messages listlengths 3 3 | metadata dict |
|---|---|
[
{
"role": "system",
"content": "You are an expert in TOML format. Analyze the data structure and generate syntactically perfect TOML."
},
{
"role": "user",
"content": "Transform this data from XML to TOML:\n<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<api_specification>\n<endpoint>/api/v1/users<... | {
"format": "toml",
"complexity": "medium",
"schema": "api_specification",
"type": "conversion",
"prompt": "Transform this data from XML to TOML:\n<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<api_specification>\n<endpoint>/api/v1/users</endpoint>\n<method>GET</method>\n<responses>\n<_200>OK</_200>\n</responses>\n</api_specification>",
"output": "Approach:\n1. Analyze the input XML structure: It represents a dictionary with 3 root fields (endpoint, method, responses) and a nesting depth of 2.\n2. Identify the target format requirements: TOML requires strict syntax. Define hierarchy using dot-notation or [section] headers.\n3. Map the fields: The root keys will map directly, while nested objects need careful formatting.\n4. Handle data types: Ensure strings, numbers, and booleans are formatted correctly for the target.\n5. Construct the output: serialized the data strictly following the target schema.\n\nOutput:\nendpoint = \"/api/v1/users\"\nmethod = \"GET\"\n\n[responses]\n200 = \"OK\"\n",
"estimated_tokens": 158
} |
[
{
"role": "system",
"content": "You are an expert in TOML format. Analyze the data structure and generate syntactically perfect TOML."
},
{
"role": "user",
"content": "Reformat the XML below into TOML:\n<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<error_log>\n<timestamp>2026-01-22T04:03:07.31557... | {
"format": "toml",
"complexity": "complex",
"schema": "error_log",
"type": "conversion",
"prompt": "Reformat the XML below into TOML:\n<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<error_log>\n<timestamp>2026-01-22T04:03:07.315575</timestamp>\n<level>ERROR</level>\n<message>Anyone trip thus player thank will.</message>\n<meta_info>\n<generated_at>2026-01-22T04:03:07.315727</generated_at>\n<version>v4.0</version>\n<tags>lay</tags>\n<tags>moment</tags>\n<tags>paper</tags>\n<tags>charge</tags>\n<tags>so</tags>\n</meta_info>\n<audit_log>\n<action>created</action>\n<by>william85</by>\n<timestamp>1974-04-08T19:46:38.582654</timestamp>\n</audit_log>\n<audit_log>\n<action>created</action>\n<by>ogutierrez</by>\n<timestamp>1995-10-31T20:35:18.036308</timestamp>\n</audit_log>\n<audit_log>\n<action>created</action>\n<by>david86</by>\n<timestamp>2010-06-08T05:13:57.827920</timestamp>\n</audit_log>\n</error_log>",
"output": "Approach:\n1. Analyze the input XML structure: It represents a dictionary with 5 root fields (timestamp, level, message...) and a nesting depth of 3.\n2. Identify the target format requirements: TOML requires strict syntax. Define hierarchy using dot-notation or [section] headers.\n3. Map the fields: The root keys will map directly, while nested objects need careful formatting.\n4. Handle data types: Ensure strings, numbers, and booleans are formatted correctly for the target.\n5. Construct the output: serialized the data strictly following the target schema.\n\nOutput:\ntimestamp = \"2026-01-22T04:03:07.315575\"\nlevel = \"ERROR\"\nmessage = \"Anyone trip thus player thank will.\"\n[[audit_log]]\naction = \"created\"\nby = \"william85\"\ntimestamp = \"1974-04-08T19:46:38.582654\"\n\n[[audit_log]]\naction = \"created\"\nby = \"ogutierrez\"\ntimestamp = \"1995-10-31T20:35:18.036308\"\n\n[[audit_log]]\naction = \"created\"\nby = \"david86\"\ntimestamp = \"2010-06-08T05:13:57.827920\"\n\n[meta_info]\ngenerated_at = \"2026-01-22T04:03:07.315727\"\nversion = \"v4.0\"\ntags = [ \"lay\", \"moment\", \"paper\", \"charge\", \"so\",]\n",
"estimated_tokens": 268
} |
[
{
"role": "system",
"content": "You are an expert in CSV format. Analyze the data structure and generate syntactically perfect CSV."
},
{
"role": "user",
"content": "Generate social media post data in CSV format."
},
{
"role": "assistant",
"content": "Approach:\n1. Define the schema:... | {
"format": "csv",
"complexity": "simple",
"schema": "social_media_post",
"type": "generation",
"prompt": "Generate social media post data in CSV format.",
"output": "Approach:\n1. Define the schema: The social_media_post should contain a dictionary with 3 root fields (user, post, likes) and a nesting depth of 1.\n2. Select the format: CSV is chosen. Flatten the hierarchical structure. Use dot notation for nested keys in the header.\n3. Generate realistic content: Use plausible names, dates, and values appropriate for the domain.\n4. Structure the data: Organize the fields logically with appropriate nesting and hierarchies.\n5. Serialize: Output the final string making sure to escape special characters if necessary.\n\nOutput:\nuser,post,likes\r\nboyersylvia,Interview knowledge ready hold establish hotel several. Money subject away without special. Oil whether short air become.,450\r\n",
"estimated_tokens": 179
} |
[
{
"role": "system",
"content": "You are an expert in JSON format. Analyze the data structure and generate syntactically perfect JSON."
