_054_extract", "task": "extract", "class": "paystub", "doc": "paystub_fin_054.pdf", "images": ["images/val/paystub/paystub_fin_054_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('paystub', 'The document class.')\nfields = (['pay_date', 'employee_name', 'employer_name', 'gross_pay', 'ytd_gross', 'pay_frequency', 'pay_period_start', 'pay_period_end', 'federal_tax', 'state_tax', 'social_security_tax', 'medicare_tax', 'hire_date', 'direct_deposit_bank_type'], 'The exact field names to extract.')\nhints = ({'pay_date': 'Date the paycheck was issued', 'employee_name': 'Name of Employee', 'employer_name': 'Name of Employer', 'gross_pay': 'Gross pay per period (current period, not YTD)', 'ytd_gross': 'Gross pay on paystub year to date (cumulative, not current period)', 'pay_frequency': 'The frequency if provided: weekly, biweekly, monthly, semi-monthly', 'pay_period_start': 'Pay period start date', 'pay_period_end': 'Pay period end date', 'hire_date': 'Job hire date', 'direct_deposit_bank_type': 'Direct deposit bank type'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"pay_date\", \"value\": \"2020-02-26\"}, {\"field\": \"employee_name\", \"value\": \"John Smith\"}, {\"field\": \"employer_name\", \"value\": \"ABC Company\"}, {\"field\": \"gross_pay\", \"value\": \"400.0\"}, {\"field\": \"ytd_gross\", \"value\": \"3600.0\"}, {\"field\": \"pay_frequency\", \"value\": \"\"}, {\"field\": \"pay_period_start\", \"value\": \"2020-02-19\"}, {\"field\": \"pay_period_end\", \"value\": \"2020-02-25\"}, {\"field\": \"federal_tax\", \"value\": \"44.5\"}, {\"field\": \"state_tax\", \"value\": \"20.0\"}, {\"field\": \"social_security_tax\", \"value\": \"24.8\"}, {\"field\": \"medicare_tax\", \"value\": \"5.8\"}, {\"field\": \"hire_date\", \"value\": \"\"}, {\"field\": \"direct_deposit_bank_type\", \"value\": \"\"}]}"}]} | |
| {"id": "paystub_fin_056_p1_classify", "task": "classify", "class": "paystub", "doc": "paystub_fin_056.pdf", "images": ["images/val/paystub/paystub_fin_056_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"paystub\", \"confidence\": 1.0, \"issuer\": \"ABC Company\", \"holder\": \"John Smith\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "paystub_fin_056_extract", "task": "extract", "class": "paystub", "doc": "paystub_fin_056.pdf", "images": ["images/val/paystub/paystub_fin_056_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('paystub', 'The document class.')\nfields = (['pay_date', 'employee_name', 'employer_name', 'gross_pay', 'ytd_gross', 'pay_frequency', 'pay_period_start', 'pay_period_end', 'federal_tax', 'state_tax', 'social_security_tax', 'medicare_tax', 'hire_date', 'direct_deposit_bank_type'], 'The exact field names to extract.')\nhints = ({'pay_date': 'Date the paycheck was issued', 'employee_name': 'Name of Employee', 'employer_name': 'Name of Employer', 'gross_pay': 'Gross pay per period (current period, not YTD)', 'ytd_gross': 'Gross pay on paystub year to date (cumulative, not current period)', 'pay_frequency': 'The frequency if provided: weekly, biweekly, monthly, semi-monthly', 'pay_period_start': 'Pay period start date', 'pay_period_end': 'Pay period end date', 'hire_date': 'Job hire date', 'direct_deposit_bank_type': 'Direct deposit bank type'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"pay_date\", \"value\": \"2020-02-26\"}, {\"field\": \"employee_name\", \"value\": \"John Smith\"}, {\"field\": \"employer_name\", \"value\": \"ABC Company\"}, {\"field\": \"gross_pay\", \"value\": \"400.0\"}, {\"field\": \"ytd_gross\", \"value\": \"3600.0\"}, {\"field\": \"pay_frequency\", \"value\": \"weekly\"}, {\"field\": \"pay_period_start\", \"value\": \"2020-02-19\"}, {\"field\": \"pay_period_end\", \"value\": \"2020-02-25\"}, {\"field\": \"federal_tax\", \"value\": \"44.5\"}, {\"field\": \"state_tax\", \"value\": \"20.0\"}, {\"field\": \"social_security_tax\", \"value\": \"24.8\"}, {\"field\": \"medicare_tax\", \"value\": \"5.8\"}, {\"field\": \"hire_date\", \"value\": \"\"}, {\"field\": \"direct_deposit_bank_type\", \"value\": \"\"}]}"}]} | |
