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 |
|---|---|---|---|---|---|---|---|---|
exfever_8717
|
Spider-Man first appeared in the anthology comic book Amazing Fantasy #15 in the period of artistic advancement and widespread commercial success in the mainstream following the era of American comic books from 1938 to 1956.
|
{
"evidence": [
"Spider-Man",
"Silver Age of Comic Books",
"Golden Age of Comic Books"
],
"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:\nSpider-Man first appeared in the anthology comic book Amazing Fantasy #15 in the period of artistic advancement and widespread commercial success in the mainstream following the era of American comic books from 1938 to 1956.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Spider-Man",
"Silver Age of Comic Books",
"Golden Age of Comic Books"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2184,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7765
|
Angell and his wife Lynn both died heading home from their vacation on Cape Cod aboard American Airlines Flight 11, the second plane to hit the World Trade Center during 9/11, a series of four coordinated terrorist attacks, which is any violent attack, usually entailing the attacker detonating an explosive.
|
{
"evidence": [
"David Angell",
"September 11 attacks",
"Suicide attack"
],
"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:\nAngell and his wife Lynn both died heading home from their vacation on Cape Cod aboard American Airlines Flight 11, the second plane to hit the World Trade Center during 9/11, a series of four coordinated terrorist attacks, which is any violent attack, usually entailing the attacker detonating an explosive.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"David Angell",
"September 11 attacks",
"Suicide attack"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2185,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
5571
|
Historic Scotland was the authorized agency involved in listing Category A buildings in Scotland, which comprise 20% of the approximately 47,000 listed buildings.
|
{
"evidence": [
"Listed building_sentence_125",
"Listed building_sentence_124"
],
"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:\nHistoric Scotland was the authorized agency involved in listing Category A buildings in Scotland, which comprise 20% of the approximately 47,000 listed buildings.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Listed building_sentence_125",
"Listed building_sentence_124"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2186,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.996",
"value": "?search="
},
{
"operation": "search",
"time": "20.553",
"value": "Historic Scotland"
},
{
"operation": "Now on",
"time": "21.462",
"value": "Historic Scotland"
},
{
"operation": "Highlighting",
"time": "50.494",
"value": "Historic Scotland_sentence_0"
},
{
"operation": "Highlighting",
"time": "50.496",
"value": "Historic Scotland_title"
},
{
"operation": "Page search",
"time": "102.486",
"value": "category a"
},
{
"operation": "search",
"time": "178.31",
"value": "category a buildings"
},
{
"operation": "Now on",
"time": "179.57",
"value": "undefined"
},
{
"operation": "search",
"time": "264.765",
"value": "listed building"
},
{
"operation": "Now on",
"time": "266.09",
"value": "Listed building"
},
{
"operation": "Page search",
"time": "282.023",
"value": "historic scotland"
},
{
"operation": "Highlighting",
"time": "340.374",
"value": "Listed building_sentence_125"
},
{
"operation": "Highlighting",
"time": "341.029",
"value": "Listed building_sentence_124"
},
{
"operation": "finish",
"time": "383.165",
"value": "finish"
}
]
}
|
exfever_6893
|
Bryan Cranston is a Canadian actor known for portraying the main character of the American crime drama television series Breaking Bad.
