answer stringlengths 2 697 | deep_reasoning stringlengths 175 534 | dialogue_history listlengths 3 65 | dialogue_id stringlengths 21 51 | domain stringclasses 14
values | id stringlengths 41 72 | is_high_quality bool 2
classes | metadata unknown | quality_flags listlengths 0 10 | quality_score float64 0 1 | source_dataset stringclasses 3
values | source_id stringlengths 11 40 | split stringclasses 1
value | streaming_chunks listlengths 3 65 | streaming_reasoning listlengths 3 65 | task_type stringclasses 1
value |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Good. Have you got any other questions? | The dialogue is technical support in education career, with information request intent. Key constraints are event_type=appointment. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Excuse me. I have an appointment with Mr. Li at nine. May I come in?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes, come in please. I am Mr. Li. You must be My Liu, right?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Yes, I am My Li... | DailyDialog_test_000074 | schedule | life_mt_sct_DailyDialog_test_000074_target16 | true | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categor... | [] | 0.899 | DailyDialog | test_000074 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: event_type; changed slots: none; removed slots: none.",
"reasoning_confidence": "high",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: event_type; changed slots: none; removed slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
You're all set on that train, and your reservation reference number is 3XM02AO1. The total due at the station will be 132.8GBP. Can I help with anything else today? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=wednesday; destination=london, london liverpool; origin=cambridge; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Hi, I need a train that leaves on Wednesday and arrives by 08:45.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'm going to need a little more information from you. Where will you be leaving from? Where are you traveling to?",
"turn_id": 2
},
{
... | MultiWOZ_PMUL1121.json | travel | life_mt_sct_MultiWOZ_PMUL1121.json_target8 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [] | 1 | MultiWOZ | PMUL1121.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: date_or_duration, transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none. Unsupported ... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: date_or_duration, transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none. Unsupported ... | prefix_to_next_assistant_text |
Okay, is that all? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=wednesday; destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi. I need help finding a flight to Paris, France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, great.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like to leave on Wednesday, April 12th.",
"turn_id": 3
},
{
"spea... | Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | travel | life_mt_sct_Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235_target6 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 0.899 | Taskmaster | dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | prefix_to_next_assistant_text |
Ok, I will contact you in a week. See you. | The dialogue is technical support in education career, with confirmation clarification intent. Key constraints are event_type=appointment. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Excuse me. I have an appointment with Mr. Li at nine. May I come in?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes, come in please. I am Mr. Li. You must be My Liu, right?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Yes, I am My Li... | DailyDialog_test_000074 | schedule | life_mt_sct_DailyDialog_test_000074_target18 | true | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categor... | [
"premature_respond"
] | 0.95 | DailyDialog | test_000074 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: event_type; changed slots: none; removed slots: none.",
"reasoning_confidence": "high",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: event_type; changed slots: none; removed slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Sure! I highly suggest All Saints Church. Would you like more information? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=wednesday; destination=london, london liverpool; origin=cambridge; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Hi, I need a train that leaves on Wednesday and arrives by 08:45.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'm going to need a little more information from you. Where will you be leaving from? Where are you traveling to?",
"turn_id": 2
},
{
... | MultiWOZ_PMUL1121.json | travel | life_mt_sct_MultiWOZ_PMUL1121.json_target10 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [] | 1 | MultiWOZ | PMUL1121.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: date_or_duration, transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none. Unsupported ... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: date_or_duration, transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none. Unsupported ... | prefix_to_next_assistant_text |
Ok. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=wednesday; destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi. I need help finding a flight to Paris, France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, great.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like to leave on Wednesday, April 12th.",
"turn_id": 3
},
{
"spea... | Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | travel | life_mt_sct_Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235_target8 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [
"answer_not_grounded",
"fragment_answer",
"generic_answer",
"too_short_answer",
"weak_target_answer"
] | 0 | Taskmaster | dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | prefix_to_next_assistant_text |
I suggest the Old Schools. The address is Trinity Lane and the phone number is [phone removed]. | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=wednesday; destination=london, london liverpool; origin=cambridge; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Hi, I need a train that leaves on Wednesday and arrives by 08:45.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'm going to need a little more information from you. Where will you be leaving from? Where are you traveling to?",
"turn_id": 2
},
{
... | MultiWOZ_PMUL1121.json | travel | life_mt_sct_MultiWOZ_PMUL1121.json_target12 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [] | 1 | MultiWOZ | PMUL1121.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: date_or_duration, transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none. Unsupported ... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: date_or_duration, transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none. Unsupported ... | prefix_to_next_assistant_text |
Okay, anything else? | The visible history is a flight booking task in travel transportation. Known constraints are budget=$1,000; date_or_duration=wednesday; destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi. I need help finding a flight to Paris, France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, great.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like to leave on Wednesday, April 12th.",
"turn_id": 3
},
{
"spea... | Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | travel | life_mt_sct_Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235_target10 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [
"too_short_answer",
"weak_target_answer"
] | 0.68 | Taskmaster | dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | prefix_to_next_assistant_text |
You are very welcome. Enjoy your trip. | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=wednesday; destination=london, london liverpool; origin=cambridge; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Hi, I need a train that leaves on Wednesday and arrives by 08:45.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'm going to need a little more information from you. Where will you be leaving from? Where are you traveling to?",
"turn_id": 2
},
{
... | MultiWOZ_PMUL1121.json | travel | life_mt_sct_MultiWOZ_PMUL1121.json_target14 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [] | 0.899 | MultiWOZ | PMUL1121.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: date_or_duration, transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none. Unsupported ... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: date_or_duration, transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none. Unsupported ... | prefix_to_next_assistant_text |
Ok sure. Just to confirm you are looking for flights out from Houston to Paris. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$1,000; date_or_duration=wednesday; destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi. I need help finding a flight to Paris, France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, great.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like to leave on Wednesday, April 12th.",
"turn_id": 3
},
{
"spea... | Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | travel | life_mt_sct_Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235_target12 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 1 | Taskmaster | dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | prefix_to_next_assistant_text |
Outlets have more reasonable prices. | The dialogue is shopping assistance in shopping retail, with planning coordination intent. Key constraints are item_type=n inexpensive cashmere sweater. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Hello, where can I buy an inexpensive cashmere sweater?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Maybe you should look around for an outlet.",
"turn_id": 2
},
{
"speaker": "user",
"text": "That is a wonderful idea.",
"turn_id": 3
... | DailyDialog_test_000076 | shopping | life_mt_sct_DailyDialog_test_000076_target4 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"shopping_retail"
],
"domain_category"... | [
"low_information_answer"
] | 0.749 | DailyDialog | test_000076 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: item_type; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: item_type; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",... | prefix_to_next_assistant_text |