| {"id": "paystub_fin_063_p1_classify", "task": "classify", "class": "paystub", "doc": "paystub_fin_063.pdf", "images": ["images/val/paystub/paystub_fin_063_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"paystub\", \"confidence\": 1.0, \"issuer\": \"Sample Company Name\", \"holder\": \"Employee Name\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "paystub_fin_063_extract", "task": "extract", "class": "paystub", "doc": "paystub_fin_063.pdf", "images": ["images/val/paystub/paystub_fin_063_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('paystub', 'The document class.')\nfields = (['pay_date', 'employee_name', 'employer_name', 'gross_pay', 'ytd_gross', 'pay_frequency', 'pay_period_start', 'pay_period_end', 'federal_tax', 'state_tax', 'social_security_tax', 'medicare_tax', 'hire_date', 'direct_deposit_bank_type'], 'The exact field names to extract.')\nhints = ({'pay_date': 'Date the paycheck was issued', 'employee_name': 'Name of Employee', 'employer_name': 'Name of Employer', 'gross_pay': 'Gross pay per period (current period, not YTD)', 'ytd_gross': 'Gross pay on paystub year to date (cumulative, not current period)', 'pay_frequency': 'The frequency if provided: weekly, biweekly, monthly, semi-monthly', 'pay_period_start': 'Pay period start date', 'pay_period_end': 'Pay period end date', 'hire_date': 'Job hire date', 'direct_deposit_bank_type': 'Direct deposit bank type'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"pay_date\", \"value\": \"2018-04-19\"}, {\"field\": \"employee_name\", \"value\": \"Employee Name\"}, {\"field\": \"employer_name\", \"value\": \"Sample Company Name\"}, {\"field\": \"gross_pay\", \"value\": \"400.0\"}, {\"field\": \"ytd_gross\", \"value\": \"6400.0\"}, {\"field\": \"pay_frequency\", \"value\": \"\"}, {\"field\": \"pay_period_start\", \"value\": \"1970-01-01\"}, {\"field\": \"pay_period_end\", \"value\": \"1970-01-01\"}, {\"field\": \"federal_tax\", \"value\": \"35.82\"}, {\"field\": \"state_tax\", \"value\": \"20.0\"}, {\"field\": \"social_security_tax\", \"value\": \"24.8\"}, {\"field\": \"medicare_tax\", \"value\": \"5.8\"}, {\"field\": \"hire_date\", \"value\": \"\"}, {\"field\": \"direct_deposit_bank_type\", \"value\": \"\"}]}"}]} | |
| {"id": "paystub_fin_069_p1_classify", "task": "classify", "class": "paystub", "doc": "paystub_fin_069.pdf", "images": ["images/val/paystub/paystub_fin_069_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"paystub\", \"confidence\": 1.0, \"issuer\": \"EXAMPLE COMPANY, INC.\", \"holder\": \"JOHN DOE\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "paystub_fin_069_extract", "task": "extract", "class": "paystub", "doc": "paystub_fin_069.pdf", "images": ["images/val/paystub/paystub_fin_069_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('paystub', 'The document class.')\nfields = (['pay_date', 'employee_name', 'employer_name', 'gross_pay', 'ytd_gross', 'pay_frequency', 'pay_period_start', 'pay_period_end', 'federal_tax', 'state_tax', 'social_security_tax', 'medicare_tax', 'hire_date', 'direct_deposit_bank_type'], 'The exact field names to extract.')