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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
It is really a hot potato. | 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": "The taxi drivers are on strike again.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "What for?",
"turn_id": 2
},
{
"speaker": "user",
"text": "They want the government to reduce the price of the gasoline.",
"turn_id": 3
}
] | DailyDialog_test_000002 | travel | life_mt_sct_DailyDialog_test_000002_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",
"mild_violence_or_conflict_context",
"sensitive_content"
] | 0.749 | DailyDialog | test_000002 | 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 |
Ok how about Charlie Chan, located at Regent Street City Centre. Postcode is cb21db with a cheap price. Can I help you further 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 a local place to dine in the centre that serves chinese food.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have restaurants matching your criteria in all price ranges. Do you have a preference on price?",
"turn_id": 2
},
{
"... | MultiWOZ_PMUL0698.json | travel | life_mt_sct_MultiWOZ_PMUL0698.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 | PMUL0698.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
So what days are you looking to fly? Hey, what else can you say? | The visible history is a flight booking task in travel transportation. Known constraints are destination=san francisco; origin=san francisco; 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 find a round trip commercial airline flight from San Francisco to Denver.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? San Francisco to Denver, got it.",
"turn_id": 2
},
{
"speaker": "user",
"... | Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | travel | life_mt_sct_Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f_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... | [
"fragment_answer"
] | 0.499 | Taskmaster | dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | 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 does that mean exactly? | The dialogue is workplace conversation in education career, with information request intent. The most recent user context is: Mainly because we've invested in a heat recovery system. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "We've managed to reduce our energy consumption in our factory by about 15 per cent in the last two years.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "That's excellent. How have you managed that?",
"turn_id": 2
},
{
"speaker": "user",
"te... | DailyDialog_test_000003 | other_life | life_mt_sct_DailyDialog_test_000003_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... | [
"weak_final_state"
] | 0.899 | DailyDialog | test_000003 | 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. Unsupported slot evidence is suppressed for ... | [
{
"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. Unsupported slot evidence is suppressed for ... | prefix_to_next_assistant_text |
Can I have more information for the train you're needing? Where are you departing from and arriving to? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=sunday; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "I'm looking for a local place to dine in the centre that serves chinese food.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have restaurants matching your criteria in all price ranges. Do you have a preference on price?",
"turn_id": 2
},
{
"... | MultiWOZ_PMUL0698.json | travel | life_mt_sct_MultiWOZ_PMUL0698.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... | [] | 1 | MultiWOZ | PMUL0698.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
That sounds good, where you looking to go? That's right okay we have prices starting at $337. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=tonight, evening, 4 days; destination=san francisco; origin=san francisco; 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 find a round trip commercial airline flight from San Francisco to Denver.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? San Francisco to Denver, got it.",
"turn_id": 2
},
{
"speaker": "user",
"... | Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | travel | life_mt_sct_Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f_target6 | 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... | [
"weak_slot_evidence"
] | 0.749 | Taskmaster | dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | 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 other sources of energy do you use? | The dialogue is workplace conversation in education career, with information request intent. The most recent user context is: Well, we use the exhaust gases from our printing presses to provide energy to heat our dryers. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "We've managed to reduce our energy consumption in our factory by about 15 per cent in the last two years.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "That's excellent. How have you managed that?",
"turn_id": 2
},
{
"speaker": "user",
"te... | DailyDialog_test_000003 | other_life | life_mt_sct_DailyDialog_test_000003_target6 | 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... | [
"weak_final_state"
] | 0.899 | DailyDialog | test_000003 | 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. Unsupported slot evidence is suppressed for ... | [
{
"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. Unsupported slot evidence is suppressed for ... | prefix_to_next_assistant_text |
I have train TR1840 leaving at 16:36 is that okay? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=sunday; destination=norwich; origin=cambridge; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "I'm looking for a local place to dine in the centre that serves chinese food.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have restaurants matching your criteria in all price ranges. Do you have a preference on price?",
"turn_id": 2
},
{
"... | MultiWOZ_PMUL0698.json | travel | life_mt_sct_MultiWOZ_PMUL0698.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... | [] | 1 | MultiWOZ | PMUL0698.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Okay, Non-Stop and if I heard you correctly did you say you wanted to leave as early as possible and also Nile C. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=tonight, evening, 4 days; destination=san francisco; origin=san francisco; 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 find a round trip commercial airline flight from San Francisco to Denver.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? San Francisco to Denver, got it.",
"turn_id": 2
},
{
"speaker": "user",
"... | Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | travel | life_mt_sct_Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f_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... | [
"weak_slot_evidence"
] | 0.749 | Taskmaster | dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | 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, Chinese people love drinking tea so much. Some even claim they can't live without tea. | The dialogue is uncertain context in general daily life, with planning coordination intent. The most recent user context is: Right. And China is the homeland of tea. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Believe it or not, tea is the most popular beverage in the world after water.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Well, people from Asia to Europe all enjoy tea.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Right. And China is... | DailyDialog_test_000004 | health_routine | life_mt_sct_DailyDialog_test_000004_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",
"weak_final_state"
] | 0.749 | DailyDialog | test_000004 | 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 |
You're all set. Reference number is NJB87PAP. Is there anything else I can help you with today? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=sunday; destination=norwich; origin=cambridge; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "I'm looking for a local place to dine in the centre that serves chinese food.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have restaurants matching your criteria in all price ranges. Do you have a preference on price?",
"turn_id": 2
},
{
"... | MultiWOZ_PMUL0698.json | travel | life_mt_sct_MultiWOZ_PMUL0698.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... | [] | 1 | MultiWOZ | PMUL0698.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Okay, you got it so it looks like United Airlines leaves at 9:20 p.m. that is nonstop the flight duration is 2 hours and 28 minutes and is priced at $337. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=tonight, evening, 4 days; destination=san francisco; origin=san francisco; transport_type=flight. The answer should address the confirmation clarification step while tracking origin, destination, and travel dat... | [
{
"speaker": "user",
"text": "Hello. I'd like to find a round trip commercial airline flight from San Francisco to Denver.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? San Francisco to Denver, got it.",
