id
stringlengths 1
12
| question
stringlengths 22
566
| golden_answers
dict | data_source
stringclasses 2
values | prompt
listlengths 1
1
| ability
stringclasses 6
values | reward_model
dict | extra_info
dict | metadata
dict |
|---|---|---|---|---|---|---|---|---|
62593
|
The 2006 Stroud District Council election took place on 4 May 2006 to elect members of Stroud District Council which is a local government district in Gloucestershire, England.
|
{
"evidence": [
"2006 Stroud District Council election_sentence_0",
"Stroud District_sentence_0"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe 2006 Stroud District Council election took place on 4 May 2006 to elect members of Stroud District Council which is a local government district in Gloucestershire, England.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"2006 Stroud District Council election_sentence_0",
"Stroud District_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 684,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.75",
"value": "?search="
},
{
"operation": "search",
"time": "38.769",
"value": "2006 Stroud District Council election"
},
{
"operation": "Now on",
"time": "40.158",
"value": "2006 Stroud District Council election"
},
{
"operation": "Highlighting",
"time": "57.021",
"value": "2006 Stroud District Council election_sentence_0"
},
{
"operation": "Page search",
"time": "71.148",
"value": "local"
},
{
"operation": "Page search",
"time": "88.427",
"value": "local"
},
{
"operation": "hyperlink",
"time": "225.055",
"value": "Stroud"
},
{
"operation": "Now on",
"time": "225.523",
"value": "Stroud District"
},
{
"operation": "Page search",
"time": "229.442",
"value": "local"
},
{
"operation": "Highlighting",
"time": "231.495",
"value": "Stroud District_sentence_0"
},
{
"operation": "finish",
"time": "256.731",
"value": "finish"
}
]
}
|
exfever_8641
|
Three Days of the Condor is Robert Redford's debut film.
|
{
"evidence": [
"Three Days of the Condor",
"Sydney Pollack"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThree Days of the Condor is Robert Redford's debut film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Three Days of the Condor",
"Sydney Pollack"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 685,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
36952
|
Ecurie Maarsbergen only every used Michelin tires in eight years competing in F1 World Championship.
|
{
"evidence": [
"Formula One tyres_sentence_8",
"Ecurie Maarsbergen_sentence_0"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nEcurie Maarsbergen only every used Michelin tires in eight years competing in F1 World Championship.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Formula One tyres_sentence_8",
"Ecurie Maarsbergen_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 686,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.208",
"value": "?search="
},
{
"operation": "search",
"time": "9.79",
"value": "Ecurie Maarsbergen"
},
{
"operation": "Now on",
"time": "10.869",
"value": "Ecurie Maarsbergen"
},
{
"operation": "Page search",
"time": "40.351",
"value": "michelin"
},
{
"operation": "search",
"time": "82.805",
"value": "F1 World Championship"
},
{
"operation": "Now on",
"time": "84.287",
"value": "Formula One"
},
{
"operation": "Page search",
"time": "149.833",
"value": "michelin"
},
{
"operation": "Highlighting",
"time": "178.446",
"value": "Formula One_sentence_111"
},
{
"operation": "Highlighting",
"time": "178.446",
"value": "Formula One_title"
},
{
"operation": "Highlighting",
"time": "178.448",
"value": "Formula One_section_0"
},
{
"operation": "Highlighting",
"time": "178.448",
"value": "Formula One_section_5"
},
{
"operation": "Highlighting deleted",
"time": "179.381",
"value": "Formula One_sentence_111"
},
{
"operation": "Highlighting deleted",
"time": "179.382",
"value": "Formula One_title"
},
{
"operation": "Highlighting deleted",
"time": "179.384",
"value": "Formula One_section_0"
},
{
"operation": "Highlighting deleted",
"time": "179.385",
"value": "Formula One_section_5"
},
{
"operation": "Highlighting",
"time": "202.453",
"value": "Formula One_sentence_111"
},
{
"operation": "Highlighting",
"time": "202.453",
"value": "Formula One_title"
},
{
"operation": "Highlighting",
"time": "202.454",
"value": "Formula One_section_0"
},
{
"operation": "Highlighting",
"time": "202.456",
"value": "Formula One_section_5"
},
{
"operation": "back-button-clicked",
"time": "229.613",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "229.729",
"value": "Ecurie Maarsbergen"
},
{
"operation": "search",
"time": "272.237",
"value": "formula one michelin"
},
{
"operation": "Now on",
"time": "273.767",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "277.397",
"value": "Formula One Michelin_section_3"
},
{
"operation": "Now on",
"time": "278.31",
"value": "Michelin#Formula One Michelin section 3"
},
{
"operation": "hyperlink",
"time": "288.428",
"value": "Formula One tyres"
},
{
"operation": "Now on",
"time": "290.824",
"value": "Formula One tyres"
},
{
"operation": "Highlighting",
"time": "307.405",
"value": "Formula One tyres_sentence_8"
},
{
"operation": "back-button-clicked",
"time": "311.797",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "311.891",
"value": "Michelin#Formula One Michelin section 3"
},
{
"operation": "back-button-clicked",
"time": "316.437",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "316.44",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "317.329",
"value": "undefined"
},
{
"operation": "search",
"time": "327.613",
"value": "Ecurie Maarsbergen"
},
{
"operation": "Now on",
"time": "328.788",
"value": "Ecurie Maarsbergen"
},
{
"operation": "Highlighting",
"time": "348.317",
"value": "Ecurie Maarsbergen_sentence_0"
},
{
"operation": "finish",
"time": "404.116",
"value": "finish"
}
]
}
|
exfever_6617
|
Appian Way Productions is the first film and TV production company founded by Leonardo DiCaprio.
|
{
"evidence": [
"Appian Way Productions",
"Television"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAppian Way Productions is the first film and TV production company founded by Leonardo DiCaprio.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Appian Way Productions",
"Television"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 687,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4090
|
A Game of Thrones is the first novel in A Song of Ice and Fire, a series of fantasy novels by an Indian novelist, screenwriter, television producer and short story writer who helped create the Wild Cards anthology series.
|
{
"evidence": [
"A Game of Thrones",
"George R. R. Martin"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nA Game of Thrones is the first novel in A Song of Ice and Fire, a series of fantasy novels by an Indian novelist, screenwriter, television producer and short story writer who helped create the Wild Cards anthology series.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"A Game of Thrones",
"George R. R. Martin"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 688,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5509
|
Zinedine Zidane is a former French professional referee who played one of the different types of football.?
|
{
"evidence": [
"Zinedine Zidane",
"Football player"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nZinedine Zidane is a former French professional referee who played one of the different types of football.?\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Zinedine Zidane",
"Football player"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 689,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7485
|
Cry Freedom is a 1988 epic apartheid drama film directed and produced by Richard Attenborough that centres on real-life events involving a South African anti-apartheid activist who was at the forefront of a grassroots anti-apartheid campaign.
|
{
"evidence": [
"Cry Freedom",
"Steve Biko"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nCry Freedom is a 1988 epic apartheid drama film directed and produced by Richard Attenborough that centres on real-life events involving a South African anti-apartheid activist who was at the forefront of a grassroots anti-apartheid campaign.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Cry Freedom",
"Steve Biko"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 690,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
36608
|
Quality Communications, a British publishing company founded by Dez Skinn, was initially formed to publish Warrior which won 17 Eagle Awards during its short run.
|
{
"evidence": [
"Quality Communications_sentence_1",
"Quality Communications_sentence_5",
"Quality Communications_sentence_6"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nQuality Communications, a British publishing company founded by Dez Skinn, was initially formed to publish Warrior which won 17 Eagle Awards during its short run.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Quality Communications_sentence_1",
"Quality Communications_sentence_5",
"Quality Communications_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 691,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.724",
"value": "?search="
},
{
"operation": "search",
"time": "12.262",
"value": "Quality Communications"
},
{
"operation": "Now on",
"time": "13.031",
"value": "Quality Communications"
},
{
"operation": "Highlighting",
"time": "18.758",
"value": "Quality Communications_sentence_1"
},
{
"operation": "Highlighting",
"time": "49.343",
"value": "Quality Communications_sentence_2"
},
{
"operation": "Highlighting",
"time": "60.943",
"value": "Quality Communications_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "62.663",
"value": "Quality Communications_sentence_2"
},
{
"operation": "Highlighting",
"time": "66.775",
"value": "Quality Communications_sentence_6"
},
{
"operation": "finish",
"time": "111.158",
"value": "finish"
}
]
}
|
46612
|
As a performance indicator aimed to push students towards academic subjects, English Baccalaureate has failed to do so as it has just widened the achievement gap for disadvantaged children.
|
{
"evidence": [
"English Baccalaureate_sentence_26"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAs a performance indicator aimed to push students towards academic subjects, English Baccalaureate has failed to do so as it has just widened the achievement gap for disadvantaged children.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"English Baccalaureate_sentence_26"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 692,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.139",
"value": "?search="
},
{
"operation": "Now on",
"time": "8.085",
"value": "?search="
},
{
"operation": "search",
"time": "19.054",
"value": "English Baccalaureate"
},
{
"operation": "Now on",
"time": "19.96",
"value": "English Baccalaureate"
},
{
"operation": "Page search",
"time": "247.704",
"value": "achievement gap"
},
{
"operation": "Highlighting",
"time": "305.139",
"value": "English Baccalaureate_sentence_26"
},
{
"operation": "finish",
"time": "346.874",
"value": "finish"
}
]
}
|
exfever_2965
|
Margot Frank was the youngest daughter of Otto Frank and Edith Frank, who died in?a prisoner of war camp.
|
{
"evidence": [
"Margot Frank",
"Bergen-Belsen concentration camp"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMargot Frank was the youngest daughter of Otto Frank and Edith Frank, who died in?a prisoner of war camp.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Margot Frank",
"Bergen-Belsen concentration camp"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 693,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1973
|
Calvin Harris is the richest DJ according to Forbes 2019.
|
{
"evidence": [
"Halsey (singer)",
"The Chainsmokers"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nCalvin Harris is the richest DJ according to Forbes 2019.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Halsey (singer)",
"The Chainsmokers"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 694,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6933
|
The Crazies is a 2010 American science fiction horror film starring an actor who made his acting debut in an off-Broadway theater in 1995, in The Monogamist, and won an award presented annually to actors and actresses in recognition of an outstanding New York City stage debut performance.
|
{
"evidence": [
"The Crazies (2010 film)",
"Timothy Olyphant",
"Theatre World Award"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Crazies is a 2010 American science fiction horror film starring an actor who made his acting debut in an off-Broadway theater in 1995, in The Monogamist, and won an award presented annually to actors and actresses in recognition of an outstanding New York City stage debut performance.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Crazies (2010 film)",
"Timothy Olyphant",
"Theatre World Award"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 695,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7155
|
Kajal Aggarwal is the highest-paid Telugu film actress.
|
{
"evidence": [
"Kajal Aggarwal",
"Darling (2010 film)",
"A. Karunakaran"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nKajal Aggarwal is the highest-paid Telugu film actress.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Kajal Aggarwal",
"Darling (2010 film)",
"A. Karunakaran"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 696,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5969
|
The Beach Boys is the most successful American rock band.
|
{
"evidence": [
"The Beach Boys",
"Vocal harmony"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Beach Boys is the most successful American rock band.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Beach Boys",
"Vocal harmony"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 697,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6422
|
Houston is the most populated city in a state in the South Central region of the United States.
|
{
"evidence": [
"Houston",
"Texas"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nHouston is the most populated city in a state in the South Central region of the United States.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Houston",
"Texas"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 698,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6239
|
Dangerous Beauty is a 1998 American biographical movie directed by Marshall Herskovitz, whose genre is a category of narrative fiction intended to be more serious than humorous in tone.
|
{
"evidence": [
"Dangerous Beauty",
"Drama (film and television)"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nDangerous Beauty is a 1998 American biographical movie directed by Marshall Herskovitz, whose genre is a category of narrative fiction intended to be more serious than humorous in tone.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Dangerous Beauty",
"Drama (film and television)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 699,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
50826
|
The 1912 Heat Rustlers season was the 51st season of the franchise and when George Dovey died in 1909, John Dovey sold the Boston Doves team after the 1920 season to John P. Harris.
|
{
"evidence": [
"George Dovey_sentence_5",
"John Dovey_sentence_4"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe 1912 Heat Rustlers season was the 51st season of the franchise and when George Dovey died in 1909, John Dovey sold the Boston Doves team after the 1920 season to John P. Harris.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"George Dovey_sentence_5",
"John Dovey_sentence_4"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 700,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.737",
"value": "?search="
},
{
"operation": "search",
"time": "10.94",
"value": "Contains...1912 Heat Rustlers season"
},
{
"operation": "Now on",
"time": "12.267",
"value": "undefined"
},
{
"operation": "search",
"time": "44.012",
"value": "Contains...1912 Heat Rustlers"
},
{
"operation": "Now on",
"time": "44.816",
"value": "undefined"
},
{
"operation": "search",
"time": "54.331",
"value": "heat rustlers"
},
{
"operation": "Now on",
"time": "55.404",
"value": "undefined"
},
{
"operation": "search",
"time": "75.788",
"value": "george dovey"
},
{
"operation": "Now on",
"time": "76.486",
"value": "George Dovey"
},
{
"operation": "Highlighting",
"time": "126.08",
"value": "George Dovey_sentence_5"
},
{
"operation": "hyperlink",
"time": "147.263",
"value": "Boston Doves"
},
{
"operation": "Now on",
"time": "148.103",
"value": "History of the Boston Braves"
},
{
"operation": "search",
"time": "182.764",
"value": "1912 boston doves"
},
{
"operation": "Now on",
"time": "184.318",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "187.897",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "188.563",
"value": "History of the Boston Braves"
},
{
"operation": "search",
"time": "241.831",
"value": "John Dovey"
},
{
"operation": "Now on",
"time": "242.732",
"value": "John Dovey"
},
{
"operation": "Highlighting",
"time": "254.509",
"value": "John Dovey_sentence_4"
},
{
"operation": "finish",
"time": "270.046",
"value": "finish"
}
]
}
|
73103
|
Fulton Theatre was built by the architects Herts & Tallant for Henry B. Harris and it features three murals, Twenty-year-old Mae West was discovered here.