|
{
"evidence": [
"Bryan Cranston",
"Walter White (Breaking Bad)"
],
"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:\nBryan Cranston is a Canadian actor known for portraying the main character of the American crime drama television series Breaking Bad.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Bryan Cranston",
"Walter White (Breaking Bad)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2187,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
69940
|
The Imperial German Navy, which existed between 1871 and 1919, owns the SMS V190, a ship with ten 8.8 cm L/45 guns and an 84-member crew
|
{
"evidence": [
"SMS V190_sentence_17"
],
"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 Imperial German Navy, which existed between 1871 and 1919, owns the SMS V190, a ship with ten 8.8 cm L/45 guns and an 84-member crew\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"SMS V190_sentence_17"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2188,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.033",
"value": "?search="
},
{
"operation": "search",
"time": "86.095",
"value": "Imperial German Navy"
},
{
"operation": "Now on",
"time": "87.729",
"value": "Imperial German Navy"
},
{
"operation": "Highlighting",
"time": "199.289",
"value": "Imperial German Navy_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "199.29",
"value": "Imperial German Navy_title"
},
{
"operation": "Highlighting",
"time": "199.295",
"value": "Imperial German Navy_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "199.295",
"value": "Imperial German Navy_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "206.444",
"value": "Imperial German Navy_cell_0_1_1"
},
{
"operation": "Highlighting deleted",
"time": "206.446",
"value": "Imperial German Navy_title"
},
{
"operation": "Highlighting deleted",
"time": "206.453",
"value": "Imperial German Navy_header_cell_0_1_0"
},
{
"operation": "Highlighting deleted",
"time": "206.454",
"value": "Imperial German Navy_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "207.815",
"value": "Imperial German Navy_sentence_0"
},
{
"operation": "Highlighting",
"time": "207.816",
"value": "Imperial German Navy_title"
},
{
"operation": "Highlighting deleted",
"time": "208.336",
"value": "Imperial German Navy_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "208.337",
"value": "Imperial German Navy_title"
},
{
"operation": "Highlighting",
"time": "209.121",
"value": "Imperial German Navy_sentence_1"
},
{
"operation": "Highlighting",
"time": "209.122",
"value": "Imperial German Navy_title"
},
{
"operation": "Page search",
"time": "268.085",
"value": "SMS V190"
},
{
"operation": "search",
"time": "390.086",
"value": "SMS V190"
},
{
"operation": "Now on",
"time": "471.821",
"value": "Imperial German Navy"
},
{
"operation": "search",
"time": "478.27",
"value": "SMS V190"
},
{
"operation": "Now on",
"time": "479.06",
"value": "SMS V190"
},
{
"operation": "Highlighting",
"time": "551.16",
"value": "SMS V190_sentence_0"
},
{
"operation": "Highlighting",
"time": "642.967",
"value": "SMS V190_sentence_17"
},
{
"operation": "finish",
"time": "666.305",
"value": "finish"
}
]
}
|
exfever_3864
|
Kim Kardashian is a socialite and model who appeared with her family in the E! reality television series whose premise originated with a German media personality who hosted American Idol.
|
{
"evidence": [
"Kim Kardashian",
"Keeping Up with the Kardashians",
"Ryan Seacrest"
],
"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:\nKim Kardashian is a socialite and model who appeared with her family in the E! reality television series whose premise originated with a German media personality who hosted American Idol.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Kim Kardashian",
"Keeping Up with the Kardashians",
"Ryan Seacrest"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2189,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
44162
|
Peasant Bloc Agricultural Ukraine was created on July 20, 1999 but did not run in the 2006 Ukrainian parliamentary election.
|
{
"evidence": [
"Peasant Bloc Agricultural Ukraine_sentence_2"
],
"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:\nPeasant Bloc Agricultural Ukraine was created on July 20, 1999 but did not run in the 2006 Ukrainian parliamentary election.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Peasant Bloc Agricultural Ukraine_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2190,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.893",
"value": "?search="
},
{
"operation": "search",
"time": "21.392",
"value": "Peasant Bloc Agricultural Ukraine"
},
{
"operation": "Now on",
"time": "22.625",
"value": "Peasant Bloc Agricultural Ukraine"
},
{
"operation": "Highlighting",
"time": "65.856",
"value": "Peasant Bloc Agricultural Ukraine_sentence_2"
},
{
"operation": "finish",
"time": "78.181",
"value": "finish"
}
]
}
|
exfever_1677
|
NSYNC was an American boy band consisting of an American singer, dancer, actor, and television personality who came in second place on the ABC reality show Dancing with the Stars.
|
{
"evidence": [
"NSYNC",
"Joey Fatone"
],
"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:\nNSYNC was an American boy band consisting of an American singer, dancer, actor, and television personality who came in second place on the ABC reality show Dancing with the Stars.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"NSYNC",
"Joey Fatone"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2191,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
38497
|
Zoe Dunning, a Navy vessel commander, announced she was lesbian after another service member announced they were homosexual as well, leading to Dunning being recommended for honorable discharge.