"turn_id": 2
},
{
"speaker": "user",
"... | Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | travel | life_mt_sct_Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f_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... | [
"weak_slot_evidence"
] | 0.749 | Taskmaster | dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | 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, I believe there are green teas, black teas and scented teas. Any Others? | The dialogue is uncertain context in general daily life, with information request intent. The most recent user context is: Do you know there are several catagories of Chinese tea? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Believe it or not, tea is the most popular beverage in the world after water.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Well, people from Asia to Europe all enjoy tea.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Right. And China is... | DailyDialog_test_000004 | health_routine | life_mt_sct_DailyDialog_test_000004_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",
"weak_final_state"
] | 0.749 | DailyDialog | test_000004 | 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 for calling us today. I hope you have a good trip. | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=sunday; destination=norwich; origin=cambridge; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "I'm looking for a local place to dine in the centre that serves chinese food.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have restaurants matching your criteria in all price ranges. Do you have a preference on price?",
"turn_id": 2
},
{
"... | MultiWOZ_PMUL0698.json | travel | life_mt_sct_MultiWOZ_PMUL0698.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... | [] | 1 | MultiWOZ | PMUL0698.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Perfect. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=tonight, evening, 4 days; destination=san francisco; origin=san francisco; 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 find a round trip commercial airline flight from San Francisco to Denver.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? San Francisco to Denver, got it.",
"turn_id": 2
},
{
"speaker": "user",
"... | Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | travel | life_mt_sct_Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f_target12 | 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_slot_evidence",
"weak_target_answer"
] | 0 | Taskmaster | dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | 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 |
Oh, yeah. Oulong tea is good for one's health. isn't it? | The dialogue is insurance support in health wellness, with information request intent. The most recent user context is: Well, have you ever heard of Oulong tea and compressed tea? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Believe it or not, tea is the most popular beverage in the world after water.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Well, people from Asia to Europe all enjoy tea.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Right. And China is... | DailyDialog_test_000004 | health_routine | life_mt_sct_DailyDialog_test_000004_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": [
"health_wellness"
... | [
"weak_final_state"
] | 0.97 | DailyDialog | test_000004 | 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 |
How does 5:30 a.m. work? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=tonight, evening, 4 days; destination=san francisco; origin=san francisco; transport_type=flight. The answer should address the customer support step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I'd like to find a round trip commercial airline flight from San Francisco to Denver.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? San Francisco to Denver, got it.",
"turn_id": 2
},
{
"speaker": "user",
"... | Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | travel | life_mt_sct_Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f_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... | [
"weak_slot_evidence"
] | 0.749 | Taskmaster | dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | 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, I like drinking tea at teahouses. | The dialogue is insurance support in health wellness, with planning coordination intent. The most recent user context is: You surely know a lot about Chinese tea. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Believe it or not, tea is the most popular beverage in the world after water.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Well, people from Asia to Europe all enjoy tea.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Right. And China is... | DailyDialog_test_000004 | health_routine | life_mt_sct_DailyDialog_test_000004_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": [
"health_wellness"
... | [
"weak_final_state"
] | 0.899 | DailyDialog | test_000004 | 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, got it. 6:55 p.m. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=tonight, evening, 4 days; destination=san francisco; origin=san francisco; 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 find a round trip commercial airline flight from San Francisco to Denver.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? San Francisco to Denver, got it.",
"turn_id": 2
},
{
"speaker": "user",
"... | Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | travel | life_mt_sct_Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f_target16 | 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... | [
"weak_slot_evidence"
] | 0.749 | Taskmaster | dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | 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 |
Why don't we go for one now? | The dialogue is insurance support in health wellness, with information request intent. The most recent user context is: Oh, so do I. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Believe it or not, tea is the most popular beverage in the world after water.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Well, people from Asia to Europe all enjoy tea.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Right. And China is... | DailyDialog_test_000004 | health_routine | life_mt_sct_DailyDialog_test_000004_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": [
"health_wellness"
... | [
"weak_final_state"
] | 0.899 | DailyDialog | test_000004 | 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 |
Alright, perfect so that is United Airlines as well. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=tonight, evening, 4 days; destination=san francisco; origin=san francisco; 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 find a round trip commercial airline flight from San Francisco to Denver.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? San Francisco to Denver, got it.",
"turn_id": 2
},
{
"speaker": "user",
"... | Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | travel | life_mt_sct_Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f_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... | [
"weak_slot_evidence"
] | 0.749 | Taskmaster | dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | 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 |
Let's go! | The dialogue is insurance support in health wellness, with planning coordination intent. The most recent user context is: Great. We can chat while enjoying a cup there. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Believe it or not, tea is the most popular beverage in the world after water.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Well, people from Asia to Europe all enjoy tea.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Right. And China is... | DailyDialog_test_000004 | health_routine | life_mt_sct_DailyDialog_test_000004_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": [
"health_wellness"
... | [
"fragment_answer",
"low_information_answer",
"too_short_answer",
"weak_final_state",
"weak_target_answer"
] | 0.22 | DailyDialog | test_000004 | 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 |
Pleasure all mine. Enjoy your trip to Denver, have a great night. Your welcome. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=tonight, evening, 4 days; destination=san francisco; origin=san francisco; 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 find a round trip commercial airline flight from San Francisco to Denver.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? San Francisco to Denver, got it.",
"turn_id": 2
},
{
"speaker": "user",
"... | Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | travel | life_mt_sct_Taskmaster_dlg-00100680-00e0-40fe-8321-6d81b21bfc4f_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... | [
"weak_slot_evidence"