Sure, they are in the moderate price range. | The visible history is a restaurant search task in food dining. It should track cuisine, area, and price. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "Could you tell me where Cotto is located?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have them at 183 East Road City Centre, cb11bg.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Great! Do you know what price range they are in?",
... | MultiWOZ_SNG02071.json | shopping | life_mt_sct_MultiWOZ_SNG02071.json_target4 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dining"
],
"domain_categ... | [
"weak_final_state"
] | 0.899 | MultiWOZ | SNG02071.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: item_type; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: item_type; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Okay, I found a flight departing at 3:40 p.m. with their friends. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$1,000; date_or_duration=wednesday; destination=paris; transport_type=flight. The answer should address the confirmation clarification step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi. I need help finding a flight to Paris, France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, great.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like to leave on Wednesday, April 12th.",
"turn_id": 3
},
{
"spea... | Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | travel | life_mt_sct_Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235_target14 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 1 | Taskmaster | dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | prefix_to_next_assistant_text |
No problem. Good luck | The dialogue is shopping assistance in shopping retail, with problem solving intent. Key constraints are item_type=n inexpensive cashmere sweater. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Hello, where can I buy an inexpensive cashmere sweater?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Maybe you should look around for an outlet.",
"turn_id": 2
},
{
"speaker": "user",
"text": "That is a wonderful idea.",
"turn_id": 3
... | DailyDialog_test_000076 | shopping | life_mt_sct_DailyDialog_test_000076_target6 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"shopping_retail"
],
"domain_category"... | [
"low_information_answer"
] | 0.749 | DailyDialog | test_000076 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: item_type; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: item_type; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",... | prefix_to_next_assistant_text |
You're welcome. Have a great day. | The visible history is a restaurant search task in food dining. It should track cuisine, area, and price. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "Could you tell me where Cotto is located?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have them at 183 East Road City Centre, cb11bg.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Great! Do you know what price range they are in?",
... | MultiWOZ_SNG02071.json | shopping | life_mt_sct_MultiWOZ_SNG02071.json_target6 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dining"
],
"domain_categ... | [
"low_information_answer",
"weak_final_state"
] | 0.749 | MultiWOZ | SNG02071.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: item_type; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: item_type; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
The ticket price is $893 round trip. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$1,000; date_or_duration=wednesday; destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi. I need help finding a flight to Paris, France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, great.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like to leave on Wednesday, April 12th.",
"turn_id": 3
},
{
"spea... | Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | travel | life_mt_sct_Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235_target16 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 0.899 | Taskmaster | dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | prefix_to_next_assistant_text |
They're 250NT each, but they're not edible. They're only used for worship. | The dialogue is uncertain context in general daily life, with information request intent. Key constraints are budget=30. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Wow! Your fruit looks really fresh! How much are these apples?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "The apples are 30NT each. How many would you like?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Let's see, 30NT is about... alm... | DailyDialog_test_000077 | other_life | life_mt_sct_DailyDialog_test_000077_target4 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"general_daily_lif... | [
"low_taxonomy_confidence"
] | 0.749 | DailyDialog | test_000077 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
Return departs at 10:10 a.m. with Air France. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$1,000; date_or_duration=wednesday; destination=paris; transport_type=flight. The answer should address the customer support step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi. I need help finding a flight to Paris, France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, great.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like to leave on Wednesday, April 12th.",
"turn_id": 3
},
{
"spea... | Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | travel | life_mt_sct_Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235_target18 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 1 | Taskmaster | dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | prefix_to_next_assistant_text |
Wait! Don't go just yet. These bananas are pretty cheap--only 35NT for this bunch. | The dialogue is uncertain context in general daily life, with information request intent. Key constraints are budget=30, 250, 8 dollars. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Wow! Your fruit looks really fresh! How much are these apples?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "The apples are 30NT each. How many would you like?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Let's see, 30NT is about... alm... | DailyDialog_test_000077 | other_life | life_mt_sct_DailyDialog_test_000077_target6 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"general_daily_lif... | [
"low_taxonomy_confidence"
] | 0.749 | DailyDialog | test_000077 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
Okay great, is that all? | The visible history is a flight booking task in travel transportation. Known constraints are budget=$1,000; date_or_duration=wednesday; destination=paris; transport_type=flight. The answer should address the confirmation clarification step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi. I need help finding a flight to Paris, France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, great.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like to leave on Wednesday, April 12th.",
"turn_id": 3
},
{
"spea... | Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | travel | life_mt_sct_Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235_target20 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 0.899 | Taskmaster | dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | prefix_to_next_assistant_text |
They're also good for your digestion! Would you like some kiwis, too? | The dialogue is uncertain context in general daily life, with information request intent. Key constraints are budget=30, 250, 8 dollars. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Wow! Your fruit looks really fresh! How much are these apples?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "The apples are 30NT each. How many would you like?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Let's see, 30NT is about... alm... | DailyDialog_test_000077 | other_life | life_mt_sct_DailyDialog_test_000077_target8 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"general_daily_lif... | [
"low_taxonomy_confidence"
] | 0.749 | DailyDialog | test_000077 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
That feature is unavailable at the moment. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$1,000; date_or_duration=wednesday; destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi. I need help finding a flight to Paris, France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, great.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like to leave on Wednesday, April 12th.",
"turn_id": 3
},
{
"spea... | Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | travel | life_mt_sct_Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235_target22 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 0.899 | Taskmaster | dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | prefix_to_next_assistant_text |
They're imported from New Zealand. Four for 50NT. Nine for a hundred. | The dialogue is uncertain context in general daily life, with information request intent. Key constraints are budget=30, 250, 8 dollars. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Wow! Your fruit looks really fresh! How much are these apples?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "The apples are 30NT each. How many would you like?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Let's see, 30NT is about... alm... | DailyDialog_test_000077 | other_life | life_mt_sct_DailyDialog_test_000077_target10 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"general_daily_lif... | [
"low_taxonomy_confidence"
] | 0.749 | DailyDialog | test_000077 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
1:45 p.m. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$1,000; date_or_duration=wednesday; destination=paris; transport_type=flight. The answer should address the customer support step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi. I need help finding a flight to Paris, France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, great.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like to leave on Wednesday, April 12th.",
"turn_id": 3
},
{
"spea... | Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | travel | life_mt_sct_Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235_target24 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [
"low_information_answer"
] | 0.749 | Taskmaster | dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | prefix_to_next_assistant_text |
really? Why? | The dialogue is uncertain context in general daily life, with information request intent. The most recent user context is: well, I wanted to let you know that I've put in my notice. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Amelia, could you spare a few minutes?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "sure. What do you need?",