\nhints = ({'pay_date': 'Date the paycheck was issued', 'employee_name': 'Name of Employee', 'employer_name': 'Name of Employer', 'gross_pay': 'Gross pay per period (current period, not YTD)', 'ytd_gross': 'Gross pay on paystub year to date (cumulative, not current period)', 'pay_frequency': 'The frequency if provided: weekly, biweekly, monthly, semi-monthly', 'pay_period_start': 'Pay period start date', 'pay_period_end': 'Pay period end date', 'hire_date': 'Job hire date', 'direct_deposit_bank_type': 'Direct deposit bank type'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"pay_date\", \"value\": \"2013-07-23\"}, {\"field\": \"employee_name\", \"value\": \"JOHN DOE\"}, {\"field\": \"employer_name\", \"value\": \"EXAMPLE COMPANY, INC.\"}, {\"field\": \"gross_pay\", \"value\": \"1200.0\"}, {\"field\": \"ytd_gross\", \"value\": \"17622.5\"}, {\"field\": \"pay_frequency\", \"value\": \"\"}, {\"field\": \"pay_period_start\", \"value\": \"2013-06-19\"}, {\"field\": \"pay_period_end\", \"value\": \"2013-07-02\"}, {\"field\": \"federal_tax\", \"value\": \"157.39\"}, {\"field\": \"state_tax\", \"value\": \"40.06\"}, {\"field\": \"social_security_tax\", \"value\": \"71.69\"}, {\"field\": \"medicare_tax\", \"value\": \"16.77\"}, {\"field\": \"hire_date\", \"value\": \"\"}, {\"field\": \"direct_deposit_bank_type\", \"value\": \"SAMPLE BANK\"}]}"}]} | |
| {"id": "paystub_fin_072_p1_classify", "task": "classify", "class": "paystub", "doc": "paystub_fin_072.pdf", "images": ["images/val/paystub/paystub_fin_072_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"paystub\", \"confidence\": 1.0, \"issuer\": \"Anthony S. Reeves\", \"holder\": \"Deborah A. Hanna\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "paystub_fin_072_extract", "task": "extract", "class": "paystub", "doc": "paystub_fin_072.pdf", "images": ["images/val/paystub/paystub_fin_072_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('paystub', 'The document class.')\nfields = (['pay_date', 'employee_name', 'employer_name', 'gross_pay', 'ytd_gross', 'pay_frequency', 'pay_period_start', 'pay_period_end', 'federal_tax', 'state_tax', 'social_security_tax', 'medicare_tax', 'hire_date', 'direct_deposit_bank_type'], 'The exact field names to extract.')\nhints = ({'pay_date': 'Date the paycheck was issued', 'employee_name': 'Name of Employee', 'employer_name': 'Name of Employer', 'gross_pay': 'Gross pay per period (current period, not YTD)', 'ytd_gross': 'Gross pay on paystub year to date (cumulative, not current period)', 'pay_frequency': 'The frequency if provided: weekly, biweekly, monthly, semi-monthly', 'pay_period_start': 'Pay period start date', 'pay_period_end': 'Pay period end date', 'hire_date': 'Job hire date', 'direct_deposit_bank_type': 'Direct deposit bank type'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"pay_date\", \"value\": \"2023-09-01\"}, {\"field\": \"employee_name\", \"value\": \"Deborah A. Hanna\"}, {\"field\": \"employer_name\", \"value\": \"Anthony S. Reeves\"}, {\"field\": \"gross_pay\", \"value\": \"2160.0\"}, {\"field\": \"ytd_gross\", \"value\": \"19440.0\"}, {\"field\": \"pay_frequency\", \"value\": \"\"}, {\"field\": \"pay_period_start\", \"value\": \"2023-08-01\"}, {\"field\": \"pay_period_end\", \"value\": \"2023-08-31\"}, {\"field\": \"federal_tax\", \"value\": \"\"}, {\"field\": \"state_tax\", \"value\": \"\"}, {\"field\": \"social_security_tax\", \"value\": \"162.0\"}, {\"field\": \"medicare_tax\", \"value\": \"45.36\"}, {\"field\": \"hire_date\", \"value\": \"\"}, {\"field\": \"direct_deposit_bank_type\", \"value\": \"\"}]}"}]} | |