] | 0.749 | Taskmaster | dlg-00100680-00e0-40fe-8321-6d81b21bfc4f | 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 don ' t try to lead people. I ' d rather cooperate with everybody, and get the job done by working together. | The dialogue is workplace conversation in education career, with information request intent. The most recent user context is: Are you more of a leader or a follower? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "What are your personal weaknesses?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I ' m afraid I ' m a poor talker. I ' m not comfortable talking with the people whom I have just met for the first time. That is not very good for business, so I have been st... | DailyDialog_test_000005 | travel | life_mt_sct_DailyDialog_test_000005_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_000005 | 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 |
Yes, in most circumstances. | The dialogue is workplace conversation in education career, with information request intent. Key constraints are destination=english. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "What are your personal weaknesses?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I ' m afraid I ' m a poor talker. I ' m not comfortable talking with the people whom I have just met for the first time. That is not very good for business, so I have been st... | DailyDialog_test_000005 | travel | life_mt_sct_DailyDialog_test_000005_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": [
"education_career"
],
"domain_category... | [
"low_information_answer"
] | 0.749 | DailyDialog | test_000005 | 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 |
Yes, I like travelling. I am young, and unmarried. It ' s no problem for me to travel frequently. | The dialogue is workplace conversation in education career, with problem solving intent. Key constraints are destination=english. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "What are your personal weaknesses?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I ' m afraid I ' m a poor talker. I ' m not comfortable talking with the people whom I have just met for the first time. That is not very good for business, so I have been st... | DailyDialog_test_000005 | travel | life_mt_sct_DailyDialog_test_000005_target8 | 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... | [] | 1 | DailyDialog | test_000005 | 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 |
you ' re right. We will be able to travel at high speeds at the beginning and end of the journey, because we will be in built-up areas. | The dialogue is travel planning in travel transportation, with planning coordination intent. Key constraints are destination=london. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "how long will it take us to drive to London?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I think it ' s a distance of 180 kilometers from here to London, so it should be a two-hour drive on the motorway.",
"turn_id": 2
},
{
"speaker": "user"... | DailyDialog_test_000006 | travel | life_mt_sct_DailyDialog_test_000006_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... | [] | 1 | DailyDialog | test_000006 | 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 |
ok. You haven ' t seen my company car, have you? | The dialogue is workplace conversation in education career, with information request intent. Key constraints are destination=london. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "how long will it take us to drive to London?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I think it ' s a distance of 180 kilometers from here to London, so it should be a two-hour drive on the motorway.",
"turn_id": 2
},
{
"speaker": "user"... | DailyDialog_test_000006 | travel | life_mt_sct_DailyDialog_test_000006_target6 | 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... | [] | 1 | DailyDialog | test_000006 | 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 |
I think it ' s over five meters long. I can ' t remember exactly. It has a maximum speed of over 200 kilometers an hour. | The dialogue is workplace conversation in education career, with planning coordination intent. Key constraints are destination=london; transport_type=car. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "how long will it take us to drive to London?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I think it ' s a distance of 180 kilometers from here to London, so it should be a two-hour drive on the motorway.",
"turn_id": 2
},
{
"speaker": "user"... | DailyDialog_test_000006 | travel | life_mt_sct_DailyDialog_test_000006_target8 | 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... | [] | 1 | DailyDialog | test_000006 | 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 |
I can book you a Grey BMW with the contact number [phone removed]. Is there anything else I can do for you today? | The visible history is a taxi booking task in travel transportation. Known constraints are transport_type=taxi. The answer should address the booking or reservation step while tracking pickup, destination, and time. | [
{
"speaker": "user",
"text": "I need a taxi to come to backstreet bistro by 19:30.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Where would you be coming from?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm coming from sesame restaurant and bar.",
"turn_id": ... | MultiWOZ_SNG01627.json | travel | life_mt_sct_MultiWOZ_SNG01627.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": [
"travel_transportation"
],
"do... | [] | 1 | MultiWOZ | SNG01627.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. Unsupported slot evidence is s... | [
{
"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. Unsupported slot evidence is s... | prefix_to_next_assistant_text |
we can ' t. if we went that fast, we would break the speed limit. | The dialogue is workplace conversation in education career, with planning coordination intent. Key constraints are destination=london; transport_type=car. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "how long will it take us to drive to London?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I think it ' s a distance of 180 kilometers from here to London, so it should be a two-hour drive on the motorway.",
"turn_id": 2
},
{
"speaker": "user"... | DailyDialog_test_000006 | travel | life_mt_sct_DailyDialog_test_000006_target10 | 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... | [] | 1 | DailyDialog | test_000006 | 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 |
Thank you for contacting us and have a great day. | The visible history is a taxi booking task in travel transportation. Known constraints are transport_type=taxi. The answer should address the booking or reservation step while tracking pickup, destination, and time. | [
{
"speaker": "user",
"text": "I need a taxi to come to backstreet bistro by 19:30.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Where would you be coming from?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm coming from sesame restaurant and bar.",
"turn_id": ... | MultiWOZ_SNG01627.json | travel | life_mt_sct_MultiWOZ_SNG01627.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": [
"travel_transportation"
],
"do... | [
"answer_not_grounded",
"premature_respond"
] | 0.499 | MultiWOZ | SNG01627.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. Unsupported slot evidence is s... | [
{
"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. Unsupported slot evidence is s... | prefix_to_next_assistant_text |
Yesterday I had a runny nose. Now my nose is stuffed up. I have a sore throat. And I ' m afraid I've got a temperature. I feel terrible. | 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": "Good morning. What's the matter with you?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Good morning, doctor. I have a terrible headache.",
"turn_id": 2
},
{
"speaker": "user",
"text": "All right, young man. Tell me how it got started.",
... | DailyDialog_test_000008 | health_routine | life_mt_sct_DailyDialog_test_000008_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": [
"health_we... | [
"medical_or_health_context",
"sensitive_content"
] | 0.749 | DailyDialog | test_000008 | 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 |
Ah. | 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": "Good morning. What's the matter with you?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Good morning, doctor. I have a terrible headache.",
"turn_id": 2
},
{
"speaker": "user",
"text": "All right, young man. Tell me how it got started.",
... | DailyDialog_test_000008 | health_routine | life_mt_sct_DailyDialog_test_000008_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": [
"health_we... | [
"fragment_answer",
"low_information_answer",
"medical_or_health_context",
"sensitive_content",
"too_short_answer",
"weak_target_answer"
] | 0.17 | DailyDialog | test_000008 | 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 am I supposed to do then? | 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": "Good morning. What's the matter with you?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Good morning, doctor. I have a terrible headache.",
"turn_id": 2
},
{
"speaker": "user",
"text": "All right, young man. Tell me how it got started.",
... | DailyDialog_test_000008 | health_routine | life_mt_sct_DailyDialog_test_000008_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": [