"turn_id": 2
},
{
"speaker": "user",
"text": "well, I wanted to let you know that I've put in my notice.",
"turn_id": 3
}
... | DailyDialog_test_000078 | schedule | life_mt_sct_DailyDialog_test_000078_target4 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"general_daily_lif... | [
"low_taxonomy_confidence",
"too_short_answer",
"weak_final_state",
"weak_target_answer"
] | 0.6 | DailyDialog | test_000078 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
8:15 in the morning. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$1,000, 3; date_or_duration=wednesday; destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi. I need help finding a flight to Paris, France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, great.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like to leave on Wednesday, April 12th.",
"turn_id": 3
},
{
"spea... | Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | travel | life_mt_sct_Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235_target26 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [
"low_information_answer"
] | 0.749 | Taskmaster | dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | prefix_to_next_assistant_text |
but surely they won't fire you! You're one of the most experienced managers here! | The dialogue is workplace conversation in education career, with planning coordination intent. The most recent user context is: it's complicated. But basically it boils down to one thing. This company is downsizing and I can't continue working for a company that may let me go. The answer is grounded only in the visible... | [
{
"speaker": "user",
"text": "Amelia, could you spare a few minutes?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "sure. What do you need?",
"turn_id": 2
},
{
"speaker": "user",
"text": "well, I wanted to let you know that I've put in my notice.",
"turn_id": 3
},... | DailyDialog_test_000078 | schedule | life_mt_sct_DailyDialog_test_000078_target6 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"education_career"... | [
"fragment_answer",
"premature_respond",
"weak_final_state"
] | 0.499 | DailyDialog | test_000078 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
there is none that serves that food. can you change location? | This sample contains safety-sensitive context. The reasoning should stay conservative, avoid amplifying sensitive details, and only support a safe, bounded assistant response. | [
{
"speaker": "user",
"text": "I am on a budget and need a cheap place to eat.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "There are 22 cheap places to eat in the area. Do you have a preference of food type?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like Ind... | MultiWOZ_PMUL4833.json | cooking | life_mt_sct_MultiWOZ_PMUL4833.json_target4 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"financial_context",
"sensitive_content"
] | 0.749 | MultiWOZ | PMUL4833.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | prefix_to_next_assistant_text |
Your welcome. Goodbye. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$1,000, 3; date_or_duration=wednesday; destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi. I need help finding a flight to Paris, France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, great.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like to leave on Wednesday, April 12th.",
"turn_id": 3
},
{
"spea... | Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | travel | life_mt_sct_Taskmaster_dlg-02329aef-3c98-40bc-ae70-c11eeeca2235_target28 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [
"fragment_answer",
"low_information_answer",
"too_short_answer",
"weak_target_answer"
] | 0.25 | Taskmaster | dlg-02329aef-3c98-40bc-ae70-c11eeeca2235 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confi... | prefix_to_next_assistant_text |
well that's great news! Congratulations! Where will you be located? | The dialogue is workplace conversation in education career, with information request intent. The most recent user context is: well, to be honest, there's another reason. I've got a better offer. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Amelia, could you spare a few minutes?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "sure. What do you need?",
"turn_id": 2
},
{
"speaker": "user",
"text": "well, I wanted to let you know that I've put in my notice.",
"turn_id": 3
},... | DailyDialog_test_000078 | schedule | life_mt_sct_DailyDialog_test_000078_target8 | true | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"education_career"... | [
"weak_final_state"
] | 0.97 | DailyDialog | test_000078 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
la raza is fine for you. can i give you the contact? | This sample contains safety-sensitive context. The reasoning should stay conservative, avoid amplifying sensitive details, and only support a safe, bounded assistant response. | [
{
"speaker": "user",
"text": "I am on a budget and need a cheap place to eat.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "There are 22 cheap places to eat in the area. Do you have a preference of food type?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like Ind... | MultiWOZ_PMUL4833.json | cooking | life_mt_sct_MultiWOZ_PMUL4833.json_target6 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"financial_context",
"sensitive_content"
] | 0.749 | MultiWOZ | PMUL4833.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | prefix_to_next_assistant_text |
Are layovers okay? | The visible history is a flight booking task in travel transportation. Known constraints are destination=chicago, los angeles; origin=los angeles; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. All right, today I need your help finding up a flight, a round trip flight from Los Angeles to Chicago.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "For what days?",
"turn_id": 2
},
{
"speaker": "user",
"text": "The days are going ... | Taskmaster_dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a | travel | life_mt_sct_Taskmaster_dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a_target4 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [
"too_short_answer",
"weak_target_answer"
] | 0.68 | Taskmaster | dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
it'll be sad to see you go, but it sounds like you're found yourself a great opportunity. | The dialogue is workplace conversation in education career, with information request intent. Key constraints are location=new york. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Amelia, could you spare a few minutes?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "sure. What do you need?",
"turn_id": 2
},
{
"speaker": "user",
"text": "well, I wanted to let you know that I've put in my notice.",
"turn_id": 3
},... | DailyDialog_test_000078 | schedule | life_mt_sct_DailyDialog_test_000078_target10 | true | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"education_career"... | [
"premature_respond"
] | 0.95 | DailyDialog | test_000078 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
Booking was successful. The table will be reserved for 15 minutes. Reference number is: UKTN9VKD. | This sample contains safety-sensitive context. The reasoning should stay conservative, avoid amplifying sensitive details, and only support a safe, bounded assistant response. | [
{
"speaker": "user",
"text": "I am on a budget and need a cheap place to eat.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "There are 22 cheap places to eat in the area. Do you have a preference of food type?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like Ind... | MultiWOZ_PMUL4833.json | cooking | life_mt_sct_MultiWOZ_PMUL4833.json_target8 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"financial_context",
"premature_respond",
"sensitive_content"
] | 0.749 | MultiWOZ | PMUL4833.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | prefix_to_next_assistant_text |
What time would you like to leave? | The visible history is a flight booking task in travel transportation. Known constraints are destination=chicago, los angeles; origin=los angeles; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. All right, today I need your help finding up a flight, a round trip flight from Los Angeles to Chicago.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "For what days?",
"turn_id": 2
},
{
"speaker": "user",
"text": "The days are going ... | Taskmaster_dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a | travel | life_mt_sct_Taskmaster_dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a_target6 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 0.899 | Taskmaster | dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
I'm sorry to bring this up, but would it be possible for you to write me a letter of recommendation before you go? | The dialogue is workplace conversation in education career, with information request intent. Key constraints are location=new york. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Amelia, could you spare a few minutes?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "sure. What do you need?",
"turn_id": 2
},
{
"speaker": "user",
"text": "well, I wanted to let you know that I've put in my notice.",
"turn_id": 3
},... | DailyDialog_test_000078 | schedule | life_mt_sct_DailyDialog_test_000078_target12 | true | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"education_career"... | [] | 1 | DailyDialog | test_000078 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
El Shaddai is an inexpensive guesthouse with internet service. Would you like me to make you a reservation there? | This sample contains safety-sensitive context. The reasoning should stay conservative, avoid amplifying sensitive details, and only support a safe, bounded assistant response. | [
{
"speaker": "user",
"text": "I am on a budget and need a cheap place to eat.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "There are 22 cheap places to eat in the area. Do you have a preference of food type?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like Ind... | MultiWOZ_PMUL4833.json | cooking | life_mt_sct_MultiWOZ_PMUL4833.json_target10 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"financial_context",
"sensitive_content"
] | 0.749 | MultiWOZ | PMUL4833.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | prefix_to_next_assistant_text |