| {"id": "state_id_fin_010_p1_classify", "task": "classify", "class": "state_id", "doc": "state_id_fin_010.pdf", "images": ["images/val/state_id/state_id_fin_010_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"state_id\", \"confidence\": 1.0, \"issuer\": \"ARKANSAS\", \"holder\": \"JUN SAMPLE\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "state_id_fin_010_extract", "task": "extract", "class": "state_id", "doc": "state_id_fin_010.pdf", "images": ["images/val/state_id/state_id_fin_010_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('state_id', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"JUN SAMPLE\"}, {\"field\": \"date_of_birth\", \"value\": \"2001-03-05\"}, {\"field\": \"address\", \"value\": \"123 NORTH STREET, CITY, AR 12345\"}, {\"field\": \"issue_date\", \"value\": \"2018-03-05\"}, {\"field\": \"expiration_date\", \"value\": \"2026-03-05\"}, {\"field\": \"state\", \"value\": \"ARKANSAS\"}]}"}]} | |
| {"id": "state_id_fin_011_p1_classify", "task": "classify", "class": "state_id", "doc": "state_id_fin_011.pdf", "images": ["images/val/state_id/state_id_fin_011_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"state_id\", \"confidence\": 1.0, \"issuer\": \"Connecticut\", \"holder\": \"SAMPLE BRENDA T\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "state_id_fin_011_extract", "task": "extract", "class": "state_id", "doc": "state_id_fin_011.pdf", "images": ["images/val/state_id/state_id_fin_011_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('state_id', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"SAMPLE BRENDA T\"}, {\"field\": \"date_of_birth\", \"value\": \"1967-01-12\"}, {\"field\": \"address\", \"value\": \"123 MAIN ST, HARTFORD, CT 06114-1234\"}, {\"field\": \"issue_date\", \"value\": \"2016-01-12\"}, {\"field\": \"expiration_date\", \"value\": \"2022-01-12\"}, {\"field\": \"state\", \"value\": \"Connecticut\"}]}"}]} | |
| {"id": "state_id_fin_015_p1_classify", "task": "classify", "class": "state_id", "doc": "state_id_fin_015.pdf", "images": ["images/val/state_id/state_id_fin_015_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"state_id\", \"confidence\": 1.0, \"issuer\": \"WASHINGTON\", \"holder\": \"TEST R BIRDE\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "state_id_fin_015_extract", "task": "extract", "class": "state_id", "doc": "state_id_fin_015.pdf", "images": ["images/val/state_id/state_id_fin_015_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('state_id', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"TEST R BIRDE\"}, {\"field\": \"date_of_birth\", \"value\": \"1954-09-06\"}, {\"field\": \"address\", \"value\": \"2602 MARTIN WAY E, OLYMPIA WA 98506-0069\"}, {\"field\": \"issue_date\", \"value\": \"2010-09-14\"}, {\"field\": \"expiration_date\", \"value\": \"2015-09-06\"}, {\"field\": \"state\", \"value\": \"WASHINGTON\"}]}"}]} | |
| {"id": "state_id_fin_028_p1_classify", "task": "classify", "class": "state_id", "doc": "state_id_fin_028.pdf", "images": ["images/val/state_id/state_id_fin_028_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"state_id\", \"confidence\": 1.0, \"issuer\": \"NEBRASKA\", \"holder\": \"SAMPLE CONNOR M, JR\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "state_id_fin_028_extract", "task": "extract", "class": "state_id", "doc": "state_id_fin_028.pdf", "images": ["images/val/state_id/state_id_fin_028_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('state_id', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"SAMPLE CONNOR M, JR\"}, {\"field\": \"date_of_birth\", \"value\": \"1967-01-12\"}, {\"field\": \"address\", \"value\": \"123 MAIN STREET, ANYTOWN, NE 12345\"}, {\"field\": \"issue_date\", \"value\": \"2023-05-01\"}, {\"field\": \"expiration_date\", \"value\": \"2028-01-12\"}, {\"field\": \"state\", \"value\": \"NEBRASKA\"}]}"}]} | |