|
{
"evidence": [
"Fulton Theatre_sentence_6"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nFulton Theatre was built by the architects Herts & Tallant for Henry B. Harris and it features three murals, Twenty-year-old Mae West was discovered here.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Fulton Theatre_sentence_6"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 701,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.143",
"value": "?search="
},
{
"operation": "search",
"time": "19.02",
"value": "Fulton Theatre"
},
{
"operation": "Now on",
"time": "19.814",
"value": "Fulton Theatre"
},
{
"operation": "Page search",
"time": "63.133",
"value": "hart"
},
{
"operation": "Page search",
"time": "82.777",
"value": "herts"
},
{
"operation": "Highlighting",
"time": "85.076",
"value": "Fulton Theatre_cell_0_7_1"
},
{
"operation": "Highlighting",
"time": "85.081",
"value": "Fulton Theatre_header_cell_0_7_0"
},
{
"operation": "Highlighting",
"time": "85.082",
"value": "Fulton Theatre_header_cell_0_3_0"
},
{
"operation": "Highlighting",
"time": "99.367",
"value": "Fulton Theatre_sentence_4"
},
{
"operation": "Highlighting",
"time": "112.532",
"value": "Fulton Theatre_sentence_5"
},
{
"operation": "Page search",
"time": "129.022",
"value": "west"
},
{
"operation": "Highlighting",
"time": "137.838",
"value": "Fulton Theatre_sentence_6"
},
{
"operation": "Highlighting deleted",
"time": "139.75",
"value": "Fulton Theatre_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "140.775",
"value": "Fulton Theatre_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "142.374",
"value": "Fulton Theatre_cell_0_7_1"
},
{
"operation": "Highlighting deleted",
"time": "142.379",
"value": "Fulton Theatre_header_cell_0_7_0"
},
{
"operation": "Highlighting deleted",
"time": "142.38",
"value": "Fulton Theatre_header_cell_0_3_0"
},
{
"operation": "finish",
"time": "296.202",
"value": "finish"
}
]
}
|
77528
|
Keiichi Ishizaka was employed by Toshiba-EMI from 1994 through 2009, the year he won the Order of the Rising Sun, Gold Rays with Neck Ribbon Award.
|
{
"evidence": [
"Keiichi Ishizaka_sentence_3"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nKeiichi Ishizaka was employed by Toshiba-EMI from 1994 through 2009, the year he won the Order of the Rising Sun, Gold Rays with Neck Ribbon Award.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Keiichi Ishizaka_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 702,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.964",
"value": "?search="
},
{
"operation": "search",
"time": "11.369",
"value": "Keiichi Ishizaka"
},
{
"operation": "Now on",
"time": "12.28",
"value": "Keiichi Ishizaka"
},
{
"operation": "Page search",
"time": "27.32",
"value": "Toshiba-EMI"
},
{
"operation": "Highlighting",
"time": "30.671",
"value": "Keiichi Ishizaka_sentence_3"
},
{
"operation": "finish",
"time": "47.414",
"value": "finish"
}
]
}
|
exfever_8111
|
Daenerys Targaryen is a fictional character by an American novelist?and author of a series of novels whose genre is high fantasy.?
|
{
"evidence": [
"Daenerys Targaryen",
"George R. R. Martin",
"High fantasy"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nDaenerys Targaryen is a fictional character by an American novelist?and author of a series of novels whose genre is high fantasy.?\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Daenerys Targaryen",
"George R. R. Martin",
"High fantasy"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 703,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
11951
|
Fonogram 2007 winner Magdi Ruzsa, outvoting five other artists, represented Hungary in the Eurovision Song Contest 2007 with the song Unsubstantial Blues.
|
{
"evidence": [
"Magdi Rúzsa_sentence_2",
"Magdi Rúzsa_sentence_3"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nFonogram 2007 winner Magdi Ruzsa, outvoting five other artists, represented Hungary in the Eurovision Song Contest 2007 with the song Unsubstantial Blues.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Magdi Rúzsa_sentence_2",
"Magdi Rúzsa_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 704,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1",
"value": "?search="
},
{
"operation": "search",
"time": "22.976",
"value": "Magdi Rúzsa"
},
{
"operation": "Now on",
"time": "24.301",
"value": "Magdi Rúzsa"
},
{
"operation": "Highlighting",
"time": "42.793",
"value": "Magdi Rúzsa_sentence_2"
},
{
"operation": "Highlighting",
"time": "51.56",
"value": "Magdi Rúzsa_sentence_3"
},
{
"operation": "hyperlink",
"time": "87.872",
"value": "Fonogram Hungarian Music Awards"
},
{
"operation": "Now on",
"time": "88.75",
"value": "Hungarian Music Awards"
},
{
"operation": "finish",
"time": "103.805",
"value": "finish"
}
]
}
|
71318
|
Tzvika Brot is the current mayor of Bat Yam, having served in that position since 2018.
|
{
"evidence": [
"Tzvika Brot_sentence_0",
"Tzvika Brot_sentence_21"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nTzvika Brot is the current mayor of Bat Yam, having served in that position since 2018.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Tzvika Brot_sentence_0",
"Tzvika Brot_sentence_21"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 705,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.112",
"value": "?search="
},
{
"operation": "search",
"time": "12.373",
"value": "Tzvika Brot"
},
{
"operation": "Now on",
"time": "14.341",
"value": "Tzvika Brot"
},
{
"operation": "Highlighting",
"time": "18.768",
"value": "Tzvika Brot_sentence_0"
},
{
"operation": "Highlighting",
"time": "28.358",
"value": "Tzvika Brot_sentence_21"
},
{
"operation": "finish",
"time": "69.808",
"value": "finish"
}
]
}
|
86600
|
Melanesia Nazarene Bible College was established in 1964, has over 157 students enrolled and graduated 43 students in September 2009.
|
{
"evidence": [
"Melanesia Nazarene Bible College_sentence_4",
"Melanesia Nazarene Bible College_sentence_5"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMelanesia Nazarene Bible College was established in 1964, has over 157 students enrolled and graduated 43 students in September 2009.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Melanesia Nazarene Bible College_sentence_4",
"Melanesia Nazarene Bible College_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 706,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.929",
"value": "?search="
},
{
"operation": "search",
"time": "8.99",
"value": "Melanesia Nazarene Bible College"
},
{
"operation": "Now on",
"time": "9.675",
"value": "Melanesia Nazarene Bible College"
},
{
"operation": "Highlighting",
"time": "14.917",
"value": "Melanesia Nazarene Bible College_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "14.919",
"value": "Melanesia Nazarene Bible College_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "19.581",
"value": "Melanesia Nazarene Bible College_cell_0_2_1"
},
{
"operation": "Highlighting",
"time": "19.583",
"value": "Melanesia Nazarene Bible College_header_cell_0_2_0"
},
{
"operation": "Highlighting deleted",
"time": "21.261",
"value": "Melanesia Nazarene Bible College_cell_0_2_1"
},
{
"operation": "Highlighting deleted",
"time": "21.262",
"value": "Melanesia Nazarene Bible College_header_cell_0_2_0"
},
{
"operation": "Highlighting deleted",
"time": "24.453",
"value": "Melanesia Nazarene Bible College_cell_0_1_1"
},
{
"operation": "Highlighting deleted",
"time": "24.455",
"value": "Melanesia Nazarene Bible College_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "28.301",
"value": "Melanesia Nazarene Bible College_cell_0_2_1"
},
{
"operation": "Highlighting",
"time": "28.302",
"value": "Melanesia Nazarene Bible College_header_cell_0_2_0"
},
{
"operation": "Highlighting deleted",
"time": "33.901",
"value": "Melanesia Nazarene Bible College_cell_0_2_1"
},
{
"operation": "Highlighting deleted",
"time": "33.903",
"value": "Melanesia Nazarene Bible College_header_cell_0_2_0"
},
{
"operation": "Highlighting",
"time": "43.445",
"value": "Melanesia Nazarene Bible College_cell_0_2_1"
},
{
"operation": "Highlighting",
"time": "43.447",
"value": "Melanesia Nazarene Bible College_header_cell_0_2_0"
},
{
"operation": "Highlighting deleted",
"time": "51.781",
"value": "Melanesia Nazarene Bible College_cell_0_2_1"
},
{
"operation": "Highlighting deleted",
"time": "51.784",
"value": "Melanesia Nazarene Bible College_header_cell_0_2_0"
},
{
"operation": "Highlighting",
"time": "59.988",
"value": "Melanesia Nazarene Bible College_sentence_4"
},
{
"operation": "Highlighting",
"time": "68.631",
"value": "Melanesia Nazarene Bible College_sentence_5"
},
{
"operation": "finish",
"time": "78.431",
"value": "finish"
}
]
}
|
exfever_8870
|
Inception is a 2010 science fiction action film written and directed by a British-American film director, producer, and screenwriter with a 2002 American psychological thriller film credited to him.
|
{
"evidence": [
"Inception",
"Christopher Nolan",
"Insomnia (2002 film)"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nInception is a 2010 science fiction action film written and directed by a British-American film director, producer, and screenwriter with a 2002 American psychological thriller film credited to him.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Inception",
"Christopher Nolan",
"Insomnia (2002 film)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 707,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
40503
|
An artist, who was born in a notable family in Uruguay, enjoyed poems, stories and organizing poetry gatherings.
|
{
"evidence": [
"Juan Zorrilla de San Martín_sentence_0",
"Juan Zorrilla de San Martín_sentence_1",
"Juan Zorrilla de San Martín_sentence_3"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAn artist, who was born in a notable family in Uruguay, enjoyed poems, stories and organizing poetry gatherings.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Juan Zorrilla de San Martín_sentence_0",
"Juan Zorrilla de San Martín_sentence_1",
"Juan Zorrilla de San Martín_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 708,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.276",
"value": "?search="
},
{
"operation": "search",
"time": "63.91",
"value": "Uruguay artist"
},
{
"operation": "Now on",
"time": "65.825",
"value": "undefined"
},
{
"operation": "Page search",
"time": "75.158",
"value": "poetry"
},
{
"operation": "search",
"time": "94.005",
"value": "Uruguay poet"
},
{
"operation": "Now on",
"time": "95.664",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "102.075",
"value": "Líber Falco"
},
{
"operation": "Now on",
"time": "102.808",
"value": "Líber Falco"
},
{
"operation": "Page search",
"time": "115.089",
"value": "notable"
},
{
"operation": "back-button-clicked",
"time": "118.237",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "119.056",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "120.563",
"value": "Juan Zorrilla de San Martín"
},
{
"operation": "Now on",
"time": "121.67",
"value": "Juan Zorrilla de San Martín"
},
{
"operation": "Page search",
"time": "125.613",
"value": "notable"
},
{
"operation": "Highlighting",
"time": "147.275",
"value": "Juan Zorrilla de San Martín_sentence_0"
},
{
"operation": "Highlighting",
"time": "150.836",
"value": "Juan Zorrilla de San Martín_sentence_1"
},
{
"operation": "Highlighting",
"time": "152.754",
"value": "Juan Zorrilla de San Martín_sentence_3"
},
{
"operation": "back-button-clicked",
"time": "172.234",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "173.045",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "176.046",
"value": "Libertango"
},
{
"operation": "Now on",
"time": "178.524",
"value": "Libertango"
},
{
"operation": "Page search",
"time": "182.926",
"value": "notable"
},
{
"operation": "back-button-clicked",
"time": "195.422",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "196.224",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "198.911",
"value": "Salvador Bécquer Puig"
},
{
"operation": "Now on",
"time": "199.64",
"value": "Salvador Bécquer Puig"
},
{
"operation": "back-button-clicked",
"time": "207.946",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "208.799",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "212.481",
"value": "Emilio Oribe"
},
{
"operation": "Now on",
"time": "213.226",
"value": "Emilio Oribe"
},
{
"operation": "back-button-clicked",
"time": "218.622",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "219.912",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "222.551",
"value": "Horacio Quiroga"
},
{
"operation": "Now on",
"time": "223.637",
"value": "Horacio Quiroga"
},
{
"operation": "back-button-clicked",
"time": "235.878",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "236.676",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "239.751",
"value": "Rafael Barradas"
},
{
"operation": "Now on",
"time": "240.469",
"value": "Rafael Barradas"
},
{
"operation": "back-button-clicked",
"time": "247.307",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "249.327",
"value": "undefined"
},
{
"operation": "finish",
"time": "283.828",
"value": "finish"
}
]
}
|
14050
|
Civil unrest was such that terror, discrimination and "ethnic cleansing" were still present; thus local Serb forces managed to complete their cleansing of the UNPA areas, started in 1991, that left only 279 Croats there out of a pre-war population of 102,000.