"health_we... | [
"medical_or_health_context",
"sensitive_content"
] | 0.749 | DailyDialog | test_000008 | 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 |
Thank you very much. | 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": "Good morning. What's the matter with you?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Good morning, doctor. I have a terrible headache.",
"turn_id": 2
},
{
"speaker": "user",
"text": "All right, young man. Tell me how it got started.",
... | DailyDialog_test_000008 | health_routine | life_mt_sct_DailyDialog_test_000008_target10 | 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": [
"health_we... | [
"low_information_answer",
"medical_or_health_context",
"sensitive_content"
] | 0.749 | DailyDialog | test_000008 | 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 |
Things are going well with me. | The dialogue is uncertain context in general daily life, with information request intent. The most recent user context is: Everything is fine, and how are you? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Hello, this is Mike, Kara.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Mike! Good to hear from you. How are you?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Everything is fine, and how are you?",
"turn_id": 3
}
] | DailyDialog_test_000010 | home | life_mt_sct_DailyDialog_test_000010_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_000010 | 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 |
May I know the time, when would you like to travel? | The visible history is a flight booking task in travel transportation. Known constraints are origin=march; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi, I'm looking for a flight. I need to visit a friend.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? Sure, I can help you with that. On what dates?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm looking to ... | Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | travel | life_mt_sct_Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013_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... | [] | 1 | Taskmaster | dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | 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 |
Mike, I don't think that it's a good idea to go out again. I really need to focus on getting packed and ready to move back home. | The dialogue is general conversation in home services, with small talk intent. Key constraints are date_or_time=friday. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Hello, this is Mike, Kara.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Mike! Good to hear from you. How are you?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Everything is fine, and how are you?",
"turn_id": 3
},
{
"speake... | DailyDialog_test_000010 | home | life_mt_sct_DailyDialog_test_000010_target6 | 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": [
"home_services"
],
"domain_category": ... | [] | 1 | DailyDialog | test_000010 | 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 |
What seating class? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=morning; origin=march; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi, I'm looking for a flight. I need to visit a friend.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? Sure, I can help you with that. On what dates?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm looking to ... | Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | travel | life_mt_sct_Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013_target6 | 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-0047a087-6a3c-4f27-b0e6-268f53a2e013 | 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 can't really deal with any distractions right now, but I appreciate the nice evening we spent together. | The dialogue is general conversation in food dining, with negotiation decision intent. Key constraints are date_or_time=friday. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Hello, this is Mike, Kara.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Mike! Good to hear from you. How are you?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Everything is fine, and how are you?",
"turn_id": 3
},
{
"speake... | DailyDialog_test_000010 | home | life_mt_sct_DailyDialog_test_000010_target8 | 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": [
"food_dining"
],
"domain_category": "f... | [] | 1 | DailyDialog | test_000010 | 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 |
Anything else? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=morning; origin=march; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi, I'm looking for a flight. I need to visit a friend.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? Sure, I can help you with that. On what dates?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm looking to ... | Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | travel | life_mt_sct_Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013_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... | [
"too_short_answer",
"weak_target_answer"
] | 0.68 | Taskmaster | dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | 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, now I want to change the date from 24th to 28th. | The dialogue is friend conversation in social relationship, with problem solving intent. Key constraints are date_or_duration=3 days; hotel_preference=hotel. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Sun-set hotel. May I help you?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes, I have booked a room for 24th. It's a double room.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Hold on, please. Let me check it for you. Yes, you're righ... | DailyDialog_test_000011 | travel | life_mt_sct_DailyDialog_test_000011_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": [
"social_relationship"
],
"domain_categ... | [
"answer_not_grounded",
"premature_respond",
"weak_slot_evidence"
] | 0.499 | DailyDialog | test_000011 | 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 found a flight for $424 on United Airlines. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=morning; origin=march; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi, I'm looking for a flight. I need to visit a friend.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? Sure, I can help you with that. On what dates?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm looking to ... | Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | travel | life_mt_sct_Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013_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... | [
"premature_respond"
] | 0.899 | Taskmaster | dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | 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 |
Oh, I just remembered I've got a report to write. | The dialogue is workplace conversation in education career, with booking or reservation intent. Key constraints are date_or_duration=tomorrow, morning. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Are you busy tomorrow morning?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I'm free. What's up?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Someone has to pick up the boss at the airport.",
"turn_id": 3
}
] | DailyDialog_test_000012 | travel | life_mt_sct_DailyDialog_test_000012_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": [
"education_career"
],
"domain_category... | [
"answer_not_grounded",
"premature_respond",
"weak_slot_evidence"
] | 0.499 | DailyDialog | test_000012 | 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: date_or_duration; 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: date_or_duration; changed slots: none; removed slots: none.",
"reasoning_confidence": "m... | prefix_to_next_assistant_text |
Yes. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=morning; destination=new york; origin=march; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi, I'm looking for a flight. I need to visit a friend.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? Sure, I can help you with that. On what dates?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm looking to ... | Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | travel | life_mt_sct_Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013_target12 | 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-0047a087-6a3c-4f27-b0e6-268f53a2e013 | 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 would recommend primavera located in 10 king s parade, cb21sj. phone number is [phone removed]. | The visible history is a attraction search task in travel transportation. It should track the visible goal, constraints, and next step. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "I want general information on places to go in the centre area of town.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "There are many attractions available, including architecture, theatre, swimming pools, parks, night clubs, museums, and cinemas. What are ... | MultiWOZ_PMUL1072.json | travel | life_mt_sct_MultiWOZ_PMUL1072.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": [