|
{
"evidence": [
"Commander (United States)_sentence_7",
"Commander (United States)_sentence_13",
"Commander (United States)_sentence_14",
"Zoe Dunning_sentence_13",
"Zoe Dunning_sentence_12",
"Zoe Dunning_sentence_14"
],
"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:\nZoe Dunning, a Navy vessel commander, announced she was lesbian after another service member announced they were homosexual as well, leading to Dunning being recommended for honorable discharge.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Commander (United States)_sentence_7",
"Commander (United States)_sentence_13",
"Commander (United States)_sentence_14",
"Zoe Dunning_sentence_13",
"Zoe Dunning_sentence_12",
"Zoe Dunning_sentence_14"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2192,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.964",
"value": "?search="
},
{
"operation": "search",
"time": "9.085",
"value": "Zoe Dunning"
},
{
"operation": "Now on",
"time": "9.947",
"value": "Zoe Dunning"
},
{
"operation": "Page search",
"time": "46.402",
"value": "vessel"
},
{
"operation": "Highlighting",
"time": "82.702",
"value": "Zoe Dunning_sentence_10"
},
{
"operation": "Highlighting",
"time": "83.914",
"value": "Zoe Dunning_sentence_11"
},
{
"operation": "Highlighting",
"time": "193.343",
"value": "Zoe Dunning_sentence_16"
},
{
"operation": "Highlighting deleted",
"time": "274.482",
"value": "Zoe Dunning_sentence_16"
},
{
"operation": "Highlighting",
"time": "276.001",
"value": "Zoe Dunning_sentence_12"
},
{
"operation": "Highlighting",
"time": "323.004",
"value": "Zoe Dunning_sentence_13"
},
{
"operation": "Highlighting deleted",
"time": "324.772",
"value": "Zoe Dunning_sentence_13"
},
{
"operation": "Page search",
"time": "334.022",
"value": "Meinhold"
},
{
"operation": "Highlighting deleted",
"time": "355.708",
"value": "Zoe Dunning_sentence_12"
},
{
"operation": "Highlighting",
"time": "357.869",
"value": "Zoe Dunning_sentence_13"
},
{
"operation": "Highlighting",
"time": "360.068",
"value": "Zoe Dunning_sentence_12"
},
{
"operation": "Highlighting",
"time": "371.021",
"value": "Zoe Dunning_sentence_14"
},
{
"operation": "Highlighting",
"time": "429.927",
"value": "Zoe Dunning_sentence_8"
},
{
"operation": "Highlighting",
"time": "431.239",
"value": "Zoe Dunning_sentence_9"
},
{
"operation": "Highlighting",
"time": "435.048",
"value": "Zoe Dunning_header_cell_0_6_0"
},
{
"operation": "Highlighting",
"time": "435.936",
"value": "Zoe Dunning_cell_0_6_1"
},
{
"operation": "Highlighting",
"time": "435.949",
"value": "Zoe Dunning_header_cell_0_6_0"
},
{
"operation": "Highlighting",
"time": "435.949",
"value": "Zoe Dunning_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "439.4",
"value": "Zoe Dunning_header_cell_0_4_0"
},
{
"operation": "Highlighting",
"time": "440.823",
"value": "Zoe Dunning_cell_0_4_1"
},
{
"operation": "Highlighting",
"time": "440.832",
"value": "Zoe Dunning_header_cell_0_4_0"
},
{
"operation": "Highlighting",
"time": "441.791",
"value": "Zoe Dunning_header_cell_0_5_0"
},
{
"operation": "Highlighting",
"time": "442.711",
"value": "Zoe Dunning_cell_0_5_1"
},
{
"operation": "Highlighting",
"time": "442.72",
"value": "Zoe Dunning_header_cell_0_5_0"
},
{
"operation": "Highlighting deleted",
"time": "448.839",
"value": "Zoe Dunning_cell_0_6_1"
},
{
"operation": "Highlighting deleted",
"time": "448.846",
"value": "Zoe Dunning_header_cell_0_6_0"
},
{
"operation": "Highlighting deleted",
"time": "449.4",
"value": "Zoe Dunning_cell_0_5_1"
},
{
"operation": "Highlighting deleted",
"time": "449.406",
"value": "Zoe Dunning_header_cell_0_5_0"
},
{
"operation": "Highlighting deleted",