|
{
"evidence": [
"United Nations Protection Force_sentence_17",
"United Nations Protection Force_sentence_18"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nCivil unrest was such that terror, discrimination and \"ethnic cleansing\" were still present; thus local Serb forces managed to complete their cleansing of the UNPA areas, started in 1991, that left only 279 Croats there out of a pre-war population of 102,000.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"United Nations Protection Force_sentence_17",
"United Nations Protection Force_sentence_18"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 709,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.753",
"value": "?search="
},
{
"operation": "search",
"time": "72.345",
"value": "United Nations Protection Force"
},
{
"operation": "Now on",
"time": "73.549",
"value": "United Nations Protection Force"
},
{
"operation": "Highlighting",
"time": "107.094",
"value": "United Nations Protection Force_sentence_17"
},
{
"operation": "Highlighting",
"time": "117.536",
"value": "United Nations Protection Force_sentence_18"
},
{
"operation": "finish",
"time": "125.299",
"value": "finish"
}
]
}
|
exfever_7706
|
Jon Snow is the youngest fictional character in the fantasy novels by George R. R. Martin.
|
{
"evidence": [
"Jon Snow (character)",
"Kit Harington",
"Primetime Emmy Award"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJon Snow is the youngest fictional character in the fantasy novels by George R. R. Martin.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jon Snow (character)",
"Kit Harington",
"Primetime Emmy Award"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 710,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_509
|
Ronald Perlman starred as a fictional character created by writer-artist Mike Mignola and has appeared in various eponymous miniseries and a standalone issue.
|
{
"evidence": [
"Ron Perlman",
"Hellboy",
"One-shot (comics)"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nRonald Perlman starred as a fictional character created by writer-artist Mike Mignola and has appeared in various eponymous miniseries and a standalone issue.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Ron Perlman",
"Hellboy",
"One-shot (comics)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 711,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8787
|
The Godfather Part III is a 1990 American crime film starring an American actor, producer, and director.
|
{
"evidence": [
"The Godfather Part III",
"Joe Mantegna"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Godfather Part III is a 1990 American crime film starring an American actor, producer, and director.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Godfather Part III",
"Joe Mantegna"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 712,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
90713
|
Nucleoporin 153, a protein which in reptiles is encoded by the NUP153 gene, is an essential component of the basket of nuclear pore complexes (NPCs) in vertebrates, and required for the anchoring of NPCs.
|
{
"evidence": [
"Nucleoporin 153_sentence_0",
"Nucleoporin 153_sentence_1"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nNucleoporin 153, a protein which in reptiles is encoded by the NUP153 gene, is an essential component of the basket of nuclear pore complexes (NPCs) in vertebrates, and required for the anchoring of NPCs.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Nucleoporin 153_sentence_0",
"Nucleoporin 153_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 713,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.522",
"value": "?search="
},
{
"operation": "search",
"time": "14.938",
"value": "Nucleoporin 153"
},
{
"operation": "Now on",
"time": "15.953",
"value": "Nucleoporin 153"
},
{
"operation": "Highlighting",
"time": "38.614",
"value": "Nucleoporin 153_sentence_0"
},
{
"operation": "Highlighting",
"time": "54.235",
"value": "Nucleoporin 153_sentence_1"
},
{
"operation": "search",
"time": "74.057",
"value": "reptiles nucleoporin"
},
{
"operation": "Now on",
"time": "75.098",
"value": "undefined"
},
{
"operation": "search",
"time": "87.019",
"value": "reptiles nup153"
},
{
"operation": "Now on",
"time": "87.794",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "93.33",
"value": "Vanuatu"
},
{
"operation": "Now on",
"time": "94.556",
"value": "Vanuatu"
},
{
"operation": "back-button-clicked",
"time": "113.474",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "114.135",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "114.862",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "114.869",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "115.121",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "116.146",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "116.153",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "116.41",
"value": "Nucleoporin 153"
},
{
"operation": "finish",
"time": "150.701",
"value": "finish"
}
]
}
|
exfever_4737
|
Temple of the Dog was an American rock supergroup that formed in Seattle it was conceived by a Korean singer, songwriter, and musician best known as the lead vocalist and rhythm guitarist.
|
{
"evidence": [
"Temple of the Dog",
"Chris Cornell"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nTemple of the Dog was an American rock supergroup that formed in Seattle it was conceived by a Korean singer, songwriter, and musician best known as the lead vocalist and rhythm guitarist.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Temple of the Dog",
"Chris Cornell"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 714,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2604
|
Land Rover was the first brand to receive a Queen's Award for Enterprise for outstanding contribution to international trade.
|
{
"evidence": [
"Land Rover",
"Sport utility vehicle",
"Light truck"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nLand Rover was the first brand to receive a Queen's Award for Enterprise for outstanding contribution to international trade.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Land Rover",
"Sport utility vehicle",
"Light truck"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 715,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3872
|
Joel Daniel Coen and Ethan Jesse Coen are American filmmakers whose most acclaimed works include the 1990 American neo-noir gangster film starring Gabriel Byrne, Marcia Gay Harden, John Turturro, Jon Polito, J. E. Freeman, and Albert Finney.
|
{
"evidence": [
"Coen brothers",
"Miller's Crossing"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJoel Daniel Coen and Ethan Jesse Coen are American filmmakers whose most acclaimed works include the 1990 American neo-noir gangster film starring Gabriel Byrne, Marcia Gay Harden, John Turturro, Jon Polito, J. E. Freeman, and Albert Finney.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Coen brothers",
"Miller's Crossing"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 716,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
73553
|
The Brankelow Cottage is a folly on the Combermere Abbey (founded in the 1130s by Hugh Malbank, Baron of Nantwichand was also associated with Ranulf de Gernons, Earl of Chester) uses red bricks with ashlar dressings as its main building component where the main (lake-facing) front has a single storey with seven symmetrical bays, and the bays of the main face are separated by pilasters topped with stone finials.
|
{
"evidence": [
"Brankelow Cottage_sentence_0",
"Combermere Abbey_sentence_1",
"Brankelow Cottage_sentence_13",
"Brankelow Cottage_sentence_15",
"Brankelow Cottage_sentence_16"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Brankelow Cottage is a folly on the Combermere Abbey (founded in the 1130s by Hugh Malbank, Baron of Nantwichand was also associated with Ranulf de Gernons, Earl of Chester) uses red bricks with ashlar dressings as its main building component where the main (lake-facing) front has a single storey with seven symmetrical bays, and the bays of the main face are separated by pilasters topped with stone finials.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Brankelow Cottage_sentence_0",
"Combermere Abbey_sentence_1",
"Brankelow Cottage_sentence_13",
"Brankelow Cottage_sentence_15",
"Brankelow Cottage_sentence_16"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 717,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.266",
"value": "?search="
},
{
"operation": "search",
"time": "9.502",
"value": "Brankelow Cottage"
},
{
"operation": "Now on",
"time": "10.358",
"value": "Brankelow Cottage"
},
{
"operation": "Highlighting",
"time": "19.638",
"value": "Brankelow Cottage_sentence_0"
},
{
"operation": "hyperlink",
"time": "24.577",
"value": "Combermere Abbey"
},
{
"operation": "Now on",
"time": "26.114",
"value": "Combermere Abbey"
},
{
"operation": "Highlighting",
"time": "28.009",
"value": "Combermere Abbey_sentence_1"
},
{
"operation": "back-button-clicked",
"time": "39.098",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "39.382",
"value": "Brankelow Cottage"
},
{
"operation": "Highlighting",
"time": "51.858",
"value": "Brankelow Cottage_sentence_13"
},
{
"operation": "Highlighting",
"time": "67.33",
"value": "Brankelow Cottage_sentence_15"
},
{
"operation": "Highlighting",
"time": "86.411",
"value": "Brankelow Cottage_sentence_16"
},
{
"operation": "finish",
"time": "158.671",
"value": "finish"
}
]
}
|
exfever_877
|
Karl Malone is an American former professional player of a team sport in which two teams, opposing one another on a rectangular court, compete with the primary objective of shooting a spherical ball, usually ranging in size from very small promotional items to extra large balls used in training exercises.
|
{
"evidence": [
"Karl Malone",
"Basketball",
"Basketball (ball)"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nKarl Malone is an American former professional player of a team sport in which two teams, opposing one another on a rectangular court, compete with the primary objective of shooting a spherical ball, usually ranging in size from very small promotional items to extra large balls used in training exercises.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Karl Malone",
"Basketball",
"Basketball (ball)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 718,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_114
|
Independent films are films with low budgets and most of these films cannot achieve high gross.
|
{
"evidence": [
"Guillermo del Toro",
"Cronos (film)",
"Independent film"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nIndependent films are films with low budgets and most of these films cannot achieve high gross.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Guillermo del Toro",
"Cronos (film)",
"Independent film"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 719,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6158
|
Batman is a 2002 American superhero film based on the character of the same name by a publisher of American comic books and related media.
|
{
"evidence": [
"Spider-Man (2002 film)",
"Marvel Comics"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nBatman is a 2002 American superhero film based on the character of the same name by a publisher of American comic books and related media.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Spider-Man (2002 film)",
"Marvel Comics"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 720,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
71583
|
Vittus Qujaukitsoq was not popular among the citizens.
|
{
"evidence": [
"Vittus Qujaukitsoq_sentence_0"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nVittus Qujaukitsoq was not popular among the citizens.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Vittus Qujaukitsoq_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 721,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.774",
"value": "?search="
},
{
"operation": "search",
"time": "12.333",
"value": "Vittus Qujaukitsoq"
},
{
"operation": "Now on",
"time": "12.948",
"value": "Vittus Qujaukitsoq"
},
{
"operation": "Page search",
"time": "34.418",
"value": "popular"
},
{
"operation": "Page search",
"time": "47.626",
"value": "citizens"
},
{
"operation": "Highlighting",
"time": "134.518",
"value": "Vittus Qujaukitsoq_sentence_0"
},
{
"operation": "finish",
"time": "142.298",
"value": "finish"
}
]
}
|
21160
|
Niono has an area of approximately 491 square kilometers and includes the town and 20 of the surrounding villages and in the 2009 census it has a population of 91,554.
|
{
"evidence": [
"Niono_sentence_1",
"Niono_sentence_2"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nNiono has an area of approximately 491 square kilometers and includes the town and 20 of the surrounding villages and in the 2009 census it has a population of 91,554.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Niono_sentence_1",
"Niono_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 722,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.664",
"value": "?search="
},
{
"operation": "search",
"time": "8.752",
"value": "Niono"
},
{
"operation": "Now on",
"time": "10.481",
"value": "Niono"
},
{
"operation": "Highlighting",
"time": "44.753",
"value": "Niono_sentence_1"
},
{
"operation": "Highlighting",
"time": "52.425",
"value": "Niono_sentence_2"
},
{
"operation": "Highlighting",
"time": "72.644",
"value": "Niono_header_cell_0_7_0"
},
{
"operation": "Highlighting",
"time": "73.305",
"value": "Niono_header_cell_0_8_0"
},
{
"operation": "Highlighting deleted",
"time": "75.802",
"value": "Niono_header_cell_0_8_0"
},
{
"operation": "Highlighting deleted",
"time": "76.229",
"value": "Niono_header_cell_0_7_0"
},
{
"operation": "finish",
"time": "80.753",
"value": "finish"
}
]
}
|
10074
|
Mitogen-activated protein kinase kinase (MAP2K6) is an enzyme and a member of the dual specificity protein kinase family that is encoded by the MAP2K6 gene on chromosome 17 and act as an integration point for multiple biochemical signals.
|
{
"evidence": [
"MAP2K6_sentence_1",
"MAP2K6_sentence_2",
"MAP2K6_sentence_3"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMitogen-activated protein kinase kinase (MAP2K6) is an enzyme and a member of the dual specificity protein kinase family that is encoded by the MAP2K6 gene on chromosome 17 and act as an integration point for multiple biochemical signals.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"MAP2K6_sentence_1",
"MAP2K6_sentence_2",
"MAP2K6_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 723,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.555",
"value": "?search="
},
{
"operation": "search",
"time": "9.303",
"value": "map2k6"
},
{
"operation": "Now on",
"time": "10.257",
"value": "MAP2K6"
},
{
"operation": "Highlighting",
"time": "15.463",
"value": "MAP2K6_sentence_1"
},
{
"operation": "Highlighting",
"time": "21",
"value": "MAP2K6_sentence_2"
},
{
"operation": "Highlighting",
"time": "33.19",
"value": "MAP2K6_sentence_3"
},
{
"operation": "finish",
"time": "41.773",
"value": "finish"
}
]
}
|
exfever_5009
|
A monk is a person who practices religious asceticism and voluntarily chooses to leave a mainstream group of individuals involved in persistent social interaction.
|
{
"evidence": [
"Monk",
"Society"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nA monk is a person who practices religious asceticism and voluntarily chooses to leave a mainstream group of individuals involved in persistent social interaction.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Monk",
"Society"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 724,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
82970
|
Tahlia Wilson was a right handed batter in the 2018–19 Sydney Sixers WBBL season with a 62.50 strike rate.
|
{
"evidence": [
"Tahlia Wilson_sentence_1"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nTahlia Wilson was a right handed batter in the 2018–19 Sydney Sixers WBBL season with a 62.50 strike rate.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Tahlia Wilson_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 725,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.997",
"value": "?search="
},
{
"operation": "search",
"time": "316.829",
"value": "Tahlia Wilson"
},
{
"operation": "Now on",
"time": "317.873",
"value": "Tahlia Wilson"
},
{
"operation": "Highlighting",
"time": "332.026",
"value": "Tahlia Wilson_sentence_1"
},
{
"operation": "finish",
"time": "399.006",
"value": "finish"
}
]
}
|
exfever_7646
|
Tate Ellington is the leading actor in the thriller series Quantico.