Got it. The Earliest flight is at 5:48 AM for departure. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=morning; destination=chicago, los angeles; origin=los angeles; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. All right, today I need your help finding up a flight, a round trip flight from Los Angeles to Chicago.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "For what days?",
"turn_id": 2
},
{
"speaker": "user",
"text": "The days are going ... | Taskmaster_dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a | travel | life_mt_sct_Taskmaster_dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a_target8 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 1 | Taskmaster | dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
thanks. I appreciate that. | The dialogue is workplace conversation in education career, with recommendation intent. Key constraints are location=new york. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Amelia, could you spare a few minutes?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "sure. What do you need?",
"turn_id": 2
},
{
"speaker": "user",
"text": "well, I wanted to let you know that I've put in my notice.",
"turn_id": 3
},... | DailyDialog_test_000078 | schedule | life_mt_sct_DailyDialog_test_000078_target14 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"education_career"... | [
"low_information_answer"
] | 0.749 | DailyDialog | test_000078 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
alexander bed and breakfast fits those criteria, would you like me to book a stay? | This sample contains safety-sensitive context. The reasoning should stay conservative, avoid amplifying sensitive details, and only support a safe, bounded assistant response. | [
{
"speaker": "user",
"text": "I am on a budget and need a cheap place to eat.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "There are 22 cheap places to eat in the area. Do you have a preference of food type?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like Ind... | MultiWOZ_PMUL4833.json | cooking | life_mt_sct_MultiWOZ_PMUL4833.json_target12 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"financial_context",
"sensitive_content"
] | 0.749 | MultiWOZ | PMUL4833.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | prefix_to_next_assistant_text |
For the return flight, I have a 6 AM and a 9:22 AM. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=morning; destination=chicago, los angeles; origin=los angeles; transport_type=flight. The answer should address the customer support step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. All right, today I need your help finding up a flight, a round trip flight from Los Angeles to Chicago.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "For what days?",
"turn_id": 2
},
{
"speaker": "user",
"text": "The days are going ... | Taskmaster_dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a | travel | life_mt_sct_Taskmaster_dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a_target10 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 1 | Taskmaster | dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
The address is 56 Saint Barnabas Road. Is there anything else that I can help you with? | This sample contains safety-sensitive context. The reasoning should stay conservative, avoid amplifying sensitive details, and only support a safe, bounded assistant response. | [
{
"speaker": "user",
"text": "I am on a budget and need a cheap place to eat.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "There are 22 cheap places to eat in the area. Do you have a preference of food type?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like Ind... | MultiWOZ_PMUL4833.json | cooking | life_mt_sct_MultiWOZ_PMUL4833.json_target14 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"financial_context",
"sensitive_content"
] | 0.749 | MultiWOZ | PMUL4833.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | prefix_to_next_assistant_text |
The Itinerary has been sent to your email. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=morning, 9:22 am; destination=chicago, los angeles; origin=los angeles; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. All right, today I need your help finding up a flight, a round trip flight from Los Angeles to Chicago.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "For what days?",
"turn_id": 2
},
{
"speaker": "user",
"text": "The days are going ... | Taskmaster_dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a | travel | life_mt_sct_Taskmaster_dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a_target12 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 0.899 | Taskmaster | dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
Yes, sir. I apologize for that. Here ' s the file you were looking for, Mr. Emory. | The dialogue is workplace conversation in education career, with recommendation intent. The most recent user context is: Christine, I know you ' re new here and there ' s a lot to learn, but you are going to have to learn to keep your work in better order. We can ' t afford to lose an important document. The answer is ... | [
{
"speaker": "user",
"text": "the James ' s file, Christine?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I had it right here a minute ago, Mr. Emory. Umm. Just a minute...",
"turn_id": 2
},
{
"speaker": "user",
"text": "Christine, I know you ' re new here and there '... | DailyDialog_test_000080 | shopping | life_mt_sct_DailyDialog_test_000080_target4 | true | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"education_career"
],
"domain_category... | [
"premature_respond",
"weak_final_state"
] | 0.92 | DailyDialog | test_000080 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
Thank you for using our system today! | This sample contains safety-sensitive context. The reasoning should stay conservative, avoid amplifying sensitive details, and only support a safe, bounded assistant response. | [
{
"speaker": "user",
"text": "I am on a budget and need a cheap place to eat.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "There are 22 cheap places to eat in the area. Do you have a preference of food type?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd like Ind... | MultiWOZ_PMUL4833.json | cooking | life_mt_sct_MultiWOZ_PMUL4833.json_target16 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"financial_context",
"sensitive_content"
] | 0.749 | MultiWOZ | PMUL4833.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the visible dialogue prefix is used. The turn is handled conservatively because the context is safety-sensitive, so the state keeps prior safe context and waits for a safe next response.",
"reasoning_confidence": "medium",
"reasoning_type": "safet... | prefix_to_next_assistant_text |
Bye. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=morning, 9:22 am; destination=chicago, los angeles; origin=los angeles; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. All right, today I need your help finding up a flight, a round trip flight from Los Angeles to Chicago.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "For what days?",
"turn_id": 2
},
{
"speaker": "user",
"text": "The days are going ... | Taskmaster_dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a | travel | life_mt_sct_Taskmaster_dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a_target14 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [
"fragment_answer",
"low_information_answer",
"too_short_answer",
"weak_target_answer"
] | 0.25 | Taskmaster | dlg-0255be42-6aa3-4b83-995c-73a21bf5de8a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
What are those dates again? | The visible history is a flight booking task in travel transportation. Known constraints are destination=seattle; origin=seattle, april; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I'd like to see about booking a flight from Seattle, Washington to Myrtle Beach, South Carolina.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "One moment.",
"turn_id": 2
},
{
"speaker": "user",
"text": "The dates would be from April... | Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | travel | life_mt_sct_Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d_target4 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 0.899 | Taskmaster | dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
Can you give me some specifications? | The visible history is a flight booking task in travel transportation. Known constraints are destination=seattle; origin=seattle, april; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I'd like to see about booking a flight from Seattle, Washington to Myrtle Beach, South Carolina.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "One moment.",
"turn_id": 2
},
{
"speaker": "user",
"text": "The dates would be from April... | Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | travel | life_mt_sct_Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d_target6 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 0.899 | Taskmaster | dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
Do you want to leave in the morning or afternoon flight? | The visible history is a flight booking task in travel transportation. Known constraints are budget=$900; destination=seattle; origin=seattle, april; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I'd like to see about booking a flight from Seattle, Washington to Myrtle Beach, South Carolina.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "One moment.",
"turn_id": 2
},
{
"speaker": "user",
"text": "The dates would be from April... | Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | travel | life_mt_sct_Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d_target8 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 1 | Taskmaster | dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
I do not have any flights for under $900. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$900; date_or_duration=morning; destination=seattle; origin=seattle, april. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I'd like to see about booking a flight from Seattle, Washington to Myrtle Beach, South Carolina.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "One moment.",
"turn_id": 2
},
{
"speaker": "user",
"text": "The dates would be from April... | Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | travel | life_mt_sct_Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d_target10 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 0.899 | Taskmaster | dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
Perfect. I found a flight for you. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$900, $1,500; date_or_duration=morning; destination=seattle; origin=seattle, april. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I'd like to see about booking a flight from Seattle, Washington to Myrtle Beach, South Carolina.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "One moment.",