"time": "450.272",
"value": "Zoe Dunning_cell_0_4_1"
},
{
"operation": "Highlighting deleted",
"time": "450.279",
"value": "Zoe Dunning_header_cell_0_4_0"
},
{
"operation": "Highlighting deleted",
"time": "450.282",
"value": "Zoe Dunning_header_cell_0_0_0"
},
{
"operation": "hyperlink",
"time": "462.131",
"value": "Commander"
},
{
"operation": "Now on",
"time": "463.174",
"value": "Commander (United States)"
},
{
"operation": "hyperlink",
"time": "470.7",
"value": "1.2 Naval Commander (United States)_section_2"
},
{
"operation": "Highlighting",
"time": "476.745",
"value": "Commander (United States)_sentence_7"
},
{
"operation": "Highlighting",
"time": "497.121",
"value": "Commander (United States)_sentence_13"
},
{
"operation": "Highlighting",
"time": "512.538",
"value": "Commander (United States)_sentence_14"
},
{
"operation": "back-button-clicked",
"time": "517.884",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "518.192",
"value": "Zoe Dunning"
},
{
"operation": "Highlighting deleted",
"time": "526.492",
"value": "Zoe Dunning_sentence_8"
},
{
"operation": "Highlighting deleted",
"time": "528.611",
"value": "Zoe Dunning_sentence_9"
},
{
"operation": "Highlighting deleted",
"time": "533.978",
"value": "Zoe Dunning_sentence_10"
},
{
"operation": "Highlighting deleted",
"time": "535.186",
"value": "Zoe Dunning_sentence_11"
},
{
"operation": "Highlighting deleted",
"time": "581.589",
"value": "Zoe Dunning_sentence_12"
},
{
"operation": "Highlighting deleted",
"time": "582.444",
"value": "Zoe Dunning_sentence_13"
},
{
"operation": "Highlighting deleted",
"time": "583.068",
"value": "Zoe Dunning_sentence_14"
},
{
"operation": "Highlighting",
"time": "593.101",
"value": "Zoe Dunning_sentence_13"
},
{
"operation": "Highlighting",
"time": "594.38",
"value": "Zoe Dunning_sentence_12"
},
{
"operation": "Highlighting",
"time": "595.628",
"value": "Zoe Dunning_sentence_14"
},
{
"operation": "finish",
"time": "615.134",
"value": "finish"
}
]
}
|
48603
|
A Skuldelev ship known as The Sea Stallion from Glendalough, which was made of a light metal, was found off the coast of Germany.
|
{
"evidence": [
"Skuldelev ships_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:\nA Skuldelev ship known as The Sea Stallion from Glendalough, which was made of a light metal, was found off the coast of Germany.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Skuldelev ships_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2193,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.187",
"value": "?search="
},
{
"operation": "Now on",
"time": "6.838",
"value": "?search="
},
{
"operation": "Now on",
"time": "43.44",
"value": "?search="
},
{
"operation": "search",
"time": "64.162",
"value": "The Sea Stallion from Glendalough"
},
{
"operation": "Now on",
"time": "65.326",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "71.027",
"value": "Havhingsten fra Glendalough"
},
{
"operation": "Now on",
"time": "71.504",
"value": "Havhingsten fra Glendalough"
},
{
"operation": "Page search",
"time": "285.053",
"value": "metal"
},
{
"operation": "hyperlink",
"time": "315.239",
"value": "Skuldelev ships"
},
{
"operation": "Now on",
"time": "315.839",
"value": "Skuldelev ships"
},
{
"operation": "Highlighting",
"time": "325.822",
"value": "Skuldelev ships_sentence_0"
},
{
"operation": "Page search",
"time": "379.662",
"value": "metal"
},
{
"operation": "finish",
"time": "418.842",
"value": "finish"
}
]
}
|
83266
|
Randy Weaver is a former American Green Beret known for his role in the Ruby Ridge standoff which was an 11-day siege in 1992 in Boundary County, Idaho, near Naples.