"travel_tr... | [
"answer_not_grounded",
"off_topic_answer",
"premature_respond",
"weak_final_state"
] | 0.22 | MultiWOZ | PMUL1072.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
One stop at Chicago O'Hare for 3 hours. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=morning; destination=new york; origin=march; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi, I'm looking for a flight. I need to visit a friend.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? Sure, I can help you with that. On what dates?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm looking to ... | Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | travel | life_mt_sct_Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013_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... | [] | 0.899 | Taskmaster | dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | 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 |
Where will you be departing from? | The visible history is a train booking task in travel transportation. Known constraints are transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "I want general information on places to go in the centre area of town.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "There are many attractions available, including architecture, theatre, swimming pools, parks, night clubs, museums, and cinemas. What are ... | MultiWOZ_PMUL1072.json | travel | life_mt_sct_MultiWOZ_PMUL1072.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... | [] | 0.899 | MultiWOZ | PMUL1072.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Booking flight. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=morning; destination=new york; origin=march; transport_type=flight. The answer should address the confirmation clarification step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi, I'm looking for a flight. I need to visit a friend.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? Sure, I can help you with that. On what dates?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm looking to ... | Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | travel | life_mt_sct_Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013_target16 | 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-0047a087-6a3c-4f27-b0e6-268f53a2e013 | 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's free of charge. | The dialogue is uncertain context in general daily life, with information request intent. The most recent user context is: How much is it? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Do you have maps of downtown area?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes, here you are.",
"turn_id": 2
},
{
"speaker": "user",
"text": "How much is it?",
"turn_id": 3
}
] | DailyDialog_test_000015 | other_life | life_mt_sct_DailyDialog_test_000015_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_000015 | 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 first train leaves at 5:01. | The visible history is a train booking task in travel transportation. Known constraints are origin=cambridge; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "I want general information on places to go in the centre area of town.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "There are many attractions available, including architecture, theatre, swimming pools, parks, night clubs, museums, and cinemas. What are ... | MultiWOZ_PMUL1072.json | travel | life_mt_sct_MultiWOZ_PMUL1072.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... | [] | 0.899 | MultiWOZ | PMUL1072.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Is there anything else, I can help you with? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=morning; destination=new york; origin=march; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi, I'm looking for a flight. I need to visit a friend.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? Sure, I can help you with that. On what dates?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm looking to ... | Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | travel | life_mt_sct_Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013_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... | [] | 0.899 | Taskmaster | dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | 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 |
Hi, Mr. Sandals. I'm Michelle, at your service. When do you need the room? | The dialogue is general conversation in travel transportation, with confirmation clarification 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": "Hi there, I want to reserve a hotel room.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "No problem at all. Could I have your full name, please?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Sure, John Sandals.",
"turn_id": 3
}
] | DailyDialog_test_000016 | travel | life_mt_sct_DailyDialog_test_000016_target4 | 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": [
"travel_transporta... | [] | 1 | DailyDialog | test_000016 | 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 |
Booking was successful, the total fee is 107.4 GBP payable at the station. Reference number is: AEE0QDGA. Is there anything else I can help with? | The visible history is a train booking task in travel transportation. Known constraints are origin=cambridge; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "I want general information on places to go in the centre area of town.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "There are many attractions available, including architecture, theatre, swimming pools, parks, night clubs, museums, and cinemas. What are ... | MultiWOZ_PMUL1072.json | travel | life_mt_sct_MultiWOZ_PMUL1072.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 | PMUL1072.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Have a nice day. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=morning; destination=new york; origin=march; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hi, I'm looking for a flight. I need to visit a friend.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Hello, how can I help you? Sure, I can help you with that. On what dates?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm looking to ... | Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | travel | life_mt_sct_Taskmaster_dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013_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... | [
"low_information_answer"
] | 0.749 | Taskmaster | dlg-0047a087-6a3c-4f27-b0e6-268f53a2e013 | 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 |
We have new room rates, sir. Will that be acceptable to you? | The dialogue is general conversation in travel transportation, with information request 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": "Hi there, I want to reserve a hotel room.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "No problem at all. Could I have your full name, please?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Sure, John Sandals.",
"turn_id": 3
},
{... | DailyDialog_test_000016 | travel | life_mt_sct_DailyDialog_test_000016_target6 | 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": [
"travel_transporta... | [] | 1 | DailyDialog | test_000016 | 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 |
Okay fantastic, have a great day. | The visible history is a train booking task in travel transportation. Known constraints are budget=6; origin=cambridge; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "I want general information on places to go in the centre area of town.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "There are many attractions available, including architecture, theatre, swimming pools, parks, night clubs, museums, and cinemas. What are ... | MultiWOZ_PMUL1072.json | travel | life_mt_sct_MultiWOZ_PMUL1072.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": [
"travel_tr... | [
"low_information_answer"
] | 0.749 | MultiWOZ | PMUL1072.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
It's $ 308 a night. | The dialogue is shopping assistance in shopping retail, with information request 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": "Hi there, I want to reserve a hotel room.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "No problem at all. Could I have your full name, please?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Sure, John Sandals.",
"turn_id": 3
},
{... | DailyDialog_test_000016 | travel | life_mt_sct_DailyDialog_test_000016_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": [
"shopping_retail"
... | [
"low_information_answer"
] | 0.749 | DailyDialog | test_000016 | 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 |
Great! Would you prefer smoking or nonsmoking? | The dialogue is shopping assistance in shopping retail, with problem solving 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": "Hi there, I want to reserve a hotel room.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "No problem at all. Could I have your full name, please?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Sure, John Sandals.",