|
{
"evidence": [
"Tate Ellington",
"Don't Trust the B---- in Apartment 23"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nTate Ellington is the leading actor in the thriller series Quantico.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Tate Ellington",
"Don't Trust the B---- in Apartment 23"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 726,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6853
|
Amy Winehouse was an English singer and songwriter known for her deep, expressive contralto vocals and her eclectic mix of musical genres including a popular music genre that originated in the African American community throughout the United Kingdom in the 1950s and early 1960s.
|
{
"evidence": [
"Amy Winehouse",
"Soul music"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAmy Winehouse was an English singer and songwriter known for her deep, expressive contralto vocals and her eclectic mix of musical genres including a popular music genre that originated in the African American community throughout the United Kingdom in the 1950s and early 1960s.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Amy Winehouse",
"Soul music"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 727,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
37984
|
Saulius Mikoliūnas was a regular in the first team for Hearts he also silenced critics at the Tynecastle versus city rivals Hibernian match.
|
{
"evidence": [
"Saulius Mikoliūnas_sentence_8",
"Saulius Mikoliūnas_sentence_9"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSaulius Mikoliūnas was a regular in the first team for Hearts he also silenced critics at the Tynecastle versus city rivals Hibernian match.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Saulius Mikoliūnas_sentence_8",
"Saulius Mikoliūnas_sentence_9"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 728,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.995",
"value": "undefined"
},
{
"operation": "search",
"time": "18.813",
"value": "Saulius Mikoliūnas"
},
{
"operation": "Now on",
"time": "20.11",
"value": "Saulius Mikoliūnas"
},
{
"operation": "search",
"time": "42.162",
"value": "Saulius Mikoliūnas"
},
{
"operation": "Now on",
"time": "43.249",
"value": "Saulius Mikoliūnas"
},
{
"operation": "hyperlink",
"time": "45.945",
"value": "Saulius Mikalajūnas"
},
{
"operation": "Now on",
"time": "46.93",
"value": "Saulius Mikalajūnas"
},
{
"operation": "back-button-clicked",
"time": "48.853",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "49.454",
"value": "Saulius Mikoliūnas"
},
{
"operation": "Page search",
"time": "75.099",
"value": "hearts"
},
{
"operation": "Page search",
"time": "75.321",
"value": "hearts"
},
{
"operation": "Highlighting",
"time": "94.39",
"value": "Saulius Mikoliūnas_sentence_8"
},
{
"operation": "Page search",
"time": "105.594",
"value": "silence"
},
{
"operation": "Page search",
"time": "105.719",
"value": "silence"
},
{
"operation": "Page search",
"time": "105.839",
"value": "silence"
},
{
"operation": "Page search",
"time": "105.967",
"value": "silence"
},
{
"operation": "Highlighting",
"time": "115.882",
"value": "Saulius Mikoliūnas_sentence_9"
},
{
"operation": "finish",
"time": "164.995",
"value": "finish"
}
]
}
|
exfever_7613
|
Franklin Delano Roosevelt was an American politician who served as the 32nd head of state and head of government of the United States of America.
|
{
"evidence": [
"Franklin D. Roosevelt",
"President of the United States"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nFranklin Delano Roosevelt was an American politician who served as the 32nd head of state and head of government of the United States of America.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Franklin D. Roosevelt",
"President of the United States"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 729,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
91900
|
Albert Fishlow (economist and professor) studied and published papers regarding Brazil and Latin America's development strategies, which later helped him to receive the National Order of the Southern Cross award of the Brazilian government.
|
{
"evidence": [
"Albert Fishlow_sentence_0",
"Albert Fishlow_sentence_3"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAlbert Fishlow (economist and professor) studied and published papers regarding Brazil and Latin America's development strategies, which later helped him to receive the National Order of the Southern Cross award of the Brazilian government.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Albert Fishlow_sentence_0",
"Albert Fishlow_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 730,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.578",
"value": "?search="
},
{
"operation": "search",
"time": "8.795",
"value": "Albert Fishlow"
},
{
"operation": "Now on",
"time": "9.713",
"value": "Albert Fishlow"
},
{
"operation": "Highlighting",
"time": "15.051",
"value": "Albert Fishlow_sentence_0"
},
{
"operation": "Highlighting",
"time": "99.877",
"value": "Albert Fishlow_sentence_3"
},
{
"operation": "finish",
"time": "363.965",
"value": "finish"
}
]
}
|
8452
|
Khelo India University Games consisted of 30 teams and the one with the most gold metals was Panjab University.
|
{
"evidence": [
"Khelo India University Games_sentence_11"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nKhelo India University Games consisted of 30 teams and the one with the most gold metals was Panjab University.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Khelo India University Games_sentence_11"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 731,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.397",
"value": "?search="
},
{
"operation": "search",
"time": "11.451",
"value": "Khelo India University Games"
},
{
"operation": "Now on",
"time": "13.802",
"value": "Khelo India University Games"
},
{
"operation": "Page search",
"time": "23.255",
"value": "teams"
},
{
"operation": "Highlighting",
"time": "55.979",
"value": "Khelo India University Games_sentence_11"
},
{
"operation": "Highlighting",
"time": "62.056",
"value": "Khelo India University Games_sentence_14"
},
{
"operation": "Highlighting",
"time": "83.644",
"value": "Khelo India University Games_cell_3_1_0"
},
{
"operation": "Highlighting",
"time": "83.646",
"value": "Khelo India University Games_section_3"
},
{
"operation": "Highlighting",
"time": "83.648",
"value": "Khelo India University Games_header_cell_3_0_0"
},
{
"operation": "Highlighting",
"time": "84.146",
"value": "Khelo India University Games_cell_3_2_0"
},
{
"operation": "Highlighting",
"time": "84.564",
"value": "Khelo India University Games_cell_3_3_0"
},
{
"operation": "Highlighting",
"time": "84.979",
"value": "Khelo India University Games_cell_3_4_0"
},
{
"operation": "Highlighting",
"time": "85.418",
"value": "Khelo India University Games_cell_3_5_0"
},
{
"operation": "Highlighting",
"time": "85.843",
"value": "Khelo India University Games_cell_3_6_0"
},
{
"operation": "Highlighting",
"time": "87.621",
"value": "Khelo India University Games_cell_3_7_0"
},
{
"operation": "Highlighting",
"time": "88.246",
"value": "Khelo India University Games_cell_3_8_0"
},
{
"operation": "Highlighting",
"time": "88.679",
"value": "Khelo India University Games_cell_3_9_0"
},
{
"operation": "Highlighting",
"time": "89.128",
"value": "Khelo India University Games_cell_3_10_0"
},
{
"operation": "Highlighting",
"time": "89.567",
"value": "Khelo India University Games_cell_3_11_0"
},
{
"operation": "Highlighting",
"time": "90.025",
"value": "Khelo India University Games_cell_3_12_0"
},
{
"operation": "Highlighting",
"time": "92.2",
"value": "Khelo India University Games_cell_3_13_0"
},
{
"operation": "Highlighting",
"time": "92.672",
"value": "Khelo India University Games_cell_3_14_0"
},
{
"operation": "Highlighting",
"time": "93.26",
"value": "Khelo India University Games_cell_3_15_0"
},
{
"operation": "Highlighting",
"time": "93.752",
"value": "Khelo India University Games_cell_3_16_0"
},
{
"operation": "Highlighting",
"time": "94.502",
"value": "Khelo India University Games_cell_3_17_0"
},
{
"operation": "Highlighting",
"time": "95.021",
"value": "Khelo India University Games_cell_3_18_0"
},
{
"operation": "Highlighting",
"time": "96.72",
"value": "Khelo India University Games_cell_3_19_0"
},
{
"operation": "Highlighting",
"time": "97.451",
"value": "Khelo India University Games_cell_3_20_0"
},
{
"operation": "Highlighting",
"time": "98.108",
"value": "Khelo India University Games_cell_3_21_0"
},
{
"operation": "Highlighting",
"time": "98.873",
"value": "Khelo India University Games_cell_3_22_0"
},
{
"operation": "Highlighting",
"time": "99.584",
"value": "Khelo India University Games_cell_3_23_0"
},
{
"operation": "Highlighting",
"time": "100.063",
"value": "Khelo India University Games_cell_3_24_0"
},
{
"operation": "Highlighting",
"time": "101.454",
"value": "Khelo India University Games_cell_3_25_0"
},
{
"operation": "Highlighting",
"time": "101.94",
"value": "Khelo India University Games_cell_3_26_0"
},
{
"operation": "Highlighting",
"time": "102.396",
"value": "Khelo India University Games_cell_3_27_0"
},
{
"operation": "Highlighting",
"time": "102.929",
"value": "Khelo India University Games_cell_3_28_0"
},
{
"operation": "Highlighting",
"time": "104.75",
"value": "Khelo India University Games_cell_3_29_0"
},
{
"operation": "Highlighting",
"time": "105.462",
"value": "Khelo India University Games_cell_3_30_0"
},
{
"operation": "Highlighting",
"time": "106.203",
"value": "Khelo India University Games_cell_3_31_0"
},
{
"operation": "Highlighting deleted",
"time": "112.275",
"value": "Khelo India University Games_sentence_14"
},
{
"operation": "Highlighting deleted",
"time": "117.705",
"value": "Khelo India University Games_cell_3_31_0"
},
{
"operation": "Highlighting deleted",
"time": "118.414",
"value": "Khelo India University Games_cell_3_30_0"
},
{
"operation": "Highlighting deleted",
"time": "118.776",
"value": "Khelo India University Games_cell_3_29_0"
},
{
"operation": "Highlighting deleted",
"time": "119.232",
"value": "Khelo India University Games_cell_3_28_0"
},
{
"operation": "Highlighting deleted",
"time": "120.539",
"value": "Khelo India University Games_cell_3_27_0"
},
{
"operation": "Highlighting deleted",
"time": "121.017",
"value": "Khelo India University Games_cell_3_26_0"
},
{
"operation": "Highlighting deleted",
"time": "121.381",
"value": "Khelo India University Games_cell_3_25_0"
},
{
"operation": "Highlighting deleted",
"time": "121.733",
"value": "Khelo India University Games_cell_3_24_0"
},
{
"operation": "Highlighting deleted",
"time": "122.276",
"value": "Khelo India University Games_cell_3_23_0"
},
{
"operation": "Highlighting deleted",
"time": "123.497",
"value": "Khelo India University Games_cell_3_22_0"
},
{
"operation": "Highlighting deleted",
"time": "123.965",
"value": "Khelo India University Games_cell_3_21_0"
},
{
"operation": "Highlighting deleted",
"time": "124.351",
"value": "Khelo India University Games_cell_3_20_0"
},
{
"operation": "Highlighting deleted",
"time": "124.715",
"value": "Khelo India University Games_cell_3_19_0"
},
{
"operation": "Highlighting deleted",
"time": "125.13",
"value": "Khelo India University Games_cell_3_18_0"
},
{
"operation": "Highlighting deleted",
"time": "126.402",
"value": "Khelo India University Games_cell_3_17_0"
},
{
"operation": "Highlighting deleted",
"time": "126.794",
"value": "Khelo India University Games_cell_3_16_0"
},
{
"operation": "Highlighting deleted",
"time": "127.991",
"value": "Khelo India University Games_cell_3_11_0"
},
{
"operation": "Highlighting deleted",
"time": "128.571",
"value": "Khelo India University Games_cell_3_13_0"
},
{
"operation": "Highlighting",
"time": "129.02",
"value": "Khelo India University Games_cell_3_13_0"
},
{
"operation": "Highlighting deleted",
"time": "129.405",
"value": "Khelo India University Games_cell_3_14_0"
},
{
"operation": "Highlighting deleted",
"time": "129.799",
"value": "Khelo India University Games_cell_3_15_0"
},
{
"operation": "Highlighting deleted",
"time": "130.47",
"value": "Khelo India University Games_cell_3_13_0"
},
{
"operation": "Highlighting deleted",
"time": "130.965",
"value": "Khelo India University Games_cell_3_12_0"
},
{
"operation": "Highlighting deleted",
"time": "131.621",
"value": "Khelo India University Games_cell_3_10_0"
},
{
"operation": "Highlighting deleted",
"time": "132.093",
"value": "Khelo India University Games_cell_3_9_0"
},
{
"operation": "Highlighting deleted",
"time": "133.877",
"value": "Khelo India University Games_cell_3_1_0"
},
{
"operation": "Highlighting deleted",
"time": "134.346",
"value": "Khelo India University Games_cell_3_2_0"
},
{
"operation": "Highlighting deleted",
"time": "134.957",
"value": "Khelo India University Games_cell_3_3_0"
},
{
"operation": "Highlighting deleted",
"time": "135.414",
"value": "Khelo India University Games_cell_3_4_0"
},
{
"operation": "Highlighting deleted",
"time": "135.877",
"value": "Khelo India University Games_cell_3_5_0"
},
{
"operation": "Highlighting deleted",
"time": "136.333",
"value": "Khelo India University Games_cell_3_6_0"
},
{
"operation": "Highlighting deleted",
"time": "136.857",
"value": "Khelo India University Games_cell_3_7_0"
},
{
"operation": "Highlighting deleted",
"time": "137.289",
"value": "Khelo India University Games_cell_3_8_0"
},
{
"operation": "Highlighting deleted",
"time": "137.293",
"value": "Khelo India University Games_section_3"
},
{
"operation": "Highlighting deleted",
"time": "137.295",
"value": "Khelo India University Games_header_cell_3_0_0"
},
{
"operation": "finish",
"time": "152.019",
"value": "finish"
}
]
}
|
51437
|
There are three members of the ADAR family, ADARs 1-3, with ADAR 1 and ADAR 2 being the only enzymatically active members and involved in editing at the Q/R site, and ADAR3 is thought to have a regulatory role in the brain and is restricted to the brain only.