"turn_id": 2
},
{
"speaker": "user",
"text": "The dates would be from April... | Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | travel | life_mt_sct_Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d_target12 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 0.899 | Taskmaster | dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
Would you like this to-go? | The dialogue is uncertain context in general daily life, with information request intent. The most recent user context is: Very nice. Thank you. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Excuse me. Check please.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "OK, how was everything?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Very nice. Thank you.",
"turn_id": 3
}
] | DailyDialog_test_000083 | other_life | life_mt_sct_DailyDialog_test_000083_target4 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categor... | [
"low_taxonomy_confidence",
"weak_final_state"
] | 0.749 | DailyDialog | test_000083 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
Departs at 12:00 PM. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$900, $1,500; date_or_duration=morning; destination=seattle; origin=seattle, april. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I'd like to see about booking a flight from Seattle, Washington to Myrtle Beach, South Carolina.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "One moment.",
"turn_id": 2
},
{
"speaker": "user",
"text": "The dates would be from April... | Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | travel | life_mt_sct_Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d_target14 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [
"low_information_answer"
] | 0.749 | Taskmaster | dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
Sure, no problem. Here you are. That'll be 25 dollars. | The dialogue is uncertain context in general daily life, with problem solving intent. The most recent user context is: Yes, can you put it in a plastic bag? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Excuse me. Check please.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "OK, how was everything?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Very nice. Thank you.",
"turn_id": 3
},
{
"speaker": "assistant",
"text": "Would... | DailyDialog_test_000083 | other_life | life_mt_sct_DailyDialog_test_000083_target6 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categor... | [
"answer_not_grounded",
"low_taxonomy_confidence",
"weak_final_state"
] | 0.499 | DailyDialog | test_000083 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
Layover in Atlanta for 1 hour and 46 minutes. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$900, $1,500; date_or_duration=morning; destination=seattle; origin=seattle, april. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I'd like to see about booking a flight from Seattle, Washington to Myrtle Beach, South Carolina.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "One moment.",
"turn_id": 2
},
{
"speaker": "user",
"text": "The dates would be from April... | Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | travel | life_mt_sct_Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d_target16 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [] | 0.899 | Taskmaster | dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
Yes, we accept Visa and MasterCard. | The dialogue is banking support in finance business, with information request intent. The most recent user context is: Do you take credit cards? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Excuse me. Check please.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "OK, how was everything?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Very nice. Thank you.",
"turn_id": 3
},
{
"speaker": "assistant",
"text": "Would... | DailyDialog_test_000083 | other_life | life_mt_sct_DailyDialog_test_000083_target8 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categor... | [
"low_information_answer",
"weak_final_state"
] | 0.749 | DailyDialog | test_000083 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
No problem. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$900, $1,500; date_or_duration=morning; destination=seattle; origin=seattle, april. The answer should address the customer support step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I'd like to see about booking a flight from Seattle, Washington to Myrtle Beach, South Carolina.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "One moment.",
"turn_id": 2
},
{
"speaker": "user",
"text": "The dates would be from April... | Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | travel | life_mt_sct_Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d_target18 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [
"answer_not_grounded",
"fragment_answer",
"generic_answer",
"too_short_answer",
"weak_target_answer"
] | 0 | Taskmaster | dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
Thanks. I'll be right back. | The dialogue is banking support in finance business, with confirmation clarification intent. The most recent user context is: OK, here you are. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Excuse me. Check please.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "OK, how was everything?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Very nice. Thank you.",
"turn_id": 3
},
{
"speaker": "assistant",
"text": "Would... | DailyDialog_test_000083 | other_life | life_mt_sct_DailyDialog_test_000083_target10 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categor... | [
"low_information_answer",
"weak_final_state"
] | 0.749 | DailyDialog | test_000083 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
Cotto is located on 183 East Road City Centre and has the postcode cb11bg. Is there anything else I could help you with today? | The visible history is a restaurant search task in travel transportation. It should track cuisine, area, and price. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "I'm looking for information in Cambridge. Can you help?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'd be happy to help you with all things Cambridge. What can I help you find today?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd l... | MultiWOZ_MUL2418.json | daily_advice | life_mt_sct_MultiWOZ_MUL2418.json_target4 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"weak_final_state"
] | 0.97 | MultiWOZ | MUL2418.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
"reas... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
"reas... | prefix_to_next_assistant_text |
You're all set. | The visible history is a flight booking task in travel transportation. Known constraints are budget=$900, $1,500; date_or_duration=morning; destination=seattle; origin=seattle, april. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I'd like to see about booking a flight from Seattle, Washington to Myrtle Beach, South Carolina.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "One moment.",
"turn_id": 2
},
{
"speaker": "user",
"text": "The dates would be from April... | Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | travel | life_mt_sct_Taskmaster_dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d_target20 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain... | [
"fragment_answer",
"low_information_answer",
"too_short_answer",
"weak_target_answer"
] | 0.25 | Taskmaster | dlg-029578d0-2b26-4bb3-8b7c-cbbd5008cd7d | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: destination, origin, transport_type; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoni... | prefix_to_next_assistant_text |
Here's your receipt. | The dialogue is banking support in finance business, with confirmation clarification intent. The most recent user context is: OK. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Excuse me. Check please.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "OK, how was everything?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Very nice. Thank you.",
"turn_id": 3
},
{
"speaker": "assistant",
"text": "Would... | DailyDialog_test_000083 | other_life | life_mt_sct_DailyDialog_test_000083_target12 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categor... | [
"fragment_answer",
"low_information_answer",
"too_short_answer",
"weak_final_state",
"weak_target_answer"
] | 0.22 | DailyDialog | test_000083 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
Riverboat Georgina is located at cambridge passenger cruisers, jubilee house, phone number [phone removed]. Can I help you with anything else? | The visible history is a restaurant search task in travel transportation. It should track cuisine, area, and price. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "I'm looking for information in Cambridge. Can you help?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'd be happy to help you with all things Cambridge. What can I help you find today?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd l... | MultiWOZ_MUL2418.json | daily_advice | life_mt_sct_MultiWOZ_MUL2418.json_target6 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"weak_final_state"
] | 0.97 | MultiWOZ | MUL2418.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
"reas... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
"reas... | prefix_to_next_assistant_text |
Okay, round trip or one way? | The visible history is a flight booking task in travel transportation. Known constraints are destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi assistant. Yes, I'm trying to schedule an airplane flight to France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, where in France?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Paris.",
"turn_id": 3
}
] | Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a | travel | life_mt_sct_Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a_target4 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"duplicate_turn",
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "... | [] | 0.899 | Taskmaster | dlg-02a3add6-906b-4598-89f9-614ff412bc5a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
You're welcome. Please come again. | The dialogue is banking support in finance business, with small talk intent. The most recent user context is: Thank you. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Excuse me. Check please.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "OK, how was everything?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Very nice. Thank you.",