},
{
"role": "user",
"content": "Transform this data from XML to JSON:\n<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<clinical_note>\n<id>67e1b420-549d-4744-8cb3-... | {
"format": "json",
"complexity": "simple",
"schema": "clinical_note",
"type": "conversion",
"prompt": "Transform this data from XML to JSON:\n<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<clinical_note>\n<id>67e1b420-549d-4744-8cb3-627e50fd14ec</id>\n<patient>Brandon Herrera</patient>\n<diagnosis>arrive</diagnosis>\n<notes>Poor story computer single. Need similar consumer a. Special new company across want PM right of.</notes>\n</clinical_note>",
"output": "Approach:\n1. Analyze the input XML structure: It represents a dictionary with 4 root fields (id, patient, diagnosis...) and a nesting depth of 1.\n2. Identify the target format requirements: JSON requires strict syntax. Ensure all keys are quoted and nested structures use curly braces.\n3. Map the fields: The root keys will map directly, while nested objects need careful formatting.\n4. Handle data types: Ensure strings, numbers, and booleans are formatted correctly for the target.\n5. Construct the output: serialized the data strictly following the target schema.\n\nOutput:\n{\n \"id\": \"67e1b420-549d-4744-8cb3-627e50fd14ec\",\n \"patient\": \"Brandon Herrera\",\n \"diagnosis\": \"arrive\",\n \"notes\": \"Poor story computer single. Need similar consumer a. Special new company across want PM right of.\"\n}",
"estimated_tokens": 198
} |
[
{
"role": "system",
"content": "You are an expert in XML format. Analyze the data structure and generate syntactically perfect XML."
},
{
"role": "user",
"content": "Convert the following CSV to XML:\nexperiment_id,title,metrics.accuracy,metrics.loss,metrics.epoch,config.batch_size,config.optimi... | {
"format": "xml",
"complexity": "complex",
"schema": "experiment_result",
"type": "conversion",
"prompt": "Convert the following CSV to XML:\nexperiment_id,title,metrics.accuracy,metrics.loss,metrics.epoch,config.batch_size,config.optimizer,config.lr,meta_info.generated_at,meta_info.version,meta_info.tags,audit_log\r\nEXP-436797,Analysis of southern,0.8346,0.0432,69,64,adam,0.001,2026-01-22T04:03:06.756426,v5.0,\"[\"\"man\"\", \"\"interesting\"\", \"\"seven\"\", \"\"able\"\", \"\"station\"\"]\",\"[{\"\"action\"\": \"\"created\"\", \"\"by\"\": \"\"saunderslaura\"\", \"\"timestamp\"\": \"\"2006-10-01T11:45:31.111840\"\"}, {\"\"action\"\": \"\"created\"\", \"\"by\"\": \"\"jeremyparks\"\", \"\"timestamp\"\": \"\"1972-05-29T19:06:07.196206\"\"}, {\"\"action\"\": \"\"created\"\", \"\"by\"\": \"\"barbara53\"\", \"\"timestamp\"\": \"\"2018-08-16T05:36:00.598648\"\"}]\"\r\n",
"output": "Approach:\n1. Analyze the input CSV structure: It represents a dictionary with 6 root fields (experiment_id, title, metrics...) and a nesting depth of 3.\n2. Identify the target format requirements: XML requires strict syntax. Map dictionary keys to tags. Handle list items by repeating child tags.\n3. Map the fields: The root keys will map directly, while nested objects need careful formatting.\n4. Handle data types: Ensure strings, numbers, and booleans are formatted correctly for the target.\n5. Construct the output: serialized the data strictly following the target schema.\n\nOutput:\n<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<experiment_result>\n<experiment_id>EXP-436797</experiment_id>\n<title>Analysis of southern</title>\n<metrics>\n<accuracy>0.8346</accuracy>\n<loss>0.0432</loss>\n<epoch>69</epoch>\n</metrics>\n<config>\n<batch_size>64</batch_size>\n<optimizer>adam</optimizer>\n<lr>0.001</lr>\n</config>\n<meta_info>\n<generated_at>2026-01-22T04:03:06.756426</generated_at>\n<version>v5.0</version>\n<tags>man</tags>\n<tags>interesting</tags>\n<tags>seven</tags>\n<tags>able</tags>\n<tags>station</tags>\n</meta_info>\n<audit_log>\n<action>created</action>\n<by>saunderslaura</by>\n<timestamp>2006-10-01T11:45:31.111840</timestamp>\n</audit_log>\n<audit_log>\n<action>created</action>\n<by>jeremyparks</by>\n<timestamp>1972-05-29T19:06:07.196206</timestamp>\n</audit_log>\n<audit_log>\n<action>created</action>\n<by>barbara53</by>\n<timestamp>2018-08-16T05:36:00.598648</timestamp>\n</audit_log>\n</experiment_result>",
"estimated_tokens": 372
} |
[
{
"role": "system",
"content": "You are an expert in TOML format. Analyze the data structure and generate syntactically perfect TOML."