|
{
"evidence": [
"5-HT2C receptor_sentence_59",
"5-HT2C receptor_sentence_91",
"5-HT2C receptor_sentence_60",
"5-HT2C receptor_sentence_62"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThere are three members of the ADAR family, ADARs 1-3, with ADAR 1 and ADAR 2 being the only enzymatically active members and involved in editing at the Q/R site, and ADAR3 is thought to have a regulatory role in the brain and is restricted to the brain only.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"5-HT2C receptor_sentence_59",
"5-HT2C receptor_sentence_91",
"5-HT2C receptor_sentence_60",
"5-HT2C receptor_sentence_62"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 732,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.178",
"value": "?search="
},
{
"operation": "search",
"time": "18.508",
"value": "Contains...ADAR family"
},
{
"operation": "Now on",
"time": "20.025",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "23.738",
"value": "5-HT2C receptor"
},
{
"operation": "Now on",
"time": "25.155",
"value": "5-HT2C receptor"
},
{
"operation": "Highlighting",
"time": "38.176",
"value": "5-HT2C receptor_sentence_59"
},
{
"operation": "Highlighting",
"time": "99.946",
"value": "5-HT2C receptor_sentence_91"
},
{
"operation": "Highlighting",
"time": "112.197",
"value": "5-HT2C receptor_sentence_60"
},
{
"operation": "Highlighting",
"time": "148.77",
"value": "5-HT2C receptor_sentence_62"
},
{
"operation": "finish",
"time": "165.938",
"value": "finish"
}
]
}
|
exfever_1594
|
Atomic Blonde is a 2017 American action thriller film starring a Scottish actor who made his acting debut as a teen in The Near Room.
|
{
"evidence": [
"Atomic Blonde",
"James McAvoy"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAtomic Blonde is a 2017 American action thriller film starring a Scottish actor who made his acting debut as a teen in The Near Room.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Atomic Blonde",
"James McAvoy"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 733,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2341
|
A Nightmare on Elm Street is an American movie involving a killer stalking and murdering a group of people, usually with the use of bladed tools.
|
{
"evidence": [
"A Nightmare on Elm Street (2010 film)",
"Slasher film"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nA Nightmare on Elm Street is an American movie involving a killer stalking and murdering a group of people, usually with the use of bladed tools.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"A Nightmare on Elm Street (2010 film)",
"Slasher film"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 734,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4556
|
The Woman in Red is a 1985 American romantic comedy film starring several talented artists, including an American actor, playwright, and screenwriter.
|
{
"evidence": [
"The Woman in Red (1984 film)",
"Joseph Bologna"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Woman in Red is a 1985 American romantic comedy film starring several talented artists, including an American actor, playwright, and screenwriter.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Woman in Red (1984 film)",
"Joseph Bologna"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 735,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3420
|
Howard Allan Stern is an American radio and television personality known for his American radio show, whose other prominent staff members include an executive producer born on March 14, 1961.
|
{
"evidence": [
"Howard Stern",
"The Howard Stern Show",
"Gary Dell'Abate"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nHoward Allan Stern is an American radio and television personality known for his American radio show, whose other prominent staff members include an executive producer born on March 14, 1961.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Howard Stern",
"The Howard Stern Show",
"Gary Dell'Abate"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 736,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
42588
|
Sisa Koyamaibole belongs to Fiji, a team that was defeated by Wales but achieve victory over South Africa.
|
{
"evidence": [
"Sisa Koyamaibole_sentence_2"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSisa Koyamaibole belongs to Fiji, a team that was defeated by Wales but achieve victory over South Africa.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Sisa Koyamaibole_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 737,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.884",
"value": "?search="
},
{
"operation": "search",
"time": "9.479",
"value": "Sisa Koyamaibole"
},
{
"operation": "Now on",
"time": "10.42",
"value": "Sisa Koyamaibole"
},
{
"operation": "Highlighting",
"time": "31.938",
"value": "Sisa Koyamaibole_sentence_2"
},
{
"operation": "hyperlink",
"time": "38.83",
"value": "Fijian"
},
{
"operation": "Now on",
"time": "39.94",
"value": "Fiji"
},
{
"operation": "back-button-clicked",
"time": "44.396",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "44.449",
"value": "Sisa Koyamaibole"
},
{
"operation": "Page search",
"time": "60.366",
"value": "Fiji"
},
{
"operation": "Highlighting",
"time": "93.072",
"value": "Sisa Koyamaibole_sentence_12"
},
{
"operation": "Highlighting",
"time": "93.075",
"value": "Sisa Koyamaibole_section_0"
},
{
"operation": "Highlighting",
"time": "93.075",
"value": "Sisa Koyamaibole_section_1"
},
{
"operation": "Highlighting deleted",
"time": "117.852",
"value": "Sisa Koyamaibole_sentence_12"
},
{
"operation": "Highlighting deleted",
"time": "117.854",
"value": "Sisa Koyamaibole_section_0"
},
{
"operation": "Highlighting deleted",
"time": "117.855",
"value": "Sisa Koyamaibole_section_1"
},
{
"operation": "finish",
"time": "149.108",
"value": "finish"
}
]
}
|
exfever_6706
|
Marie Antoinette was the last Queen of France before the period of radical political and societal change in France that began in 1789 and ended in 1799.
|
{
"evidence": [
"Marie Antoinette",
"French Revolution"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMarie Antoinette was the last Queen of France before the period of radical political and societal change in France that began in 1789 and ended in 1799.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Marie Antoinette",
"French Revolution"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 738,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
39428
|
James Alexander Jermyn, an Anglican priest in the first half of the 20th century, was educated at the University of New Zealand and was Archdeacon of Māwhera from 1930 to 1940.
|
{
"evidence": [
"James Jermyn_sentence_0",
"James Jermyn_sentence_1",
"James Jermyn_sentence_5"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJames Alexander Jermyn, an Anglican priest in the first half of the 20th century, was educated at the University of New Zealand and was Archdeacon of Māwhera from 1930 to 1940.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"James Jermyn_sentence_0",
"James Jermyn_sentence_1",
"James Jermyn_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 739,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.726",
"value": "?search="
},
{
"operation": "search",
"time": "9.028",
"value": "James Alexander Jermyn"
},
{
"operation": "Now on",
"time": "9.883",
"value": "James Jermyn"
},
{
"operation": "Highlighting",
"time": "11.91",
"value": "James Jermyn_sentence_0"
},
{
"operation": "Highlighting",
"time": "20.239",
"value": "James Jermyn_sentence_1"
},
{
"operation": "Highlighting",
"time": "38.919",
"value": "James Jermyn_sentence_5"
},
{
"operation": "finish",
"time": "46.191",
"value": "finish"
}
]
}
|
69547
|
The USS Culgoa was a commissioned naval vessel, so it was unable to deliver supplies during the naval blockade of Manila.
|
{
"evidence": [
"USS Culgoa_sentence_3"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe USS Culgoa was a commissioned naval vessel, so it was unable to deliver supplies during the naval blockade of Manila.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"USS Culgoa_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 740,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "7.044",
"value": "?search="
},
{
"operation": "search",
"time": "9.856",
"value": "USS Culgoa"
},
{
"operation": "Now on",
"time": "11.017",
"value": "USS Culgoa"
},
{
"operation": "Highlighting",
"time": "36.037",
"value": "USS Culgoa_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "86.455",
"value": "USS Culgoa_sentence_4"
},
{
"operation": "Highlighting",
"time": "93.427",
"value": "USS Culgoa_cell_0_6_1"
},
{
"operation": "Highlighting",
"time": "93.447",
"value": "USS Culgoa_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "95.562",
"value": "USS Culgoa_cell_0_6_0"
},
{
"operation": "Page search",
"time": "112.567",
"value": "manila"
},
{
"operation": "Highlighting deleted",
"time": "126.451",
"value": "USS Culgoa_cell_0_6_0"
},
{
"operation": "Highlighting deleted",
"time": "127.182",
"value": "USS Culgoa_cell_0_6_1"
},
{
"operation": "Highlighting deleted",
"time": "127.196",
"value": "USS Culgoa_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "131.719",
"value": "USS Culgoa_sentence_3"
},
{
"operation": "finish",
"time": "194.605",
"value": "finish"
}
]
}
|
exfever_3661
|
Laura Prepon is an actress who played a role in a series based on Piper Kerman’s experiences in federal a place used for convicts who violated federal law.
|
{
"evidence": [
"Laura Prepon",
"Orange Is the New Black",
"Federal prison"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nLaura Prepon is an actress who played a role in a series based on Piper Kerman’s experiences in federal a place used for convicts who violated federal law.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Laura Prepon",
"Orange Is the New Black",
"Federal prison"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 741,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
47073
|
The Charlie Davis Orchestra had close connections with the Royal Peacocks and shared a billing with Duke Ellington.
|
{
"evidence": [
"The Charlie Davis Orchestra_sentence_3",
"The Charlie Davis Orchestra_sentence_4"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Charlie Davis Orchestra had close connections with the Royal Peacocks and shared a billing with Duke Ellington.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"The Charlie Davis Orchestra_sentence_3",
"The Charlie Davis Orchestra_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 742,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.942",
"value": "?search="
},
{
"operation": "search",
"time": "10.726",
"value": "Contains...Charlie Davis Orchestra"
},
{
"operation": "Now on",
"time": "12.325",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "31.455",
"value": "The Charlie Davis Orchestra"
},
{
"operation": "Now on",
"time": "31.997",
"value": "The Charlie Davis Orchestra"
},
{
"operation": "Highlighting",
"time": "57.342",
"value": "The Charlie Davis Orchestra_sentence_3"
},
{
"operation": "Highlighting",
"time": "64.081",
"value": "The Charlie Davis Orchestra_sentence_4"
},
{
"operation": "finish",
"time": "69.041",
"value": "finish"
}
]
}
|
exfever_7925
|
James Oliver Cromwell was the most famous American actor and activist.
|
{
"evidence": [
"James Cromwell",
"Secretariat (film)",
"Nick Glennie-Smith"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJames Oliver Cromwell was the most famous American actor and activist.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"James Cromwell",
"Secretariat (film)",
"Nick Glennie-Smith"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 743,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6077
|
Tunisia is the richest country in the northernmost country in Africa.
|
{
"evidence": [
"Tunisia",
"Algeria"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nTunisia is the richest country in the northernmost country in Africa.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Tunisia",
"Algeria"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 744,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_878
|
Goat Island is a small island in the Niagara River, in the middle of Niagara Falls between the Bridal Veil Falls and the Canadian Falls, which is the largest of the three waterfalls that collectively form Niagara Falls on the Niagara River.
|
{
"evidence": [
"Goat Island (New York)",
"Horseshoe Falls"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nGoat Island is a small island in the Niagara River, in the middle of Niagara Falls between the Bridal Veil Falls and the Canadian Falls, which is the largest of the three waterfalls that collectively form Niagara Falls on the Niagara River.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Goat Island (New York)",
"Horseshoe Falls"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 745,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1398
|
London is the smallest city in England.
|
{
"evidence": [
"Agatha Christie",
"Guinness World Records"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nLondon is the smallest city in England.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Agatha Christie",
"Guinness World Records"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 746,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
65651
|
Hirado Castle was constructed in 1704 by order of the 5th daimyō of Hirado domain, Matsura Takashi, and the expenses nearly bankrupted them.
|
{
"evidence": [
"Hirado Castle_sentence_10"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nHirado Castle was constructed in 1704 by order of the 5th daimyō of Hirado domain, Matsura Takashi, and the expenses nearly bankrupted them.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Hirado Castle_sentence_10"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 747,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.878",
"value": "?search="
},
{
"operation": "Now on",
"time": "4.673",
"value": "?search="
},
{
"operation": "search",
"time": "7.692",
"value": "Hirado Castle"
},
{
"operation": "Now on",
"time": "10.592",
"value": "Hirado Castle"
},
{
"operation": "Highlighting",
"time": "43.221",
"value": "Hirado Castle_sentence_10"
},
{
"operation": "finish",
"time": "53.824",
"value": "finish"
}
]
}
|
9080
|
1648 Shajna was discovered by Grigory on the 5th of September 1935.
|
{
"evidence": [
"1648 Shajna_sentence_1"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\n1648 Shajna was discovered by Grigory on the 5th of September 1935.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"1648 Shajna_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 748,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.538",
"value": "?search="
},
{
"operation": "search",
"time": "12.875",
"value": "1648 Shajna"
},
{
"operation": "Now on",
"time": "13.595",
"value": "1648 Shajna"
},
{
"operation": "Highlighting",
"time": "27.895",
"value": "1648 Shajna_sentence_1"
},
{
"operation": "finish",
"time": "37.164",
"value": "finish"
}
]
}
|
31540
|
Rafts and Dreams was presented in 1990 at the Royal Court Theatre under the direction of Jonathan Cullen, and was later revived in 2003 at the Royal Exchange Manchester under the direction of Tim Stark.