"turn_id": 3
},
{
"speaker": "assistant",
"text": "Would... | DailyDialog_test_000083 | other_life | life_mt_sct_DailyDialog_test_000083_target14 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categor... | [
"low_information_answer",
"weak_final_state"
] | 0.749 | DailyDialog | test_000083 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
The attraction type for the Riverboat Georgina is "boat." Can I be of any further assistance today? | The visible history is a restaurant search task in travel transportation. It should track cuisine, area, and price. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "I'm looking for information in Cambridge. Can you help?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'd be happy to help you with all things Cambridge. What can I help you find today?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd l... | MultiWOZ_MUL2418.json | daily_advice | life_mt_sct_MultiWOZ_MUL2418.json_target8 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"weak_final_state"
] | 0.97 | MultiWOZ | MUL2418.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
"reas... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
"reas... | prefix_to_next_assistant_text |
Okay, what class would you like to fly? | The visible history is a flight booking task in travel transportation. Known constraints are destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi assistant. Yes, I'm trying to schedule an airplane flight to France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, where in France?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Paris.",
"turn_id": 3
},
{
"speaker": ... | Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a | travel | life_mt_sct_Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a_target6 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"duplicate_turn",
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "... | [] | 0.899 | Taskmaster | dlg-02a3add6-906b-4598-89f9-614ff412bc5a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
The task is tough. | The dialogue is workplace conversation in education career, with information request intent. The most recent user context is: Why? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "You look upset, anything wrong?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'm going to quit the job.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Why?",
"turn_id": 3
}
] | DailyDialog_test_000084 | emotional_support | life_mt_sct_DailyDialog_test_000084_target4 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"education... | [
"low_information_answer",
"weak_final_state"
] | 0.749 | DailyDialog | test_000084 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
No, that is the attraction type listed in our database. It is listed as a boat attraction. | The visible history is a restaurant search task in travel transportation. It should track cuisine, area, and price. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "I'm looking for information in Cambridge. Can you help?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'd be happy to help you with all things Cambridge. What can I help you find today?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd l... | MultiWOZ_MUL2418.json | daily_advice | life_mt_sct_MultiWOZ_MUL2418.json_target10 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"weak_final_state"
] | 0.97 | MultiWOZ | MUL2418.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
"reas... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
"reas... | prefix_to_next_assistant_text |
Okay, when would you like to leave and return? | The visible history is a flight booking task in travel transportation. Known constraints are destination=paris; transport_type=flight. The answer should address the customer support step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi assistant. Yes, I'm trying to schedule an airplane flight to France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, where in France?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Paris.",
"turn_id": 3
},
{
"speaker": ... | Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a | travel | life_mt_sct_Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a_target8 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"duplicate_turn",
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "... | [] | 0.899 | Taskmaster | dlg-02a3add6-906b-4598-89f9-614ff412bc5a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
Thanks for your concern. | The dialogue is workplace conversation in education career, with small talk intent. The most recent user context is: You'd look before you leap. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "You look upset, anything wrong?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'm going to quit the job.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Why?",
"turn_id": 3
},
{
"speaker": "assistant",
"text": "The task is ... | DailyDialog_test_000084 | emotional_support | life_mt_sct_DailyDialog_test_000084_target6 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"education... | [
"low_information_answer",
"weak_final_state"
] | 0.749 | DailyDialog | test_000084 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
Your welcome! Is there anything else I can help you with today? | The visible history is a restaurant search task in travel transportation. It should track cuisine, area, and price. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "I'm looking for information in Cambridge. Can you help?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'd be happy to help you with all things Cambridge. What can I help you find today?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd l... | MultiWOZ_MUL2418.json | daily_advice | life_mt_sct_MultiWOZ_MUL2418.json_target12 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"weak_final_state"
] | 0.97 | MultiWOZ | MUL2418.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
"reas... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
"reas... | prefix_to_next_assistant_text |
Sounds good any other preferences? | The visible history is a flight booking task in travel transportation. Known constraints are destination=paris; transport_type=flight. The answer should address the customer support step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi assistant. Yes, I'm trying to schedule an airplane flight to France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, where in France?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Paris.",
"turn_id": 3
},
{
"speaker": ... | Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a | travel | life_mt_sct_Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a_target10 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"duplicate_turn",
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "... | [] | 0.899 | Taskmaster | dlg-02a3add6-906b-4598-89f9-614ff412bc5a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
Well, maybe I can put them in the airport storage there. | The dialogue is travel planning in travel transportation, with emotional support intent. Key constraints are date_or_duration=24 hours; destination=new york, london. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "How long will you stay in New York?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Just tor three days. I won't need these luggages.CouId I put them here?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I am sorry. If you have here more tha... | DailyDialog_test_000085 | travel | life_mt_sct_DailyDialog_test_000085_target4 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_transportation"
],
"domain_cat... | [
"weak_slot_evidence"
] | 0.749 | DailyDialog | test_000085 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: destination; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: destination; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium... | prefix_to_next_assistant_text |
Your welcome. Thank you for contacting us. | The visible history is a restaurant search task in travel transportation. It should track cuisine, area, and price. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "I'm looking for information in Cambridge. Can you help?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'd be happy to help you with all things Cambridge. What can I help you find today?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'd l... | MultiWOZ_MUL2418.json | daily_advice | life_mt_sct_MultiWOZ_MUL2418.json_target14 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"weak_final_state"
] | 0.899 | MultiWOZ | MUL2418.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
"reas... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: none; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
"reas... | prefix_to_next_assistant_text |
Sure, anything else? Okay great. | The visible history is a flight booking task in travel transportation. Known constraints are destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi assistant. Yes, I'm trying to schedule an airplane flight to France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, where in France?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Paris.",
"turn_id": 3
},
{
"speaker": ... | Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a | travel | life_mt_sct_Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a_target12 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"duplicate_turn",
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "... | [] | 0.899 | Taskmaster | dlg-02a3add6-906b-4598-89f9-614ff412bc5a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
Walk that way for about four blocks. The hotel's about two blocks north of there. | The dialogue is general conversation in travel transportation, with recommendation intent. Key constraints are hotel_preference=hotel. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Excuse me. Do you know where the Admiral Hotel is?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "That's over on Callaway Street, isn't it?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Yes, but I can't find Callaway Street.",
"turn_i... | DailyDialog_test_000087 | travel | life_mt_sct_DailyDialog_test_000087_target4 | true | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_transportation"
],
"domain_cat... | [
"premature_respond"
] | 0.95 | DailyDialog | test_000087 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: hotel_preference; changed slots: none; removed slots: none.",
"reasoning_confidence": "m... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: hotel_preference; changed slots: none; removed slots: none.",