"turn_id": 3
},
{... | DailyDialog_test_000016 | travel | life_mt_sct_DailyDialog_test_000016_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": [
"shopping_retail"
... | [] | 0.899 | DailyDialog | test_000016 | 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 |
Nonsmoking. Now, is a queen-size bed okay? | The dialogue is shopping assistance in shopping retail, with information request 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": "Hi there, I want to reserve a hotel room.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "No problem at all. Could I have your full name, please?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Sure, John Sandals.",
"turn_id": 3
},
{... | DailyDialog_test_000016 | travel | life_mt_sct_DailyDialog_test_000016_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": [
"shopping_retail"
... | [] | 0.899 | DailyDialog | test_000016 | 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 |
Great, Mr. Sandals. Your reservation is confirmed. Now all I need is your phone number. | The dialogue is technical support in shopping retail, with confirmation clarification 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": "Hi there, I want to reserve a hotel room.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "No problem at all. Could I have your full name, please?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Sure, John Sandals.",
"turn_id": 3
},
{... | DailyDialog_test_000016 | travel | life_mt_sct_DailyDialog_test_000016_target14 | 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": [
"shopping_retail"
... | [
"premature_respond"
] | 0.95 | DailyDialog | test_000016 | 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 |
What dates do you want to travel? | The visible history is a flight booking task in travel transportation. Known constraints are destination=new york, albany. The answer should address the confirmation clarification step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_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-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Thank you so much, Mr. Sandals. We look forward to seeing you! | The dialogue is technical support in shopping retail, with information request 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": "Hi there, I want to reserve a hotel room.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "No problem at all. Could I have your full name, please?",
"turn_id": 2
},
{
"speaker": "user",
"text": "Sure, John Sandals.",
"turn_id": 3
},
{... | DailyDialog_test_000016 | travel | life_mt_sct_DailyDialog_test_000016_target16 | 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": [
"shopping_retail"
... | [
"premature_respond"
] | 0.95 | DailyDialog | test_000016 | 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 |
Do you want to return on next Thursday or Friday? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday; destination=new york, albany. The answer should address the customer support step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_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... | [] | 1 | Taskmaster | dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
I'm sorry, sir. What seems to be the trouble? | The dialogue is uncertain context in general daily life, with information request intent. Key constraints are expenses=bill. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Could I have my bill, please?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Certainly, sir.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm afraid there's been a mistake.",
"turn_id": 3
}
] | DailyDialog_test_000017 | personal_finance | life_mt_sct_DailyDialog_test_000017_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"
] | 0.749 | DailyDialog | test_000017 | 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: expenses; 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: expenses; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
Okay, I will find a return flight on 19th morning. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday, morning; destination=new york, albany. The answer should address the customer support step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_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-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
I'll just go and check it for you, sir. | The dialogue is uncertain context in general daily life, with small talk intent. Key constraints are budget=6.5; expenses=bill. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Could I have my bill, please?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Certainly, sir.",
"turn_id": 2
},
{
"speaker": "user",
"text": "I'm afraid there's been a mistake.",
"turn_id": 3
},
{
"speaker": "assistant",
"tex... | DailyDialog_test_000017 | personal_finance | life_mt_sct_DailyDialog_test_000017_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": [
"general_daily_life"
],
"domain_catego... | [
"low_taxonomy_confidence"
] | 0.749 | DailyDialog | test_000017 | 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: expenses; 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: expenses; changed slots: none; removed slots: none.",
"reasoning_confidence": "medium",
... | prefix_to_next_assistant_text |
How many tickets do you need? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday, morning; destination=new york, albany. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_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-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Yes. When I spread it out back home, I found this hole. | The dialogue is customer complaint in home services, with problem solving intent. Key constraints are date_or_time=evening. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Good evening, madam. Can I help you?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes. I bought this sheet here yesterday.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Anything wrong with it?",
"turn_id": 3
}
] | DailyDialog_test_000018 | home | life_mt_sct_DailyDialog_test_000018_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": [
"home_services"
],
"domain_category": ... | [] | 1 | DailyDialog | test_000018 | 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: date_or_time; changed slots: none; removed slots: none.",
"reasoning_confidence": "mediu... | [
{
"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: date_or_time; changed slots: none; removed slots: none.",
"reasoning_confidence": "mediu... | prefix_to_next_assistant_text |
Unfortunately, we do not. | The visible history is a train booking task in travel transportation. It should track departure, destination, and time constraints. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "I'm looking to play a variety of sports. Are there facilities that cater to that?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes, there is one such facility, The Cherry Hinton Village Centre, located at colville road, cherry hinton in the east side of ... | MultiWOZ_PMUL1100.json | travel | life_mt_sct_MultiWOZ_PMUL1100.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": [
"travel_tr... | [
"low_information_answer",
"weak_final_state"
] | 0.749 | MultiWOZ | PMUL1100.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Do you have a preference for class? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday, morning; destination=new york, albany; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_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-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Here it is. | The dialogue is customer complaint in home services, with information request intent. Key constraints are date_or_time=evening. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Good evening, madam. Can I help you?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes. I bought this sheet here yesterday.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Anything wrong with it?",
"turn_id": 3
},
{
"speaker": ... | DailyDialog_test_000018 | home | life_mt_sct_DailyDialog_test_000018_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": [
"home_services"
],
"domain_category": ... | [
"fragment_answer",
"low_information_answer",
"too_short_answer",
"weak_target_answer"
] | 0.25 | DailyDialog | test_000018 | 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: date_or_time; changed slots: none; removed slots: none.",
"reasoning_confidence": "mediu... | [
{
"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: date_or_time; changed slots: none; removed slots: none.",
"reasoning_confidence": "mediu... | prefix_to_next_assistant_text |
I have listings for 5, can i recommend one? | The visible history is a attraction search task in travel transportation. It should track the visible goal, constraints, and next step. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "I'm looking to play a variety of sports. Are there facilities that cater to that?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes, there is one such facility, The Cherry Hinton Village Centre, located at colville road, cherry hinton in the east side of ... | MultiWOZ_PMUL1100.json | travel | life_mt_sct_MultiWOZ_PMUL1100.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... | [