|
{
"evidence": [
"Rafts and Dreams_sentence_5"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nRafts and Dreams was presented in 1990 at the Royal Court Theatre under the direction of Jonathan Cullen, and was later revived in 2003 at the Royal Exchange Manchester under the direction of Tim Stark.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Rafts and Dreams_sentence_5"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 749,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.596",
"value": "?search="
},
{
"operation": "search",
"time": "17.392",
"value": "afts and Dreams"
},
{
"operation": "Now on",
"time": "19.751",
"value": "undefined"
},
{
"operation": "search",
"time": "22.183",
"value": "R"
},
{
"operation": "Now on",
"time": "23.887",
"value": "R"
},
{
"operation": "search",
"time": "29.56",
"value": "Rafts and Dreams"
},
{
"operation": "Now on",
"time": "31.289",
"value": "Rafts and Dreams"
},
{
"operation": "Highlighting",
"time": "43.028",
"value": "Rafts and Dreams_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "59.688",
"value": "Rafts and Dreams_sentence_4"
},
{
"operation": "Highlighting",
"time": "60.441",
"value": "Rafts and Dreams_sentence_5"
},
{
"operation": "finish",
"time": "118.117",
"value": "finish"
}
]
}
|
734
|
The Webster Cup Chase, which was awarded Grade 2 status in 2011, is open to horses aged five years and older and takes place every other year at Navan.
|
{
"evidence": [
"Webster Cup Chase_sentence_1"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Webster Cup Chase, which was awarded Grade 2 status in 2011, is open to horses aged five years and older and takes place every other year at Navan.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Webster Cup Chase_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 750,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "97.196",
"value": "Webster Cup Chase"
},
{
"operation": "Highlighting",
"time": "109.477",
"value": "Webster Cup Chase_sentence_0"
},
{
"operation": "Highlighting",
"time": "116.995",
"value": "Webster Cup Chase_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "120.584",
"value": "Webster Cup Chase_sentence_0"
},
{
"operation": "finish",
"time": "151",
"value": "finish"
}
]
}
|
20276
|
Euan is a male name that originated from Scotland's Pictish, an extinct language spoken by a Celtic group of people called Picts.
|
{
"evidence": [
"Pictish language_sentence_0",
"Picts_sentence_2",
"Euan_sentence_0",
"Euan_sentence_1"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nEuan is a male name that originated from Scotland's Pictish, an extinct language spoken by a Celtic group of people called Picts.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Pictish language_sentence_0",
"Picts_sentence_2",
"Euan_sentence_0",
"Euan_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 751,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.627",
"value": "?search="
},
{
"operation": "search",
"time": "25.518",
"value": "Pictish language"
},
{
"operation": "Now on",
"time": "26.869",
"value": "Pictish language"
},
{
"operation": "Highlighting",
"time": "37.023",
"value": "Pictish language_sentence_0"
},
{
"operation": "hyperlink",
"time": "95.085",
"value": "Picts"
},
{
"operation": "Now on",
"time": "96.208",
"value": "Picts"
},
{
"operation": "Highlighting",
"time": "99.546",
"value": "Picts_sentence_2"
},
{
"operation": "back-button-clicked",
"time": "122.319",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "122.481",
"value": "Pictish language"
},
{
"operation": "Page search",
"time": "131.847",
"value": "euan"
},
{
"operation": "Page search",
"time": "180.553",
"value": "name"
},
{
"operation": "hyperlink",
"time": "185.401",
"value": "personal names"
},
{
"operation": "Now on",
"time": "185.983",
"value": "Anthroponymy"
},
{
"operation": "back-button-clicked",
"time": "190.712",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "190.852",
"value": "Pictish language"
},
{
"operation": "hyperlink",
"time": "199.652",
"value": "kingdoms of the Picts"
},
{
"operation": "Now on",
"time": "200.095",
"value": "Picts#Kings and kingdoms"
},
{
"operation": "Page search",
"time": "219.854",
"value": "euan"
},
{
"operation": "search",
"time": "242.843",
"value": "Euan"
},
{
"operation": "Now on",
"time": "243.831",
"value": "Euan"
},
{
"operation": "Highlighting",
"time": "247.092",
"value": "Euan_sentence_0"
},
{
"operation": "Highlighting",
"time": "249.059",
"value": "Euan_sentence_1"
},
{
"operation": "finish",
"time": "403.675",
"value": "finish"
}
]
}
|
59959
|
Dmytro Serhiyovych Osadchyi is a product of the Kirovohrad and Kyiv youth sportive school systems and played in the Ukrainian Second League.
|
{
"evidence": [
"Dmytro Serhiyovych Osadchyi_sentence_2",
"Dmytro Serhiyovych Osadchyi_sentence_3"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nDmytro Serhiyovych Osadchyi is a product of the Kirovohrad and Kyiv youth sportive school systems and played in the Ukrainian Second League.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Dmytro Serhiyovych Osadchyi_sentence_2",
"Dmytro Serhiyovych Osadchyi_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 752,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.106",
"value": "?search="
},
{
"operation": "search",
"time": "9.519",
"value": "Dmytro Serhiyovych Osadchyi"
},
{
"operation": "Now on",
"time": "10.431",
"value": "Dmytro Serhiyovych Osadchyi"
},
{
"operation": "Highlighting",
"time": "382.522",
"value": "Dmytro Serhiyovych Osadchyi_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "436.267",
"value": "Dmytro Serhiyovych Osadchyi_sentence_0"
},
{
"operation": "Highlighting",
"time": "444.018",
"value": "Dmytro Serhiyovych Osadchyi_sentence_2"
},
{
"operation": "Highlighting",
"time": "447.954",
"value": "Dmytro Serhiyovych Osadchyi_sentence_3"
},
{
"operation": "finish",
"time": "455.777",
"value": "finish"
}
]
}
|
18389
|
Mint produced 4,700 gold (1.34% gold, 93% silver and 6% copper and weighs 412g), silver and bronze medals.
|
{
"evidence": [
"Mint (facility)_sentence_1"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMint produced 4,700 gold (1.34% gold, 93% silver and 6% copper and weighs 412g), silver and bronze medals.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Mint (facility)_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 753,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.021",
"value": "?search="
},
{
"operation": "search",
"time": "26.991",
"value": "Mint produced 4,700 gold"
},
{
"operation": "Now on",
"time": "28.755",
"value": "undefined"
},
{
"operation": "search",
"time": "39.191",
"value": "mint"
},
{
"operation": "Now on",
"time": "39.958",
"value": "Mint"
},
{
"operation": "hyperlink",
"time": "211.478",
"value": "2 Coins and collectibles Mint_section_1"
},
{
"operation": "hyperlink",
"time": "214.655",
"value": "Mint (facility)"
},
{
"operation": "Now on",
"time": "215.453",
"value": "Mint (facility)"
},
{
"operation": "Highlighting",
"time": "240.662",
"value": "Mint (facility)_sentence_1"
},
{
"operation": "finish",
"time": "246.388",
"value": "finish"
}
]
}
|
24762
|
Halil Güven founded and directed two important centers at San Diego State University and served as secretary for two terms (1988, 1989) and as president (1993) at Association of Energy Engineers (AEE), San Diego Chapter.
|
{
"evidence": [
"Halil Güven_sentence_11"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nHalil Güven founded and directed two important centers at San Diego State University and served as secretary for two terms (1988, 1989) and as president (1993) at Association of Energy Engineers (AEE), San Diego Chapter.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Halil Güven_sentence_11"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 754,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.16",
"value": "?search="
},
{
"operation": "search",
"time": "23.726",
"value": "Halil Güven"
},
{
"operation": "Now on",
"time": "24.639",
"value": "Halil Güven"
},
{
"operation": "Highlighting",
"time": "60.94",
"value": "Halil Güven_sentence_9"
},
{
"operation": "Highlighting",
"time": "77.915",
"value": "Halil Güven_sentence_11"
},
{
"operation": "Highlighting deleted",
"time": "79.253",
"value": "Halil Güven_sentence_9"
},
{
"operation": "finish",
"time": "90.447",
"value": "finish"
}
]
}
|
83900
|
Leophron is the eldest of the two sons of Anaxilas, in whose name Micythus assumed the sovereignty, and who afterward, at the instigation of Hieron of Syracuse, dispossessed the latter of his authority, Diodorus, from whom we learn these facts, does not mention the name of either of the young princes.
|
{
"evidence": [
"Leophron_sentence_2"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nLeophron is the eldest of the two sons of Anaxilas, in whose name Micythus assumed the sovereignty, and who afterward, at the instigation of Hieron of Syracuse, dispossessed the latter of his authority, Diodorus, from whom we learn these facts, does not mention the name of either of the young princes.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Leophron_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 755,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.929",
"value": "?search="
},
{
"operation": "search",
"time": "14.475",
"value": "Leophron"
},
{
"operation": "Now on",
"time": "15.632",
"value": "Leophron"
},
{
"operation": "Highlighting",
"time": "32.469",
"value": "Leophron_sentence_2"
},
{
"operation": "finish",
"time": "213.966",
"value": "finish"
}
]
}
|
95583
|
Paul Harland had initially been reported as a optimistic, Later his husband, Bosnian architect Tarik Dreca, was convicted for his murder.
|
{
"evidence": [
"Paul Harland_sentence_3",
"Paul Harland_sentence_4"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nPaul Harland had initially been reported as a optimistic, Later his husband, Bosnian architect Tarik Dreca, was convicted for his murder.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Paul Harland_sentence_3",
"Paul Harland_sentence_4"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 756,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.875",
"value": "?search="
},
{
"operation": "search",
"time": "14.075",
"value": "Paul Harland"
},
{
"operation": "Now on",
"time": "14.976",
"value": "Paul Harland"
},
{
"operation": "Page search",
"time": "26.782",
"value": "optimistic"
},
{
"operation": "Highlighting",
"time": "41.197",
"value": "Paul Harland_sentence_3"
},
{
"operation": "Highlighting",
"time": "48.161",
"value": "Paul Harland_sentence_4"
},
{
"operation": "finish",
"time": "204.075",
"value": "finish"
}
]
}
|
exfever_2550
|
Miley Cyrus is the eleventh American singer who has attained the most US Billboard 200 top-five albums in the 21st century.
|
{
"evidence": [
"Miley Cyrus",
"Hannah Montana",
"Alter ego"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMiley Cyrus is the eleventh American singer who has attained the most US Billboard 200 top-five albums in the 21st century.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Miley Cyrus",
"Hannah Montana",
"Alter ego"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 757,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3882
|
Caryn Elaine Johnson is the only American actor to win both Emmy Award and Grammy Award.
|
{
"evidence": [
"Whoopi Goldberg",
"Emmy Award"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nCaryn Elaine Johnson is the only American actor to win both Emmy Award and Grammy Award.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Whoopi Goldberg",
"Emmy Award"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 758,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
33834
|
KEVA (1240 AM) was a radio station broadcasting from Evanston, has been on air since 1953 but did not offer local programming.
|
{
"evidence": [
"KEVA_sentence_1",
"KEVA_sentence_2",
"KEVA_sentence_3"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nKEVA (1240 AM) was a radio station broadcasting from Evanston, has been on air since 1953 but did not offer local programming.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"KEVA_sentence_1",
"KEVA_sentence_2",
"KEVA_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 759,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.849",
"value": "?search="
},
{
"operation": "search",
"time": "24.698",
"value": "KEVA"
},
{
"operation": "Now on",
"time": "25.562",
"value": "KEVA"
},
{
"operation": "Highlighting",
"time": "29.957",
"value": "KEVA_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "37.105",
"value": "KEVA_sentence_1"
},
{
"operation": "Highlighting",
"time": "38.567",
"value": "KEVA_sentence_1"
},
{
"operation": "hyperlink",
"time": "40.658",
"value": "AM"
},
{
"operation": "Now on",
"time": "41.888",
"value": "AM broadcasting"
},
{
"operation": "back-button-clicked",
"time": "44.945",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "45.034",
"value": "KEVA"
},
{
"operation": "Highlighting",
"time": "55.884",
"value": "KEVA_sentence_2"
},
{
"operation": "Highlighting",
"time": "65.539",
"value": "KEVA_sentence_3"
},
{
"operation": "finish",
"time": "72.949",
"value": "finish"
}
]
}
|
75491
|
Beaver Stadium is located on the campus of Pennsylvania State University, its covered in natural grass and has a capacity of less than a hundred thousand.
|
{
"evidence": [
"Beaver Stadium_sentence_4"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nBeaver Stadium is located on the campus of Pennsylvania State University, its covered in natural grass and has a capacity of less than a hundred thousand.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Beaver Stadium_sentence_4"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 760,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.597",
"value": "?search="
},
{
"operation": "search",
"time": "15.163",
"value": "Beaver Stadium"
},
{
"operation": "Now on",
"time": "16.554",
"value": "Beaver Stadium"
},
{
"operation": "Highlighting",
"time": "22.783",
"value": "Beaver Stadium_sentence_0"
},
{
"operation": "Highlighting",
"time": "33.078",
"value": "Beaver Stadium_sentence_5"
},
{
"operation": "Highlighting",
"time": "38.42",
"value": "Beaver Stadium_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "39.636",
"value": "Beaver Stadium_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "40.796",
"value": "Beaver Stadium_sentence_0"
},
{
"operation": "finish",
"time": "193.584",
"value": "finish"
}
]
}
|
exfever_5084
|
The Adjustment Bureau is a 2011 American science fiction written and directed by George Nolfi that has narrative that involves elements of the romance and thriller genres.