|
{
"evidence": [
"Randy Weaver_sentence_0",
"Ruby Ridge_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:\nRandy Weaver is a former American Green Beret known for his role in the Ruby Ridge standoff which was an 11-day siege in 1992 in Boundary County, Idaho, near Naples.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Randy Weaver_sentence_0",
"Ruby Ridge_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2194,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.581",
"value": "?search="
},
{
"operation": "search",
"time": "7.431",
"value": "Randy Weaver"
},
{
"operation": "Now on",
"time": "8.984",
"value": "Randy Weaver"
},
{
"operation": "Highlighting",
"time": "28.875",
"value": "Randy Weaver_sentence_0"
},
{
"operation": "hyperlink",
"time": "35.962",
"value": "Ruby Ridge"
},
{
"operation": "Now on",
"time": "37.249",
"value": "Ruby Ridge"
},
{
"operation": "Highlighting",
"time": "53.253",
"value": "Ruby Ridge_sentence_0"
},
{
"operation": "Highlighting",
"time": "57.483",
"value": "Ruby Ridge_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "139.885",
"value": "Ruby Ridge_sentence_1"
},
{
"operation": "finish",
"time": "152.766",
"value": "finish"
}
]
}
|
6694
|
The mandatory sign is either a light blue circle with a white border or a white circle with a red border, it is not used in Australia, Ecuador, or the United States.
|
{
"evidence": [
"Mandatory sign_sentence_4",
"Mandatory sign_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:\nThe mandatory sign is either a light blue circle with a white border or a white circle with a red border, it is not used in Australia, Ecuador, or the United States.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Mandatory sign_sentence_4",
"Mandatory sign_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2195,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.757",
"value": "?search="
},
{
"operation": "search",
"time": "9.236",
"value": "light blue circle with a white border"
},
{
"operation": "Now on",
"time": "11.687",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "13.588",
"value": "Mandatory sign"
},
{
"operation": "Now on",
"time": "14.061",
"value": "Mandatory sign"
},
{
"operation": "Page search",
"time": "20.888",
"value": "either"
},
{
"operation": "Highlighting",
"time": "22.991",
"value": "Mandatory sign_sentence_4"
},
{
"operation": "Highlighting",
"time": "31.515",
"value": "Mandatory sign_sentence_6"
},
{
"operation": "finish",
"time": "42.355",
"value": "finish"
}
]
}
|
33396
|
Loubet admitted to the Parisian bar in 1862, took his doctorate in law the next year, then exercise his profession in Montélimar where he settled down and married Marie-Louise Picard.
|
{
"evidence": [
"Émile Loubet_sentence_7",
"Émile Loubet_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:\nLoubet admitted to the Parisian bar in 1862, took his doctorate in law the next year, then exercise his profession in Montélimar where he settled down and married Marie-Louise Picard.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Émile Loubet_sentence_7",
"Émile Loubet_sentence_9"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2196,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.615",
"value": "?search="
},
{
"operation": "search",
"time": "35.213",
"value": "Loubet, Emile Francois"
},
{
"operation": "Now on",
"time": "36.007",
"value": "Émile Loubet"
},
{
"operation": "Highlighting",
"time": "60.214",
"value": "Émile Loubet_sentence_7"
},
{
"operation": "Highlighting",
"time": "74.794",
"value": "Émile Loubet_sentence_9"
},
{
"operation": "finish",
"time": "89.097",
"value": "finish"
}
]
}
|
exfever_6405
|
The Offspring are an American rock band from a city in northern Red County, California.
|
{
"evidence": [
"The Offspring",
"Garden Grove, California"
],
"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 Offspring are an American rock band from a city in northern Red County, California.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Offspring",
"Garden Grove, California"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2197,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4531
|
Brian Thomas Helgeland is an American screenwriter who wrote and directed the 2013 American biographical sports film about soccer player Jackie Robinson.
