| sample_id,domain,category,prompt,fp32_output,int8_output,ground_truth,fp32_correct,int8_correct,difference_type | |
| 6,smart_home,positive,warm the house to 24 degrees,"[{""name"": ""set_thermostat"", ""arguments"": {""temperature"": 24}}]","[{""name"": ""set_thermostat"", ""arguments"": {""temperature"": 24, ""required"": [""temperature""]}}]","[{""name"": ""set_thermostat"", ""arguments"": {""temperature"": 24}}]",True,False,different_argument | |
| 22,smart_home,irrelevant,lock the back door,"[{""name"": ""start_robot_vacuum"", ""arguments"": {""action"": ""dock""}}]",[],[],False,True,different_tool | |
| 23,smart_home,irrelevant,check whether the robot vacuum is charging,"[{""name"": ""start_robot_vacuum"", ""arguments"": {""action"": ""start"", ""room"": ""living_room""}}]","[{""name"": ""start_robot_vacuum"", ""arguments"": {""action"": ""start""}}]",[],False,False,different_argument | |
| 36,kitchen_appliance,positive,brew a fresh pot of coffee,"[{""name"": ""control_coffee_maker"", ""arguments"": {""action"": ""brew""}}, {""name"": ""set_oven"", ""arguments"": {""temperature"": 50}}, {""name"": ""set_cooking_timer"", ""arguments"": {""label"": ""coffee"", ""minutes"": 20}}]","[{""name"": ""control_coffee_maker"", ""arguments"": {""action"": ""brew"", ""cycle"": ""quick""}}]","[{""name"": ""control_coffee_maker"", ""arguments"": {""action"": ""brew""}}]",False,False,different_tool | |
| 51,kitchen_appliance,missing,set a cooking timer for the rice,"[{""name"": ""set_cooking_timer"", ""arguments"": {""label"": ""rice"", ""minutes"": 0}}]","[{""name"": ""set_cooking_timer"", ""arguments"": {""label"": ""rice"", ""minutes"": 30}}]",[],False,False,different_argument | |
| 56,kitchen_appliance,irrelevant,turn the fridge down to 3 degrees,"[{""name"": ""set_oven"", ""arguments"": {""temperature"": 35}}]","[{""name"": ""set_oven"", ""arguments"": {""temperature"": 3}}]",[],False,False,different_argument | |
| 59,kitchen_appliance,negation,never brew coffee this late at night,"[{""name"": ""start_dishwasher"", ""arguments"": {""cycle"": ""quick""}}]","[{""name"": ""set_oven"", ""arguments"": {""temperature"": 180}}]",[],False,False,different_tool | |
| 84,media_player,missing,turn the music down a bit,"[{""name"": ""set_volume"", ""arguments"": {""level"": 15}}]","[{""name"": ""set_volume"", ""arguments"": {""level"": 50}}]",[],False,False,different_argument | |
| 91,media_player,negation,never play Baby Shark on this speaker again,"[{""name"": ""pause_media"", ""arguments"": {}}]","[{""name"": ""set_volume"", ""arguments"": {""level"": 0}}]",[],False,False,different_tool | |
| 101,productivity,positive,remind me tomorrow at noon to renew the car insurance,"[{""name"": ""create_reminder"", ""arguments"": {""message"": ""renew the car insurance"", ""date_time_human"": ""tomorrow at noon""}}]","[{""name"": ""create_reminder"", ""arguments"": {""message"": ""renew the car insurance"", ""date_time_human"": ""tomorrow at 12:00""}}]","[{""name"": ""create_reminder"", ""arguments"": {""message"": ""renew the car insurance"", ""date_time_human"": ""tomorrow at noon""}}]",True,False,different_argument | |
| 107,productivity,positive,add renew my passport to my to-do list,"[{""name"": ""add_task"", ""arguments"": {""title"": ""renew my passport""}}]","[{""name"": ""add_task"", ""arguments"": {""title"": ""my passport""}}]","[{""name"": ""add_task"", ""arguments"": {""title"": ""renew my passport""}}]",True,False,different_argument | |