"reasoning_confidence": "m... | prefix_to_next_assistant_text |
I have several options for you. Where is your destination? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=wednesday; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Howdy, I need a train heading into cambridge.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I would be happy to help you find a train. Where are you departing from?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I am departing from norwic... | MultiWOZ_PMUL1181.json | travel | life_mt_sct_MultiWOZ_PMUL1181.json_target4 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [] | 1 | MultiWOZ | PMUL1181.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | prefix_to_next_assistant_text |
There is one flight for two thousand nine hundred one dollars. | The visible history is a flight booking task in travel transportation. Known constraints are destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi assistant. Yes, I'm trying to schedule an airplane flight to France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, where in France?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Paris.",
"turn_id": 3
},
{
"speaker": ... | Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a | travel | life_mt_sct_Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a_target14 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"duplicate_turn",
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "... | [] | 1 | Taskmaster | dlg-02a3add6-906b-4598-89f9-614ff412bc5a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
Not at all. | The dialogue is general conversation in travel transportation, with small talk intent. Key constraints are hotel_preference=hotel. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Excuse me. Do you know where the Admiral Hotel is?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "That's over on Callaway Street, isn't it?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Yes, but I can't find Callaway Street.",
"turn_i... | DailyDialog_test_000087 | travel | life_mt_sct_DailyDialog_test_000087_target6 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_transportation"
],
"domain_cat... | [
"fragment_answer",
"low_information_answer",
"too_short_answer",
"weak_target_answer"
] | 0.25 | DailyDialog | test_000087 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: hotel_preference; changed slots: none; removed slots: none.",
"reasoning_confidence": "m... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: hotel_preference; changed slots: none; removed slots: none.",
"reasoning_confidence": "m... | prefix_to_next_assistant_text |
The earliest after 18:45 is the TR8658, leaving Norwich at 19:16. Can I reserve you one or more seats on this train? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=wednesday; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Howdy, I need a train heading into cambridge.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I would be happy to help you find a train. Where are you departing from?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I am departing from norwic... | MultiWOZ_PMUL1181.json | travel | life_mt_sct_MultiWOZ_PMUL1181.json_target6 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [] | 1 | MultiWOZ | PMUL1181.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | prefix_to_next_assistant_text |
Okay, would you like me to book that flight. | The visible history is a flight booking task in travel transportation. Known constraints are destination=paris; transport_type=flight. The answer should address the confirmation clarification step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi assistant. Yes, I'm trying to schedule an airplane flight to France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, where in France?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Paris.",
"turn_id": 3
},
{
"speaker": ... | Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a | travel | life_mt_sct_Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a_target16 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"duplicate_turn",
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "... | [] | 0.899 | Taskmaster | dlg-02a3add6-906b-4598-89f9-614ff412bc5a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
Booking was successful, the total fee is 17.6 GBP payable at the station. Your reference number is AXH1NM1I. Do you need assistance with anything else? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=wednesday; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Howdy, I need a train heading into cambridge.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I would be happy to help you find a train. Where are you departing from?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I am departing from norwic... | MultiWOZ_PMUL1181.json | travel | life_mt_sct_MultiWOZ_PMUL1181.json_target8 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [] | 1 | MultiWOZ | PMUL1181.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | prefix_to_next_assistant_text |
Would you like to know about your return flight. | The visible history is a flight booking task in travel transportation. Known constraints are destination=paris; transport_type=flight. The answer should address the confirmation clarification step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi assistant. Yes, I'm trying to schedule an airplane flight to France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, where in France?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Paris.",
"turn_id": 3
},
{
"speaker": ... | Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a | travel | life_mt_sct_Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a_target18 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"duplicate_turn",
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "... | [] | 0.899 | Taskmaster | dlg-02a3add6-906b-4598-89f9-614ff412bc5a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
It looks like there is The Cherry Hinton Village Centre. Can I get you more information about it? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=wednesday; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Howdy, I need a train heading into cambridge.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I would be happy to help you find a train. Where are you departing from?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I am departing from norwic... | MultiWOZ_PMUL1181.json | travel | life_mt_sct_MultiWOZ_PMUL1181.json_target10 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [] | 1 | MultiWOZ | PMUL1181.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | prefix_to_next_assistant_text |
There is one non stop for $3,387. | The visible history is a flight booking task in travel transportation. Known constraints are destination=paris; transport_type=flight. The answer should address the confirmation clarification step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi assistant. Yes, I'm trying to schedule an airplane flight to France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, where in France?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Paris.",
"turn_id": 3
},
{
"speaker": ... | Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a | travel | life_mt_sct_Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a_target20 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"duplicate_turn",
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "... | [] | 0.899 | Taskmaster | dlg-02a3add6-906b-4598-89f9-614ff412bc5a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
Yes, please tell her that band practice has been moved to Tuesday night at eight thirty. | The dialogue is uncertain context in general daily life, with information request intent. The most recent user context is: No, I ' m afraid not, Mary. May I take a message for her? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Hello?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hi, Mr. Smith. This is Mary. Is Jenny there?",
"turn_id": 2
},
{
"speaker": "user",
"text": "No, I ' m afraid not, Mary. May I take a message for her?",
"turn_id": 3
}
] | DailyDialog_test_000090 | other_life | life_mt_sct_DailyDialog_test_000090_target4 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"general_d... | [
"low_taxonomy_confidence",
"weak_final_state"
] | 0.749 | DailyDialog | test_000090 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
their phone number is [phone removed]. anything else? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=wednesday; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Howdy, I need a train heading into cambridge.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I would be happy to help you find a train. Where are you departing from?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I am departing from norwic... | MultiWOZ_PMUL1181.json | travel | life_mt_sct_MultiWOZ_PMUL1181.json_target12 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [] | 0.899 | MultiWOZ | PMUL1181.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | prefix_to_next_assistant_text |
Is there anything else I can do for you? | The visible history is a flight booking task in travel transportation. Known constraints are destination=paris; transport_type=flight. The answer should address the confirmation clarification step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi assistant. Yes, I'm trying to schedule an airplane flight to France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, where in France?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Paris.",
"turn_id": 3
},
{
"speaker": ... | Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a | travel | life_mt_sct_Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a_target22 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"duplicate_turn",
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "... | [] | 0.899 | Taskmaster | dlg-02a3add6-906b-4598-89f9-614ff412bc5a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
No, but if she has any questions, she can call me at 555-2345. | The dialogue is uncertain context in general daily life, with problem solving intent. The most recent user context is: O. K. No problem. Anything else? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Hello?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hi, Mr. Smith. This is Mary. Is Jenny there?",
"turn_id": 2
},
{
"speaker": "user",
"text": "No, I ' m afraid not, Mary. May I take a message for her?",
"turn_id": 3
},
{
"sp... | DailyDialog_test_000090 | other_life | life_mt_sct_DailyDialog_test_000090_target6 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"general_d... | [