|
{
"evidence": [
"The Adjustment Bureau",
"Romantic thriller"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Adjustment Bureau is a 2011 American science fiction written and directed by George Nolfi that has narrative that involves elements of the romance and thriller genres.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Adjustment Bureau",
"Romantic thriller"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 761,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
22658
|
Néstor Breitenbruch was loaned to fellow Primera División team Quilmes in 2015 and joined Liga MX side Tigres UANL in the following year.
|
{
"evidence": [
"Néstor Breitenbruch_sentence_4",
"Néstor Breitenbruch_sentence_6"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nNéstor Breitenbruch was loaned to fellow Primera División team Quilmes in 2015 and joined Liga MX side Tigres UANL in the following year.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Néstor Breitenbruch_sentence_4",
"Néstor Breitenbruch_sentence_6"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 762,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.03",
"value": "?search="
},
{
"operation": "search",
"time": "21.669",
"value": "Néstor Breitenbruch"
},
{
"operation": "Now on",
"time": "22.624",
"value": "Néstor Breitenbruch"
},
{
"operation": "Highlighting",
"time": "89.764",
"value": "Néstor Breitenbruch_sentence_4"
},
{
"operation": "Highlighting",
"time": "97.917",
"value": "Néstor Breitenbruch_sentence_6"
},
{
"operation": "finish",
"time": "112.89",
"value": "finish"
}
]
}
|
exfever_7374
|
The Matrix Revolutions is a 2003 American action novel whose genre uses speculative, fictional science-based depictions of phenomena that are not fully accepted by mainstream science.
|
{
"evidence": [
"The Matrix Revolutions",
"Science fiction film"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Matrix Revolutions is a 2003 American action novel whose genre uses speculative, fictional science-based depictions of phenomena that are not fully accepted by mainstream science.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Matrix Revolutions",
"Science fiction film"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 763,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
86841
|
During the American Revolution, Clare Jung was a medical assistant before becoming a press secretary for five years.
|
{
"evidence": [
"Cläre Jung_sentence_8"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nDuring the American Revolution, Clare Jung was a medical assistant before becoming a press secretary for five years.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Cläre Jung_sentence_8"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 764,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.942",
"value": "?search="
},
{
"operation": "search",
"time": "11.569",
"value": "Clare Jung"
},
{
"operation": "Now on",
"time": "13.583",
"value": "Clare Jung"
},
{
"operation": "Highlighting",
"time": "49.584",
"value": "Cläre Jung_sentence_8"
},
{
"operation": "Highlighting deleted",
"time": "53.215",
"value": "Cläre Jung_sentence_8"
},
{
"operation": "Highlighting",
"time": "55.542",
"value": "Cläre Jung_sentence_8"
},
{
"operation": "Highlighting",
"time": "57.742",
"value": "Cläre Jung_sentence_10"
},
{
"operation": "hyperlink",
"time": "66.062",
"value": "revolutionary period"
},
{
"operation": "Now on",
"time": "67.894",
"value": "German Revolution of 1918–1919"
},
{
"operation": "Highlighting",
"time": "71.567",
"value": "German Revolution of 1918–1919_sentence_4"
},
{
"operation": "Highlighting",
"time": "71.567",
"value": "German Revolution of 1918–1919_title"
},
{
"operation": "back-button-clicked",
"time": "73.023",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "73.671",
"value": "Cläre Jung"
},
{
"operation": "Highlighting",
"time": "86.495",
"value": "Cläre Jung_sentence_8"
},
{
"operation": "finish",
"time": "106.023",
"value": "finish"
}
]
}
|
exfever_354
|
Alexandra Anna Daddario is an American actress who starred in a 2013 American slasher film directed by John Luessenhop.
|
{
"evidence": [
"Alexandra Daddario",
"Texas Chainsaw 3D"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAlexandra Anna Daddario is an American actress who starred in a 2013 American slasher film directed by John Luessenhop.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Alexandra Daddario",
"Texas Chainsaw 3D"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 765,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5494
|
Eva Jacqueline Longoria Bastón was the youngest actress on the NBC sitcom Telenovela.
|
{
"evidence": [
"Eva Longoria",
"CBS"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nEva Jacqueline Longoria Bastón was the youngest actress on the NBC sitcom Telenovela.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Eva Longoria",
"CBS"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 766,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1691
|
Jessica Lange is the first actress to receive multiple awards in just one Awards night.
|
{
"evidence": [
"Jessica Lange",
"Academy Award for Best Supporting Actress"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJessica Lange is the first actress to receive multiple awards in just one Awards night.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jessica Lange",
"Academy Award for Best Supporting Actress"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 767,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
25161
|
A species of sea snail is characterized by its long ribs and a trench which cuts through the ribs.
|
{
"evidence": [
"Gastropoda_sentence_2",
"Gastropoda_sentence_0",
"Invertebrate_sentence_0",
"Snail_sentence_35",
"Snail_sentence_36",
"Snail_sentence_3",
"Snail_sentence_1",
"Snail_sentence_6"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nA species of sea snail is characterized by its long ribs and a trench which cuts through the ribs.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Gastropoda_sentence_2",
"Gastropoda_sentence_0",
"Invertebrate_sentence_0",
"Snail_sentence_35",
"Snail_sentence_36",
"Snail_sentence_3",
"Snail_sentence_1",
"Snail_sentence_6"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 768,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.865",
"value": "?search="
},
{
"operation": "search",
"time": "10.392",
"value": "sea snail"
},
{
"operation": "Now on",
"time": "11.698",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "15.719",
"value": "Types of snails by habitat Snail_section_2"
},
{
"operation": "Now on",
"time": "16.962",
"value": "Snail#Types of snails by habitat Snail section 2"
},
{
"operation": "Highlighting",
"time": "25.419",
"value": "Snail_sentence_35"
},
{
"operation": "hyperlink",
"time": "35.35",
"value": "Snail (disambiguation)"
},
{
"operation": "Now on",
"time": "36.337",
"value": "Snail (disambiguation)"
},
{
"operation": "hyperlink",
"time": "51.449",
"value": "Gastropoda"
},
{
"operation": "Now on",
"time": "52.766",
"value": "Gastropoda"
},
{
"operation": "Highlighting",
"time": "61.158",
"value": "Gastropoda_sentence_2"
},
{
"operation": "Page search",
"time": "87.066",
"value": "sea"
},
{
"operation": "Highlighting",
"time": "112.375",
"value": "Gastropoda_sentence_13"
},
{
"operation": "Page search",
"time": "139.427",
"value": "trench"
},
{
"operation": "Highlighting deleted",
"time": "142.156",
"value": "Gastropoda_sentence_2"
},
{
"operation": "Highlighting",
"time": "143.092",
"value": "Gastropoda_sentence_2"
},
{
"operation": "Page search",
"time": "167.597",
"value": "rib"
},
{
"operation": "Highlighting",
"time": "194.084",
"value": "Gastropoda_sentence_0"
},
{
"operation": "hyperlink",
"time": "195.163",
"value": "invertebrates"
},
{
"operation": "Now on",
"time": "196.638",
"value": "Invertebrate"
},
{
"operation": "Highlighting",
"time": "203.259",
"value": "Invertebrate_sentence_0"
},
{
"operation": "search",
"time": "254.114",
"value": "sea snail"
},
{
"operation": "Now on",
"time": "255.174",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "257.136",
"value": "Types of snails by habitat Snail_section_2"
},
{
"operation": "Now on",
"time": "257.986",
"value": "Snail#Types of snails by habitat Snail section 2"
},
{
"operation": "Highlighting",
"time": "259.947",
"value": "Snail_sentence_35"
},
{
"operation": "Highlighting",
"time": "262.007",
"value": "Snail_sentence_36"
},
{
"operation": "Highlighting",
"time": "271.041",
"value": "Snail_sentence_3"
},
{
"operation": "Highlighting",
"time": "277.462",
"value": "Snail_sentence_1"
},
{
"operation": "Highlighting",
"time": "285.43",
"value": "Snail_sentence_6"
},
{
"operation": "hyperlink",
"time": "298.824",
"value": "3 Types of snails by habitat Snail_section_2"
},
{
"operation": "Now on",
"time": "318.746",
"value": "Snail#Types of snails by habitat Snail section 2"
},
{
"operation": "finish",
"time": "335.562",
"value": "finish"
}
]
}
|
13724
|
Christianity, in its early development, accommodated many traditional practices which at different times, accepted omens and practiced forms of ritual sacrifice; and concepts of "Divine Grace" or "Blessing", as they are described by believers, closely resemble what is referred to as "luck" by others.
|
{
"evidence": [
"Luck_sentence_45",
"Luck_sentence_46"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nChristianity, in its early development, accommodated many traditional practices which at different times, accepted omens and practiced forms of ritual sacrifice; and concepts of \"Divine Grace\" or \"Blessing\", as they are described by believers, closely resemble what is referred to as \"luck\" by others.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Luck_sentence_45",
"Luck_sentence_46"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 769,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.845",
"value": "?search="
},
{
"operation": "search",
"time": "12.85",
"value": "Christianity"
},
{
"operation": "Now on",
"time": "14.834",
"value": "Christianity"
},
{
"operation": "search",
"time": "119.373",
"value": "Luck"
},
{
"operation": "Now on",
"time": "120.626",
"value": "Luck"
},
{
"operation": "Page search",
"time": "138.99",
"value": "accommodated many traditional practices which at different times, accepted omens and practiced forms of ritual sacrifice"
},
{
"operation": "Highlighting",
"time": "149.516",
"value": "Luck_sentence_45"
},
{
"operation": "Highlighting",
"time": "152.794",
"value": "Luck_sentence_46"
},
{
"operation": "finish",
"time": "320.976",
"value": "finish"
}
]
}
|
exfever_2513
|
Joseph Stalin was a Soviet political leader who adhered to the Leninist interpretation of a method of socioeconomic analysis that uses a materialist interpretation of historical development to understand the struggle for agency or power in a society that occurs when two or more people oppose each other in social interaction.
|
{
"evidence": [
"Joseph Stalin",
"Marxism",
"Social conflict"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJoseph Stalin was a Soviet political leader who adhered to the Leninist interpretation of a method of socioeconomic analysis that uses a materialist interpretation of historical development to understand the struggle for agency or power in a society that occurs when two or more people oppose each other in social interaction.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Joseph Stalin",
"Marxism",
"Social conflict"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 770,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_794
|
London is the capital and largest city in England that stands on the longest river entirely in England that flows into the North Sea near a town in the borough of Thurrock, Essex, England.
|
{
"evidence": [
"London",
"River Thames",
"Tilbury"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nLondon is the capital and largest city in England that stands on the longest river entirely in England that flows into the North Sea near a town in the borough of Thurrock, Essex, England.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"London",
"River Thames",
"Tilbury"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 771,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
73358
|
The Latter Day Saint movement held a policy of excommunication of erring members.
|
{
"evidence": [
"The Church of Jesus Christ of Latter-day Saints_sentence_146"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Latter Day Saint movement held a policy of excommunication of erring members.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"The Church of Jesus Christ of Latter-day Saints_sentence_146"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 772,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.249",
"value": "?search="
},
{
"operation": "search",
"time": "31.056",
"value": "latter day saint movement excommunication"
},
{
"operation": "Now on",
"time": "34.376",
"value": "undefined"
},
{
"operation": "search",
"time": "60.423",
"value": "Latter-day Saints"
},
{
"operation": "Now on",
"time": "71.506",
"value": "The Church of Jesus Christ of Latter-day Saints"
},
{
"operation": "hyperlink",
"time": "106.755",
"value": "6 Controversy and criticism The Church of Jesus Christ of Latter-day Saints_section_22"
},
{
"operation": "hyperlink",
"time": "155.928",
"value": "List of sects in the Latter Day Saint movement"
},
{
"operation": "Now on",
"time": "163.18",
"value": "List of denominations in the Latter Day Saint movement"
},
{
"operation": "search",
"time": "254.683",
"value": "excommunication"
},
{
"operation": "Now on",
"time": "260.213",
"value": "Excommunication"
},
{
"operation": "hyperlink",
"time": "298.194",
"value": "1.8 The Church of Jesus Christ of Latter-day Saints Excommunication_section_19"
},
{
"operation": "Highlighting",
"time": "300.784",
"value": "Excommunication_sentence_137"
},
{
"operation": "Highlighting",
"time": "300.785",
"value": "Excommunication_title"
},
{
"operation": "Highlighting",
"time": "300.787",
"value": "Excommunication_section_0"
},
{
"operation": "Highlighting",
"time": "300.788",
"value": "Excommunication_section_19"
},
{
"operation": "Highlighting deleted",
"time": "349.174",
"value": "Excommunication_sentence_137"
},
{
"operation": "Highlighting deleted",
"time": "349.174",
"value": "Excommunication_title"
},
{
"operation": "Highlighting deleted",
"time": "349.177",
"value": "Excommunication_section_0"
},
{
"operation": "Highlighting deleted",
"time": "349.178",
"value": "Excommunication_section_19"
},
{
"operation": "hyperlink",
"time": "356.79",
"value": "The Church of Jesus Christ of Latter-day Saints"
},
{
"operation": "Now on",
"time": "370.865",
"value": "The Church of Jesus Christ of Latter-day Saints"
},
{
"operation": "hyperlink",
"time": "392.879",
"value": "3.4 Programs and organizations The Church of Jesus Christ of Latter-day Saints_section_14"
},
{
"operation": "search",
"time": "540.523",
"value": "intitle"
},
{
"operation": "Now on",
"time": "542.999",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "547.443",
"value": "Comparisons with Christian denominations outside the Latter Day Saint movement The Church of Jesus Christ of Latter-day Saints_section_8"
},
{
"operation": "Now on",
"time": "548.425",
"value": "The Church of Jesus Christ of Latter-day Saints#Comparisons with Christian denominations outside the Latter Day Saint movement The Church of Jesus Christ of Latter-day Saints section 8"
},
{
"operation": "Highlighting",
"time": "602.719",
"value": "The Church of Jesus Christ of Latter-day Saints_sentence_146"
},
{
"operation": "back-button-clicked",
"time": "634.333",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "635.976",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "660.528",
"value": "Comparisons with Christian denominations outside the Latter Day Saint movement The Church of Jesus Christ of Latter-day Saints_section_8"
},
{
"operation": "Now on",
"time": "661.514",
"value": "The Church of Jesus Christ of Latter-day Saints#Comparisons with Christian denominations outside the Latter Day Saint movement The Church of Jesus Christ of Latter-day Saints section 8"
},
{
"operation": "search",
"time": "796.32",
"value": "intitle"
},
{
"operation": "Now on",
"time": "797.752",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "800.668",
"value": "Origin Mormonism and polygamy_section_0"
},
{
"operation": "Now on",
"time": "802.741",
"value": "Mormonism and polygamy#Origin Mormonism and polygamy section 0"
},
{
"operation": "Highlighting",
"time": "819.395",
"value": "Mormonism and polygamy_sentence_34"
},
{
"operation": "Highlighting",
"time": "819.395",
"value": "Mormonism and polygamy_title"
},
{
"operation": "Highlighting",
"time": "819.396",
"value": "Mormonism and polygamy_section_0"
},
{
"operation": "search",
"time": "894.209",
"value": "intitle"
},
{
"operation": "Now on",
"time": "896.914",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "910.9",
"value": "Teachings on the multiple wives of God and Jesus Mormonism and polygamy_section_1"
},
{
"operation": "Now on",
"time": "912.017",
"value": "Mormonism and polygamy#Teachings on the multiple wives of God and Jesus Mormonism and polygamy section 1"
},
{
"operation": "finish",
"time": "953.815",
"value": "finish"
}
]
}
|
20801
|
Miriam Meckel served as the State Secretary, she was a professor of communication sciences and wrote textbooks on cyberpolitics which is the use of the Internet for political activity..