| 109,productivity,positive,add file the insurance claim as a high priority task,"[{""name"": ""add_task"", ""arguments"": {""title"": ""file the insurance claim"", ""priority"": ""high""}}]","[{""name"": ""add_task"", ""arguments"": {""title"": ""insurance claim"", ""priority"": ""high""}}]","[{""name"": ""add_task"", ""arguments"": {""title"": ""file the insurance claim"", ""priority"": ""high""}}]",True,False,different_argument | |
| 114,productivity,missing,remind me to take out the recycling,"[{""name"": ""create_reminder"", ""arguments"": {""message"": ""take out the recycling"", ""date_time_human"": ""now""}}]","[{""name"": ""create_reminder"", ""arguments"": {""message"": ""take out the recycling"", ""date_time_human"": ""today at 8pm""}}]",[],False,False,different_argument | |
| 119,productivity,irrelevant,check my calendar for this weekend,"[{""name"": ""create_calendar_event"", ""arguments"": {""title"": ""check calendar"", ""start_time_human"": ""2026-10-08""}}]","[{""name"": ""create_calendar_event"", ""arguments"": {""title"": ""check calendar"", ""start_time_human"": ""2026-10-06""}}]",[],False,False,different_argument | |
| 124,productivity,invalid,set a timer for negative 5 minutes,"[{""name"": ""set_timer"", ""arguments"": {""time_human"": ""05 minutes""}}]","[{""name"": ""set_timer"", ""arguments"": {""time_human"": ""5 minutes""}}]",[],False,False,different_argument | |
| 125,productivity,invalid,remind me yesterday at 4pm to submit the timesheet,"[{""name"": ""create_reminder"", ""arguments"": {""message"": ""submit the timesheet"", ""date_time_human"": ""2026-10-03 16:00""}}]","[{""name"": ""create_reminder"", ""arguments"": {""message"": ""submit the timesheet"", ""date_time_human"": ""2026-10-05 16:00""}}]",[],False,False,different_argument | |
| 150,wearable,irrelevant,check my heart rate on the watch,"[{""name"": ""find_my_phone"", ""arguments"": {}}]",[],[],False,True,different_tool | |
| 151,wearable,irrelevant,call Maya from my watch,"[{""name"": ""reply_to_notification"", ""arguments"": {""notification_match"": ""Maya"", ""text"": ""call Maya from my watch""}}]","[{""name"": ""reply_to_notification"", ""arguments"": {""notification_match"": ""Maya"", ""text"": ""call""}}]",[],False,False,different_argument | |
| 153,wearable,negation,don't reply to the message from Leo,"[{""name"": ""reply_to_notification"", ""arguments"": {""notification_match"": ""Leo"", ""text"": ""don't reply""}}]","[{""name"": ""reply_to_notification"", ""arguments"": {""notification_match"": ""Leo"", ""text"": ""I don't reply""}}]",[],False,False,different_argument | |
| 154,wearable,negation,do not start a running workout yet,"[{""name"": ""end_workout"", ""arguments"": {}}]","[{""name"": ""start_workout"", ""arguments"": {""workout_type"": ""running""}}]",[],False,False,different_tool | |
| 178,data_capture,missing,log an expense of 45 from this afternoon,"[{""name"": ""log_expense"", ""arguments"": {""amount"": 45, ""category"": ""food""}}]","[{""name"": ""log_expense"", ""arguments"": {""amount"": 45, ""category"": ""lunch""}}]",[],False,False,different_argument | |
| 184,data_capture,irrelevant,delete yesterday's lunch entry from the log,"[{""name"": ""log_meal"", ""arguments"": {""description"": ""lunch"", ""meal_type"": ""lunch""}}]",[],[],False,True,different_tool | |
| 207,productivity,negation_calendar,"Never mind, do not schedule any meeting with Bob on Friday","[{""name"": ""create_calendar_event"", ""arguments"": {""title"": ""meeting with Bob"", ""start_time_human"": ""Friday at 9:00""}}]","[{""name"": ""create_calendar_event"", ""arguments"": {""title"": ""meeting with Bob"", ""start_time_human"": ""Friday at 10:00""}}]",[],False,False,different_argument | |