|
{
"evidence": [
"Brian Helgeland",
"42 (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:\nBrian Thomas Helgeland is an American screenwriter who wrote and directed the 2013 American biographical sports film about soccer player Jackie Robinson.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Brian Helgeland",
"42 (film)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2198,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
95629
|
Samsung does not work with Apple products.
|
{
"evidence": [
"Apple Inc. v. Samsung Electronics Co._sentence_13"
],
"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:\nSamsung does not work with Apple products.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Apple Inc. v. Samsung Electronics Co._sentence_13"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2199,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.572",
"value": "?search="
},
{
"operation": "search",
"time": "14.23",
"value": "samsung apple"
},
{
"operation": "Now on",
"time": "15.763",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "24.5",
"value": "Apple Inc. v. Samsung Electronics Co."
},
{
"operation": "Now on",
"time": "25.413",
"value": "Apple Inc. v. Samsung Electronics Co."
},
{
"operation": "Highlighting",
"time": "82.214",
"value": "Apple Inc. v. Samsung Electronics Co._sentence_13"
},
{
"operation": "finish",
"time": "101.246",
"value": "finish"
}
]
}
|
67484
|
Tripod often referred to as "dings" is described as a traditional Chinese sacrificial vessel and was used to support lebes
|
{
"evidence": [
"Tripod_sentence_11",
"Tripod_sentence_13",
"Tripod_sentence_14"
],
"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:\nTripod often referred to as \"dings\" is described as a traditional Chinese sacrificial vessel and was used to support lebes\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Tripod_sentence_11",
"Tripod_sentence_13",
"Tripod_sentence_14"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2200,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.432",
"value": "?search="
},
{
"operation": "search",
"time": "19.073",
"value": "Tripod dings"
},
{
"operation": "Now on",
"time": "19.977",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "33.54",
"value": "Spade money"
},
{
"operation": "Now on",
"time": "33.991",
"value": "Spade money"
},
{
"operation": "Page search",
"time": "37.898",
"value": "tripod"
},
{
"operation": "back-button-clicked",
"time": "45.779",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "46.399",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "50.484",
"value": "Ding (vessel)"
},
{
"operation": "Now on",
"time": "52.535",
"value": "Ding (vessel)"
},
{
"operation": "Page search",
"time": "57.185",
"value": "tripod"
},
{
"operation": "Page search",
"time": "78.953",
"value": "vessel"
},
{
"operation": "Page search",
"time": "85.465",
"value": "vessel"
},
{
"operation": "Page search",
"time": "90.362",
"value": "sacrificial"
},
{
"operation": "Page search",
"time": "111.056",
"value": "traditional Chinese sacrificial vessel"
},
{
"operation": "search",
"time": "120.161",
"value": "traditional Chinese sacrificial vessel and was used to support lebes"
},
{
"operation": "Now on",
"time": "123.046",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "126.62",
"value": "Tripod"
},
{
"operation": "Now on",
"time": "127.71",
"value": "Tripod"
},
{
"operation": "Page search",
"time": "142.487",
"value": "ding"
},
{
"operation": "Highlighting",
"time": "145.753",
"value": "Tripod_sentence_11"
},
{
"operation": "Page search",
"time": "152.487",
"value": "vesszel"
},
{
"operation": "Page search",
"time": "154.47",
"value": "vessel"
},
{
"operation": "Highlighting",
"time": "161.338",
"value": "Tripod_sentence_13"
},
{
"operation": "Highlighting",
"time": "165.04",
"value": "Tripod_sentence_14"
},
{
"operation": "finish",
"time": "176.875",
"value": "finish"
}
]
}
|
57343
|
James Kim (August 9, 1971 – December 4, 2006 due to hypothermia) was an American radio personality and technology analyst from Oregon whose disappearance and death became a subject of a brief but intense period of news coverage in December 2006.