|
{
"evidence": [
"Miriam Meckel_sentence_3",
"Miriam Meckel_sentence_4",
"Miriam Meckel_sentence_5",
"Cyberpolitics_sentence_0"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMiriam Meckel served as the State Secretary, she was a professor of communication sciences and wrote textbooks on cyberpolitics which is the use of the Internet for political activity..\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Miriam Meckel_sentence_3",
"Miriam Meckel_sentence_4",
"Miriam Meckel_sentence_5",
"Cyberpolitics_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 773,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.545",
"value": "?search="
},
{
"operation": "search",
"time": "10.529",
"value": "Miriam Meckel"
},
{
"operation": "Now on",
"time": "11.231",
"value": "Miriam Meckel"
},
{
"operation": "Page search",
"time": "108.753",
"value": "secretary"
},
{
"operation": "Highlighting",
"time": "119.814",
"value": "Miriam Meckel_sentence_3"
},
{
"operation": "Page search",
"time": "138.552",
"value": "communication sc"
},
{
"operation": "Highlighting",
"time": "141.16",
"value": "Miriam Meckel_sentence_4"
},
{
"operation": "Page search",
"time": "147.257",
"value": "textbook"
},
{
"operation": "Page search",
"time": "158.512",
"value": "cyberpol"
},
{
"operation": "Highlighting",
"time": "164.927",
"value": "Miriam Meckel_sentence_5"
},
{
"operation": "hyperlink",
"time": "168.134",
"value": "cyberpolitics"
},
{
"operation": "Now on",
"time": "168.923",
"value": "Cyberpolitics"
},
{
"operation": "Highlighting",
"time": "174.52",
"value": "Cyberpolitics_sentence_0"
},
{
"operation": "finish",
"time": "180.54",
"value": "finish"
}
]
}
|
exfever_4958
|
Kajal Aggarwal is an Indian actress and model who had her first Telugu film released in 2007, a romantic action film dubbed "Meri Saugandh", whose Indo-Aryan language is spoken chiefly in most regions of India.
|
{
"evidence": [
"Kajal Aggarwal",
"Lakshmi Kalyanam (2007 film)",
"Hindi"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nKajal Aggarwal is an Indian actress and model who had her first Telugu film released in 2007, a romantic action film dubbed \"Meri Saugandh\", whose Indo-Aryan language is spoken chiefly in most regions of India.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Kajal Aggarwal",
"Lakshmi Kalyanam (2007 film)",
"Hindi"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 774,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_110
|
The Crown is a historical drama television series that was developed from a play by the Canadian playwright and screenwriter Peter Morgan.
|
{
"evidence": [
"The Crown (TV series)",
"The Audience (2013 play)"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Crown is a historical drama television series that was developed from a play by the Canadian playwright and screenwriter Peter Morgan.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Crown (TV series)",
"The Audience (2013 play)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 775,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
23582
|
The Willow Copse is a play by Dion Boucicault, know for works such as The Shaughraun, and it ran for 191 consecutive performances.
|
{
"evidence": [
"The Willow Copse_sentence_3"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Willow Copse is a play by Dion Boucicault, know for works such as The Shaughraun, and it ran for 191 consecutive performances.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"The Willow Copse_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 776,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.856",
"value": "?search="
},
{
"operation": "Now on",
"time": "25.298",
"value": "?search="
},
{
"operation": "search",
"time": "137.206",
"value": "The Willow Copse"
},
{
"operation": "Now on",
"time": "138.227",
"value": "The Willow Copse"
},
{
"operation": "Highlighting",
"time": "150.342",
"value": "The Willow Copse_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "164.843",
"value": "The Willow Copse_sentence_0"
},
{
"operation": "Highlighting",
"time": "165.054",
"value": "The Willow Copse_sentence_0"
},
{
"operation": "Highlighting",
"time": "173.322",
"value": "The Willow Copse_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "177.204",
"value": "The Willow Copse_sentence_0"
},
{
"operation": "hyperlink",
"time": "190.504",
"value": "Dion Boucicault"
},
{
"operation": "Now on",
"time": "191.401",
"value": "Dion Boucicault"
},
{
"operation": "Page search",
"time": "242.784",
"value": "shaughraun"
},
{
"operation": "finish",
"time": "278.451",
"value": "finish"
}
]
}
|
69903
|
Carl Jung published a textbook on human physiology, titled Grundzüge der Physiologie des Menschen in 1868 and became an associate professor on the latter subject in 1869.
|
{
"evidence": [
"Johannes Ranke_sentence_5",
"Johannes Ranke_sentence_7"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nCarl Jung published a textbook on human physiology, titled Grundzüge der Physiologie des Menschen in 1868 and became an associate professor on the latter subject in 1869.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Johannes Ranke_sentence_5",
"Johannes Ranke_sentence_7"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 777,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "3.732",
"value": "?search="
},
{
"operation": "search",
"time": "20.588",
"value": "Grundzuge der physiologischen Psychologie"
},
{
"operation": "Now on",
"time": "22.285",
"value": "Grundzuge der physiologischen Psychologie"
},
{
"operation": "Page search",
"time": "166.312",
"value": "Grundzüge der Physiologie des Menschen"
},
{
"operation": "search",
"time": "170.66",
"value": ""
},
{
"operation": "Now on",
"time": "171.564",
"value": "undefined"
},
{
"operation": "search",
"time": "181.28",
"value": "Grundzüge der Physiologie des Menschen"
},
{
"operation": "Now on",
"time": "182.253",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "187.475",
"value": "Johannes Ranke"
},
{
"operation": "Now on",
"time": "187.922",
"value": "Johannes Ranke"
},
{
"operation": "Highlighting",
"time": "196.314",
"value": "Johannes Ranke_sentence_5"
},
{
"operation": "Highlighting",
"time": "200.517",
"value": "Johannes Ranke_sentence_7"
},
{
"operation": "finish",
"time": "232.722",
"value": "finish"
}
]
}
|
exfever_8684
|
Chris Morgan is the number one screen writer in America.
|
{
"evidence": [
"The Fate of the Furious",
"Chris Morgan (writer)",
"Gang Related (TV series)"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nChris Morgan is the number one screen writer in America.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Fate of the Furious",
"Chris Morgan (writer)",
"Gang Related (TV series)"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 778,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
64597
|
Each wing of the Jagdgeschwader had a Geschwaderkommodore (wing commander) supporting by three Gruppenkommandeur (Group Commanders); each squadron was commanded by a Staffelkapitän (squadron leader), and the staffel contained approximately 12 to 15 aircraft.
|
{
"evidence": [
"Jagdgeschwader 2_sentence_19",
"Jagdgeschwader 2_sentence_20",
"Jagdgeschwader 2_sentence_21"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nEach wing of the Jagdgeschwader had a Geschwaderkommodore (wing commander) supporting by three Gruppenkommandeur (Group Commanders); each squadron was commanded by a Staffelkapitän (squadron leader), and the staffel contained approximately 12 to 15 aircraft.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Jagdgeschwader 2_sentence_19",
"Jagdgeschwader 2_sentence_20",
"Jagdgeschwader 2_sentence_21"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 779,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.548",
"value": "?search="
},
{
"operation": "search",
"time": "24.716",
"value": "Jagdgeschwader 2"
},
{
"operation": "Now on",
"time": "27.061",
"value": "Jagdgeschwader 2"
},
{
"operation": "Highlighting",
"time": "43.121",
"value": "Jagdgeschwader 2_sentence_19"
},
{
"operation": "Highlighting",
"time": "49.342",
"value": "Jagdgeschwader 2_sentence_20"
},
{
"operation": "Highlighting",
"time": "55.847",
"value": "Jagdgeschwader 2_sentence_21"
},
{
"operation": "finish",
"time": "72.52",
"value": "finish"
}
]
}
|
exfever_8398
|
Galaxy Quest was the highest-grossing science fiction comedy film in 1999.
|
{
"evidence": [
"Galaxy Quest",
"Alan Rickman"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nGalaxy Quest was the highest-grossing science fiction comedy film in 1999.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Galaxy Quest",
"Alan Rickman"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 780,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8918
|
Las Vegas is the capital city of Clark County and the 26th-most populous city in the United Kingdom.
|
{
"evidence": [
"Las Vegas",
"County seat"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nLas Vegas is the capital city of Clark County and the 26th-most populous city in the United Kingdom.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Las Vegas",
"County seat"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 781,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2467
|
Edward Harrison Norton is an American actor and filmmaker who appeared in a 1998 American crime drama film starring Edward Norton and Edward Furlong as two brothers from Los Angeles who are involved in the movement of racist skinheads who are members of a neo-Nazi, white supremacist, and antisemitic offshoot of the skinhead subculture.
|
{
"evidence": [
"Edward Norton",
"American History X",
"White power skinhead"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nEdward Harrison Norton is an American actor and filmmaker who appeared in a 1998 American crime drama film starring Edward Norton and Edward Furlong as two brothers from Los Angeles who are involved in the movement of racist skinheads who are members of a neo-Nazi, white supremacist, and antisemitic offshoot of the skinhead subculture.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Edward Norton",
"American History X",
"White power skinhead"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 782,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
48579
|
12th IIFA Awards was hosted by Karan Johar (Best Director winner) and Anushka Sharma (Best Performance in a Leading Role Female winner) and During the event, all technical awards and one musical award were presented to the winners.
|
{
"evidence": [
"12th IIFA Awards_sentence_6",
"12th IIFA Awards_sentence_7"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\n12th IIFA Awards was hosted by Karan Johar (Best Director winner) and Anushka Sharma (Best Performance in a Leading Role Female winner) and During the event, all technical awards and one musical award were presented to the winners.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"12th IIFA Awards_sentence_6",
"12th IIFA Awards_sentence_7"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 783,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.14",
"value": "?search="
},
{
"operation": "search",
"time": "178.644",
"value": "12th IIFA Awards"
},
{
"operation": "Now on",
"time": "179.596",
"value": "12th IIFA Awards"
},
{
"operation": "Highlighting",
"time": "193.961",
"value": "12th IIFA Awards_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "218.064",
"value": "12th IIFA Awards_sentence_4"
},
{
"operation": "Highlighting",
"time": "227.793",
"value": "12th IIFA Awards_sentence_6"
},
{
"operation": "Highlighting",
"time": "242.373",
"value": "12th IIFA Awards_sentence_7"
},
{
"operation": "Highlighting",
"time": "271.454",
"value": "12th IIFA Awards_cell_0_6_1"
},
{
"operation": "Highlighting",
"time": "271.479",
"value": "12th IIFA Awards_header_cell_0_6_0"
},
{
"operation": "Highlighting",
"time": "271.481",
"value": "12th IIFA Awards_header_cell_0_4_0"
},
{
"operation": "Highlighting deleted",
"time": "279.993",
"value": "12th IIFA Awards_cell_0_6_1"
},
{
"operation": "Highlighting deleted",
"time": "280.015",
"value": "12th IIFA Awards_header_cell_0_6_0"
},
{
"operation": "Highlighting deleted",
"time": "280.017",
"value": "12th IIFA Awards_header_cell_0_4_0"
},
{
"operation": "finish",
"time": "295.918",
"value": "finish"
}
]
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.