"low_taxonomy_confidence",
"weak_final_state"
] | 0.749 | DailyDialog | test_000090 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
Sure, the postcode is cb19ej. Can I help you find any other information about Cambridge? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=wednesday; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Howdy, I need a train heading into cambridge.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I would be happy to help you find a train. Where are you departing from?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I am departing from norwic... | MultiWOZ_PMUL1181.json | travel | life_mt_sct_MultiWOZ_PMUL1181.json_target14 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [] | 1 | MultiWOZ | PMUL1181.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | prefix_to_next_assistant_text |
Okay, I booked your flight and emailed you the Details. | The visible history is a flight booking task in travel transportation. Known constraints are destination=paris; transport_type=flight. The answer should address the confirmation clarification step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi assistant. Yes, I'm trying to schedule an airplane flight to France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, where in France?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Paris.",
"turn_id": 3
},
{
"speaker": ... | Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a | travel | life_mt_sct_Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a_target24 | true | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"duplicate_turn",
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "... | [] | 1 | Taskmaster | dlg-02a3add6-906b-4598-89f9-614ff412bc5a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
Thank you. Bye. | The dialogue is uncertain context in general daily life, with booking or reservation intent. The most recent user context is: All right, I ' ll leave her the message, Mary. Thanks for calling. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Hello?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hi, Mr. Smith. This is Mary. Is Jenny there?",
"turn_id": 2
},
{
"speaker": "user",
"text": "No, I ' m afraid not, Mary. May I take a message for her?",
"turn_id": 3
},
{
"sp... | DailyDialog_test_000090 | other_life | life_mt_sct_DailyDialog_test_000090_target8 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"general_d... | [
"fragment_answer",
"low_information_answer",
"low_taxonomy_confidence",
"too_short_answer",
"weak_final_state",
"weak_target_answer"
] | 0.17 | DailyDialog | test_000090 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
enjoy your time in Cambridge! | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=wednesday; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Howdy, I need a train heading into cambridge.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I would be happy to help you find a train. Where are you departing from?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I am departing from norwic... | MultiWOZ_PMUL1181.json | travel | life_mt_sct_MultiWOZ_PMUL1181.json_target16 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [
"low_information_answer"
] | 0.749 | MultiWOZ | PMUL1181.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence": ... | prefix_to_next_assistant_text |
Have a great flight. | The visible history is a flight booking task in travel transportation. Known constraints are destination=paris; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi assistant. Yes, I'm trying to schedule an airplane flight to France.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay, where in France?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Paris.",
"turn_id": 3
},
{
"speaker": ... | Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a | travel | life_mt_sct_Taskmaster_dlg-02a3add6-906b-4598-89f9-614ff412bc5a_target26 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"duplicate_turn",
"too_many_turns",
"too_short_average_turn"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "... | [
"low_information_answer"
] | 0.749 | Taskmaster | dlg-02a3add6-906b-4598-89f9-614ff412bc5a | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
I'm sorry. I can't quite follow you. Would you mind speaking slowly? | The dialogue is uncertain context in general daily life, with information request intent. The most recent user context is: Can you tell me how to get to the Jade Buddha Temple? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Do you speak English?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes, a little.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Can you tell me how to get to the Jade Buddha Temple?",
"turn_id": 3
}
] | DailyDialog_test_000091 | other_life | life_mt_sct_DailyDialog_test_000091_target4 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"general_daily_life"
],
"domain_catego... | [
"low_taxonomy_confidence",
"weak_final_state"
] | 0.749 | DailyDialog | test_000091 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
Royal Standard has good reviews. Their phone # is [phone removed] and they are located at 290 Mill Road City Centre. | The visible history is a restaurant search task in travel transportation. Known constraints are date_or_duration=tonight. The answer should address the information request step while tracking cuisine, area, and price. | [
{
"speaker": "user",
"text": "Hi there. I'm trying to find a place to eat tonight. I'd like it to be more high end and expensive, and serve gastropub food. Can you help me?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have three Gastropub restaurants that meet your criteria. Two ar... | MultiWOZ_MUL1604.json | travel | life_mt_sct_MultiWOZ_MUL1604.json_target4 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"premature_respond",
"weak_slot_evidence"
] | 0.749 | MultiWOZ | MUL1604.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: date_or_duration; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: date_or_duration; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
Do you have anyone travelling along with you? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=4 days; origin=la; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "I need a flight from LA to Miami.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I can help you with that. Can you please confirm the dates of your travel?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I want to leave today latest time po... | Taskmaster_dlg-02d3cc76-c1bb-4b86-9c08-48b01dbeaaf2 | travel | life_mt_sct_Taskmaster_dlg-02d3cc76-c1bb-4b86-9c08-48b01dbeaaf2_target4 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [
"weak_slot_evidence"
] | 0.749 | Taskmaster | dlg-02d3cc76-c1bb-4b86-9c08-48b01dbeaaf2 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: origin, transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_con... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: origin, transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_con... | prefix_to_next_assistant_text |
Yes, it's so helpful. | The dialogue is uncertain context in general daily life, with information request intent. The most recent user context is: So you have all the news on broadcast? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "How do you get road news?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I've a driver mate in my car!",
"turn_id": 2
},
{
"speaker": "user",
"text": "So you have all the news on broadcast?",
"turn_id": 3
}
] | DailyDialog_test_000092 | other_life | life_mt_sct_DailyDialog_test_000092_target4 | false | {
"category": "daily_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"general_daily_life"
],
"domain_catego... | [
"low_information_answer",
"low_taxonomy_confidence",
"weak_final_state"
] | 0.749 | DailyDialog | test_000092 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible dailydialog prefix is used. The user turn updates the daily dialogue context and response policy without relying on future turns; added slots: none; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
I can help you with that. First, can you tell me where you will be departing and the timeframe you had in mind? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=tonight, thursday; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Hi there. I'm trying to find a place to eat tonight. I'd like it to be more high end and expensive, and serve gastropub food. Can you help me?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have three Gastropub restaurants that meet your criteria. Two ar... | MultiWOZ_MUL1604.json | travel | life_mt_sct_MultiWOZ_MUL1604.json_target6 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"food_dini... | [
"weak_slot_evidence"
] | 0.749 | MultiWOZ | MUL1604.json | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: date_or_duration; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible multiwoz prefix is used. The user turn is treated as new task evidence; added slots: date_or_duration; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_confidence"... | prefix_to_next_assistant_text |
Would you like to travel by economy, business class, premium economy or first class? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=4 days; origin=la; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "I need a flight from LA to Miami.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I can help you with that. Can you please confirm the dates of your travel?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I want to leave today latest time po... | Taskmaster_dlg-02d3cc76-c1bb-4b86-9c08-48b01dbeaaf2 | travel | life_mt_sct_Taskmaster_dlg-02d3cc76-c1bb-4b86-9c08-48b01dbeaaf2_target6 | false | {
"category": "task_oriented_dialogue",
"category_taxonomy_method": "deterministic_source_aware_rules_v1",
"chunk_level": "turn",
"cleaning_flags": [
"too_many_turns"
],
"construction_type": "prefix_to_next_assistant_turn",
"deep_reasoning_method": "rule_based",
"domain_categories": [
"travel_tr... | [
"weak_slot_evidence"
] | 0.749 | Taskmaster | dlg-02d3cc76-c1bb-4b86-9c08-48b01dbeaaf2 | train | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: origin, transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_con... | [
{
"chunk_id": "C1",
"reasoning": "After turn 1, only the current visible taskmaster prefix is used. The user turn is treated as new task evidence; added slots: origin, transport_type; changed slots: none; removed slots: none; new missing slots: destination; resolved missing slots: none.",
"reasoning_con... | prefix_to_next_assistant_text |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.