"weak_final_state"
] | 0.899 | MultiWOZ | PMUL1100.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
There are no direct flights. Do you want to check in business? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday, morning; destination=new york, albany; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_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-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
That's very kind of you. Thank you. | The dialogue is customer complaint in home services, with problem solving intent. Key constraints are date_or_time=evening. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "Good evening, madam. Can I help you?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes. I bought this sheet here yesterday.",
"turn_id": 2
},
{
"speaker": "user",
"text": "Anything wrong with it?",
"turn_id": 3
},
{
"speaker": ... | DailyDialog_test_000018 | home | life_mt_sct_DailyDialog_test_000018_target8 | 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": [
"home_services"
],
"domain_category": ... | [] | 0.899 | DailyDialog | test_000018 | 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: date_or_time; changed slots: none; removed slots: none.",
"reasoning_confidence": "mediu... | [
{
"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: date_or_time; changed slots: none; removed slots: none.",
"reasoning_confidence": "mediu... | prefix_to_next_assistant_text |
You may want to try castle galleries. | The visible history is a attraction search task in travel transportation. It should track the visible goal, constraints, and next step. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "I'm looking to play a variety of sports. Are there facilities that cater to that?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes, there is one such facility, The Cherry Hinton Village Centre, located at colville road, cherry hinton in the east side of ... | MultiWOZ_PMUL1100.json | travel | life_mt_sct_MultiWOZ_PMUL1100.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... | [
"weak_final_state"
] | 0.899 | MultiWOZ | PMUL1100.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
There are no direct flights in any class. I will look for the shortest layover for you. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday, morning; destination=new york, albany; transport_type=flight. The answer should address the confirmation clarification step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_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... | [] | 1 | Taskmaster | dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
They're only $ 20 a dozen. | The dialogue is family conversation in social relationship, with information request intent. Key constraints are item_type=some flowers for my wife. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "I need to buy some flowers for my wife.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Perhaps you'd be interested in red roses.",
"turn_id": 2
},
{
"speaker": "user",
"text": "What would the roses cost me?",
"turn_id": 3
}
] | DailyDialog_test_000019 | shopping | life_mt_sct_DailyDialog_test_000019_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": [
"social_relationship"
],
"domain_categ... | [
"low_information_answer"
] | 0.749 | DailyDialog | test_000019 | 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 |
The Castle Galleries is located at Unit SU43, Grande Arcade, Saint Andrews Street. It's in the City Centre. | The visible history is a attraction search task in travel transportation. It should track the visible goal, constraints, and next step. The answer should ask, confirm, or respond only to details present in the visible history. | [
{
"speaker": "user",
"text": "I'm looking to play a variety of sports. Are there facilities that cater to that?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes, there is one such facility, The Cherry Hinton Village Centre, located at colville road, cherry hinton in the east side of ... | MultiWOZ_PMUL1100.json | travel | life_mt_sct_MultiWOZ_PMUL1100.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... | [
"premature_respond",
"weak_final_state"
] | 0.92 | MultiWOZ | PMUL1100.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Is there anything else you want me to look for? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday, morning; destination=new york, albany; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_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-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Yes, that is today's sale price. | The dialogue is family conversation in social relationship, with information request intent. Key constraints are item_type=some flowers for my wife. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "I need to buy some flowers for my wife.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Perhaps you'd be interested in red roses.",
"turn_id": 2
},
{
"speaker": "user",
"text": "What would the roses cost me?",
"turn_id": 3
},
{
"... | DailyDialog_test_000019 | shopping | life_mt_sct_DailyDialog_test_000019_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": [
"social_relationship"
],
"domain_categ... | [
"low_information_answer"
] | 0.749 | DailyDialog | test_000019 | 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 |
I have train TR8726 that would leave at 19:21 and get you to Stevenage at 20:10. Would that work for you? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=sunday; destination=stevenage; origin=cambridge; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "I'm looking to play a variety of sports. Are there facilities that cater to that?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes, there is one such facility, The Cherry Hinton Village Centre, located at colville road, cherry hinton in the east side of ... | MultiWOZ_PMUL1100.json | travel | life_mt_sct_MultiWOZ_PMUL1100.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 | PMUL1100.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Okay, is that it? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday, morning; destination=new york, albany; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_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-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Is there anything else you'd like to get? | The dialogue is family conversation in social relationship, with information request intent. Key constraints are item_type=some flowers for my wife. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "I need to buy some flowers for my wife.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Perhaps you'd be interested in red roses.",
"turn_id": 2
},
{
"speaker": "user",
"text": "What would the roses cost me?",
"turn_id": 3
},
{
"... | DailyDialog_test_000019 | shopping | life_mt_sct_DailyDialog_test_000019_target8 | 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": [
"social_relationship"
],
"domain_categ... | [] | 0.899 | DailyDialog | test_000019 | 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 |
Booking was successful, the total fee is 40.96 GBP payable at the station. Reference number is: MVFN99UC. | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=sunday; destination=stevenage; origin=cambridge; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "I'm looking to play a variety of sports. Are there facilities that cater to that?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes, there is one such facility, The Cherry Hinton Village Centre, located at colville road, cherry hinton in the east side of ... | MultiWOZ_PMUL1100.json | travel | life_mt_sct_MultiWOZ_PMUL1100.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": [
"travel_tr... | [
"answer_not_grounded",
"off_topic_answer"
] | 0.3 | MultiWOZ | PMUL1100.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
I found you a 6 am flight with United Airlines. The cost of the ticket is $1,430. It has Wi-Fi, first class and has one stop for an hour and a half. The total flight time is 7 hours and 24 minutes. How does that sound? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday, morning; destination=new york, albany; transport_type=flight. The answer should address the confirmation clarification step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_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... | [] | 1 | Taskmaster | dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
These roses should make your wife very happy. | The dialogue is family conversation in social relationship, with confirmation clarification intent. Key constraints are item_type=some flowers for my wife. The answer is grounded because it responds to that goal using only those stated details. | [
{
"speaker": "user",
"text": "I need to buy some flowers for my wife.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Perhaps you'd be interested in red roses.",
"turn_id": 2
},
{
"speaker": "user",
"text": "What would the roses cost me?",
"turn_id": 3
},
{
"... | DailyDialog_test_000019 | shopping | life_mt_sct_DailyDialog_test_000019_target10 | 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": [