},
{
"role": "user",
"content": "Create a TOML representation of lab result."
},
{
"role": "assistant",
"content": "Approach:\n1. Define the schema: ... | {
"format": "toml",
"complexity": "complex",
"schema": "lab_result",
"type": "generation",
"prompt": "Create a TOML representation of lab result.",
"output": "Approach:\n1. Define the schema: The lab_result should contain a dictionary with 5 root fields (id, test, value...) and a nesting depth of 3.\n2. Select the format: TOML is chosen. Define hierarchy using dot-notation or [section] headers.\n3. Generate realistic content: Use plausible names, dates, and values appropriate for the domain.\n4. Structure the data: Organize the fields logically with appropriate nesting and hierarchies.\n5. Serialize: Output the final string making sure to escape special characters if necessary.\n\nOutput:\nid = \"ce6ab4d4-4e57-435d-bf44-68b0ddda8b05\"\ntest = \"necessary\"\nvalue = 36.569220334710764\n[[audit_log]]\naction = \"created\"\nby = \"elizabethmcdonald\"\ntimestamp = \"2024-10-17T08:29:18.608704\"\n\n[[audit_log]]\naction = \"created\"\nby = \"ewebb\"\ntimestamp = \"1997-12-18T06:07:52.332788\"\n\n[meta_info]\ngenerated_at = \"2026-01-22T04:03:06.974558\"\nversion = \"v5.0\"\ntags = [ \"feeling\", \"ask\", \"ready\", \"interesting\", \"discussion\",]\n",
"estimated_tokens": 237
} |
[
{
"role": "system",
"content": "You are an expert in JSON format. Analyze the data structure and generate syntactically perfect JSON."
},
{
"role": "user",
"content": "Create a JSON representation of product listing."
},
{
"role": "assistant",
"content": "Approach:\n1. Define the sch... | {
"format": "json",
"complexity": "complex",
"schema": "product_listing",
"type": "generation",
"prompt": "Create a JSON representation of product listing.",
"output": "Approach:\n1. Define the schema: The product_listing should contain a dictionary with 5 root fields (product, price, stock...) and a nesting depth of 3.\n2. Select the format: JSON is chosen. Ensure all keys are quoted and nested structures use curly braces.\n3. Generate realistic content: Use plausible names, dates, and values appropriate for the domain.\n4. Structure the data: Organize the fields logically with appropriate nesting and hierarchies.\n5. Serialize: Output the final string making sure to escape special characters if necessary.\n\nOutput:\n{\n \"product\": \"common\",\n \"price\": 16.96,\n \"stock\": 9,\n \"meta_info\": {\n \"generated_at\": \"2026-01-22T04:03:06.623023\",\n \"version\": \"v1.0\",\n \"tags\": [\n \"leave\",\n \"music\",\n \"side\",\n \"feeling\",\n \"car\"\n ]\n },\n \"audit_log\": [\n {\n \"action\": \"created\",\n \"by\": \"miranda27\",\n \"timestamp\": \"2015-12-10T21:15:20.214770\"\n }\n ]\n}",
"estimated_tokens": 232
} |
[
{
"role": "system",
"content": "You are an expert in YAML format. Analyze the data structure and generate syntactically perfect YAML."
},
{
"role": "user",
"content": "Transform this data from CSV to YAML:\nstudent,score,grade\r\nJohn Booth,62,A\r\n"
},
{
"role": "assistant",
"conten... | {
"format": "yaml",
"complexity": "medium",
"schema": "student_assessment",
"type": "conversion",
"prompt": "Transform this data from CSV to YAML:\nstudent,score,grade\r\nJohn Booth,62,A\r\n",
"output": "Approach:\n1. Analyze the input CSV structure: It represents a dictionary with 3 root fields (student, score, grade) and a nesting depth of 1.\n2. Identify the target format requirements: YAML requires strict syntax. Use indentation to represent nesting. lists are denoted by hyphens.\n3. Map the fields: The root keys will map directly, while nested objects need careful formatting.\n4. Handle data types: Ensure strings, numbers, and booleans are formatted correctly for the target.\n5. Construct the output: serialized the data strictly following the target schema.\n\nOutput:\nstudent: John Booth\nscore: 62\ngrade: A\n",
"estimated_tokens": 153
} |
Subsets and Splits
Format and Complexity Counts
Groups training examples by their format and complexity metadata to reveal patterns in dataset structure and potentially identify undersampled combinations that could inform data balancing strategies.