| {"id": "state_id_fin_061_p1_classify", "task": "classify", "class": "state_id", "doc": "state_id_fin_061.pdf", "images": ["images/val/state_id/state_id_fin_061_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"state_id\", \"confidence\": 1.0, \"issuer\": \"ROMANIA\", \"holder\": \"MANOLE CORINA IOANA\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "state_id_fin_061_extract", "task": "extract", "class": "state_id", "doc": "state_id_fin_061.pdf", "images": ["images/val/state_id/state_id_fin_061_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('state_id', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"MANOLE CORINA IOANA\"}, {\"field\": \"date_of_birth\", \"value\": \"1983-07-03\"}, {\"field\": \"address\", \"value\": \"\"}, {\"field\": \"issue_date\", \"value\": \"\"}, {\"field\": \"expiration_date\", \"value\": \"2031-09-01\"}, {\"field\": \"state\", \"value\": \"ROMANIA\"}]}"}]} | |
| {"id": "state_id_fin_064_p1_classify", "task": "classify", "class": "state_id", "doc": "state_id_fin_064.pdf", "images": ["images/val/state_id/state_id_fin_064_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"state_id\", \"confidence\": 1.0, \"issuer\": \"Virginia\", \"holder\": \"BANISTER GLENDA, REILLY\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "state_id_fin_064_extract", "task": "extract", "class": "state_id", "doc": "state_id_fin_064.pdf", "images": ["images/val/state_id/state_id_fin_064_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('state_id', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"BANISTER GLENDA, REILLY\"}, {\"field\": \"date_of_birth\", \"value\": \"1931-02-22\"}, {\"field\": \"address\", \"value\": \"4050 VALLEY PIKE, WINCHESTER, VA 22602\"}, {\"field\": \"issue_date\", \"value\": \"2009-05-14\"}, {\"field\": \"expiration_date\", \"value\": \"2016-02-29\"}, {\"field\": \"state\", \"value\": \"Virginia\"}]}"}]} | |
| {"id": "state_id_fin_069_p1_classify", "task": "classify", "class": "state_id", "doc": "state_id_fin_069.pdf", "images": ["images/val/state_id/state_id_fin_069_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"state_id\", \"confidence\": 1.0, \"issuer\": \"North Carolina\", \"holder\": \"SAMPLE IMA\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "state_id_fin_069_extract", "task": "extract", "class": "state_id", "doc": "state_id_fin_069.pdf", "images": ["images/val/state_id/state_id_fin_069_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('state_id', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"SAMPLE IMA\"}, {\"field\": \"date_of_birth\", \"value\": \"1979-08-31\"}, {\"field\": \"address\", \"value\": \"123 MAIN STREET APT 8A, YOUR CITY, NC 99999-1234\"}, {\"field\": \"issue_date\", \"value\": \"\"}, {\"field\": \"expiration_date\", \"value\": \"\"}, {\"field\": \"state\", \"value\": \"North Carolina\"}]}"}]} | |
| {"id": "state_id_fin_077_p1_classify", "task": "classify", "class": "state_id", "doc": "state_id_fin_077.pdf", "images": ["images/val/state_id/state_id_fin_077_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"state_id\", \"confidence\": 1.0, \"issuer\": \"CALIFORNIA\", \"holder\": \"ALFREDO VILLAGRACIA LAGMAY SR\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "state_id_fin_077_extract", "task": "extract", "class": "state_id", "doc": "state_id_fin_077.pdf", "images": ["images/val/state_id/state_id_fin_077_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('state_id', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"ALFREDO VILLAGRACIA LAGMAY SR\"}, {\"field\": \"date_of_birth\", \"value\": \"1919-08-14\"}, {\"field\": \"address\", \"value\": \"2420 PACIFIC DR 46, SANTA CLARA CA 95051\"}, {\"field\": \"issue_date\", \"value\": \"1996-12-05\"}, {\"field\": \"expiration_date\", \"value\": \"2006-08-14\"}, {\"field\": \"state\", \"value\": \"CALIFORNIA\"}]}"}]} | |