"social_relationship"
],
"domain_categ... | [] | 0.899 | DailyDialog | test_000019 | 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 are welcome. Thank you for contacting the Cambridge TownInfo centre. Goodbye. | The visible history is a train booking task in travel transportation. Known constraints are budget=4; date_or_duration=sunday; destination=stevenage; origin=cambridge. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "I'm looking to play a variety of sports. Are there facilities that cater to that?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Yes, there is one such facility, The Cherry Hinton Village Centre, located at colville road, cherry hinton in the east side of ... | MultiWOZ_PMUL1100.json | travel | life_mt_sct_MultiWOZ_PMUL1100.json_target16 | 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 | PMUL1100.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
I can. Do you want to know the return flight details first? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday, morning; destination=new york, albany; transport_type=flight. The answer should address the customer support step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_target24 | 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-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
I have the express by holiday inn cambridge. Would you like me to book it for you? | The visible history is a hotel booking task in travel transportation. Known constraints are hotel_preference=hotel. The answer should address the booking or reservation step while tracking area, price, dates, people, and amenities. | [
{
"speaker": "user",
"text": "Are there any accommodations in the east part of town that off free parking?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have 6 places. Would you prefer a guesthouse or a hotel?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I want it... | MultiWOZ_PMUL3979.json | travel | life_mt_sct_MultiWOZ_PMUL3979.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 | PMUL3979.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
The return flight leaves at 10:20 am has one stop for 15 minutes and arrives back in Seattle at 3:36 pm. How does that work for you? | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday, morning; destination=new york, albany; transport_type=flight. The answer should address the confirmation clarification step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_target26 | 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-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Yes, you did. | The dialogue is uncertain context in general daily life, with information request intent. The most recent user context is: I ran a red light? The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Why'd you pull me over?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Are you aware that you drove through a red light?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I ran a red light?",
"turn_id": 3
}
] | DailyDialog_test_000021 | other_life | life_mt_sct_DailyDialog_test_000021_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... | [
"fragment_answer",
"low_information_answer",
"low_taxonomy_confidence",
"too_short_answer",
"weak_final_state",
"weak_target_answer"
] | 0.17 | DailyDialog | test_000021 | 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 |
it has a two star rating | The visible history is a hotel booking task in travel transportation. Known constraints are hotel_preference=hotel. The answer should address the booking or reservation step while tracking area, price, dates, people, and amenities. | [
{
"speaker": "user",
"text": "Are there any accommodations in the east part of town that off free parking?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have 6 places. Would you prefer a guesthouse or a hotel?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I want it... | MultiWOZ_PMUL3979.json | travel | life_mt_sct_MultiWOZ_PMUL3979.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": [
"travel_tr... | [
"low_information_answer"
] | 0.749 | MultiWOZ | PMUL3979.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Great. You're welcome. It's booked. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday, morning; destination=new york, albany; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_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... | [
"low_information_answer"
] | 0.749 | Taskmaster | dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
Weren't you taught that yellow means slow down, not speed up? | The dialogue is uncertain context in general daily life, with information request intent. The most recent user context is: I apologize, but I didn't realize that I did. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Why'd you pull me over?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Are you aware that you drove through a red light?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I ran a red light?",
"turn_id": 3
},
{
"speaker": "assistan... | DailyDialog_test_000021 | other_life | life_mt_sct_DailyDialog_test_000021_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",
"weak_final_state"
] | 0.749 | DailyDialog | test_000021 | 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 |
It is located at 15-17 norman way, coldhams business park. | The visible history is a hotel booking task in travel transportation. Known constraints are hotel_preference=hotel. The answer should address the booking or reservation step while tracking area, price, dates, people, and amenities. | [
{
"speaker": "user",
"text": "Are there any accommodations in the east part of town that off free parking?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have 6 places. Would you prefer a guesthouse or a hotel?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I want it... | MultiWOZ_PMUL3979.json | travel | life_mt_sct_MultiWOZ_PMUL3979.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": [
"travel_tr... | [
"answer_not_grounded",
"premature_respond"
] | 0.499 | MultiWOZ | PMUL3979.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
I will do that. It is done. Thank you. | The visible history is a flight booking task in travel transportation. Known constraints are date_or_duration=friday, morning; destination=new york, albany; transport_type=flight. The answer should address the booking or reservation step while tracking origin, destination, and travel dates. | [
{
"speaker": "user",
"text": "Hello. I need to take a trip to Albany, New York.",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Okay. I see that you're in Seattle right now. Is that where you want to fly out from to Albany?",
"turn_id": 2
},
{
"speaker": "user",
"text": ... | Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa | travel | life_mt_sct_Taskmaster_dlg-006d8337-fc53-4aac-8895-b2f0caa14baa_target30 | 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-006d8337-fc53-4aac-8895-b2f0caa14baa | 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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | [
{
"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; changed slots: none; removed slots: none; new missing slots: none; resolved missing slots: none.",
"reasoning_confidence": "high",
... | prefix_to_next_assistant_text |
So, then why did you speed up? | The dialogue is uncertain context in general daily life, with information request intent. The most recent user context is: I did learn that. The answer is grounded only in the visible dialogue history and should stay conservative. | [
{
"speaker": "user",
"text": "Why'd you pull me over?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "Are you aware that you drove through a red light?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I ran a red light?",
"turn_id": 3
},
{
"speaker": "assistan... | DailyDialog_test_000021 | other_life | life_mt_sct_DailyDialog_test_000021_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",
"weak_final_state"
] | 0.749 | DailyDialog | test_000021 | 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 |
great, what is your departure site? | The visible history is a train booking task in travel transportation. Known constraints are date_or_duration=tuesday; destination=london; hotel_preference=hotel; transport_type=train. The answer should address the booking or reservation step while tracking departure, destination, and time constraints. | [
{
"speaker": "user",
"text": "Are there any accommodations in the east part of town that off free parking?",
"turn_id": 1
},
{
"speaker": "assistant",
"text": "I have 6 places. Would you prefer a guesthouse or a hotel?",
"turn_id": 2
},
{
"speaker": "user",
"text": "I want it... | MultiWOZ_PMUL3979.json | travel | life_mt_sct_MultiWOZ_PMUL3979.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... | [] | 0.899 | MultiWOZ | PMUL3979.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: destination; 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: destination; resolved missing slots: none.",
"reasoning_confidence": "high",
... | 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.