| {"id": "state_id_fin_085_p1_classify", "task": "classify", "class": "state_id", "doc": "state_id_fin_085.pdf", "images": ["images/val/state_id/state_id_fin_085_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"state_id\", \"confidence\": 1.0, \"issuer\": \"CALIFORNIA\", \"holder\": \"ANDERSON CRYSTAL\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "state_id_fin_085_extract", "task": "extract", "class": "state_id", "doc": "state_id_fin_085.pdf", "images": ["images/val/state_id/state_id_fin_085_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('state_id', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"ANDERSON CRYSTAL\"}, {\"field\": \"date_of_birth\", \"value\": \"1985-01-08\"}, {\"field\": \"address\", \"value\": \"839 W 85TH ST APT A, LOS ANGELES, CA 90044\"}, {\"field\": \"issue_date\", \"value\": \"2020-06-05\"}, {\"field\": \"expiration_date\", \"value\": \"2032-01-08\"}, {\"field\": \"state\", \"value\": \"CALIFORNIA\"}]}"}]} | |
| {"id": "state_id_fin_088_p1_classify", "task": "classify", "class": "state_id", "doc": "state_id_fin_088.pdf", "images": ["images/val/state_id/state_id_fin_088_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Classify the document image into exactly one of the given class names (unknown if none fit), and read its identity fields (issuer, holder, page marker) as printed on the page.\n\nclasses = (['bank_statement', 'drivers_license', 'monthly_bill', 'paystub', 'state_id', 'unknown'], 'Allowed class names to choose from.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"cls\": \"state_id\", \"confidence\": 1.0, \"issuer\": \"Delaware\", \"holder\": \"CLINT SAMPLE\", \"page_marker\": \"\"}]}"}]} | |
| {"id": "state_id_fin_088_extract", "task": "extract", "class": "state_id", "doc": "state_id_fin_088.pdf", "images": ["images/val/state_id/state_id_fin_088_p1.png"], "messages": [{"role": "system", "content": " This is a task you must complete by returning only the output.\n Do not include explanations, code, or extra text\u2014only the result.\n "}, {"role": "user", "content": [{"type": "text", "text": "Read the financial document image and extract the requested fields from what is actually printed on it. Return exactly one entry per requested field, using an empty string when a field is absent. Values are short verbatim strings from the document - never sentences or repeated text. Dates as ISO 8601 (YYYY-MM-DD). Amounts as plain numbers without currency symbols or thousands separators.\n\ncls = ('state_id', 'The document class.')\nfields = (['full_name', 'date_of_birth', 'address', 'issue_date', 'expiration_date', 'state'], 'The exact field names to extract.')\nhints = ({'full_name': 'Name', 'date_of_birth': 'Date of Birth', 'address': 'Address', 'issue_date': 'Issued Date', 'expiration_date': 'Valid Until Date', 'state': 'Issuing state'}, 'Per-field guidance mapping a field name to a short description.')"}, {"type": "image"}, {"type": "text", "text": "Schema requirements:\n- schema_object_wrapper (array)"}]}, {"role": "assistant", "content": "{\"schema_object_wrapper\": [{\"field\": \"full_name\", \"value\": \"CLINT SAMPLE\"}, {\"field\": \"date_of_birth\", \"value\": \"1970-04-30\"}, {\"field\": \"address\", \"value\": \"2230 HESSLER BOULEVARD, NEW CASTLE, DE 19720-0000\"}, {\"field\": \"issue_date\", \"value\": \"2018-03-15\"}, {\"field\": \"expiration_date\", \"value\": \"2022-04-30\"}, {\"field\": \"state\", \"value\": \"Delaware\"}]}"}]} | |