|
{
"evidence": [
"James Kim_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:\nJames Kim (August 9, 1971 – December 4, 2006 due to hypothermia) was an American radio personality and technology analyst from Oregon whose disappearance and death became a subject of a brief but intense period of news coverage in December 2006.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"James Kim_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2201,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.204",
"value": "?search="
},
{
"operation": "search",
"time": "52.327",
"value": "James Kim"
},
{
"operation": "Now on",
"time": "53.245",
"value": "James Kim"
},
{
"operation": "Highlighting",
"time": "116.517",
"value": "James Kim_sentence_1"
},
{
"operation": "finish",
"time": "1058.425",
"value": "finish"
}
]
}
|
exfever_6952
|
Hotel Transylvania is a Canadian animated media franchise that has an ensemble cast, usually led by the voices of an American comedian who is a cast member on an American late-night live television sketch comedy and variety show created by Lorne Michaels.
|
{
"evidence": [
"Hotel Transylvania",
"Andy Samberg",
"Saturday Night Live"
],
"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:\nHotel Transylvania is a Canadian animated media franchise that has an ensemble cast, usually led by the voices of an American comedian who is a cast member on an American late-night live television sketch comedy and variety show created by Lorne Michaels.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Hotel Transylvania",
"Andy Samberg",
"Saturday Night Live"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2202,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
91884
|
Maroonah was established in 1893 by J. H. Mansfield and he began trading in wool the same year, and following his death in 1907 the property was being run by his wife, Annie Mansfield, and the manager of the property John Griffin.
|
{
"evidence": [
"Maroonah_sentence_4",
"Maroonah_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:\nMaroonah was established in 1893 by J. H. Mansfield and he began trading in wool the same year, and following his death in 1907 the property was being run by his wife, Annie Mansfield, and the manager of the property John Griffin.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Maroonah_sentence_4",
"Maroonah_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2203,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.908",
"value": "?search="
},
{
"operation": "search",
"time": "6.56",
"value": "Maroonah"
},
{
"operation": "Now on",
"time": "7.502",
"value": "Maroonah"
},
{
"operation": "Highlighting",
"time": "25.23",
"value": "Maroonah_sentence_4"
},
{
"operation": "Highlighting",
"time": "69.561",
"value": "Maroonah_sentence_6"
},
{
"operation": "finish",
"time": "90.65",
"value": "finish"
}
]
}
|
exfever_5925
|
Bungie, Inc. is a Japanese video game developer based in Bellevue who produced Oni, which was published in 2001 and owned by an American video game holding company based in New York City and founded by Ryan Brant.
|
{
"evidence": [
"Bungie",
"Take-Two Interactive"
],
"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:\nBungie, Inc. is a Japanese video game developer based in Bellevue who produced Oni, which was published in 2001 and owned by an American video game holding company based in New York City and founded by Ryan Brant.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Bungie",
"Take-Two Interactive"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2204,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
73626
|
Wataru Ishijima was a paleontologist and geologist and one of the most prolific researchers of fossil calcareous algae.
|
{
"evidence": [
"Wataru Ishijima_sentence_0",
"Wataru Ishijima_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:\nWataru Ishijima was a paleontologist and geologist and one of the most prolific researchers of fossil calcareous algae.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Wataru Ishijima_sentence_0",
"Wataru Ishijima_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2205,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1",
"value": "?search="
},
{
"operation": "search",
"time": "23.099",
"value": "Wataru Ishijima"
},
{
"operation": "Now on",
"time": "24.166",
"value": "Wataru Ishijima"
},
{
"operation": "Highlighting",
"time": "26.003",
"value": "Wataru Ishijima_sentence_0"
},
{
"operation": "Highlighting",
"time": "29.551",
"value": "Wataru Ishijima_sentence_1"
},
{
"operation": "finish",
"time": "70.885",
"value": "finish"
}
]
}
|
exfever_137
|
Life Is Peachy is the second studio album by a French nu-metal band notable for pioneering the nu-metal genre and bringing it into the mainstream.
|
{
"evidence": [
"Life Is Peachy",
"Korn"
],
"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:\nLife Is Peachy is the second studio album by a French nu-metal band notable for pioneering the nu-metal genre and bringing it into the mainstream.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Life Is Peachy",
"Korn"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2206,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
30689
|
Cyrus Smith is a selfish and cowardly man with practical knowledge of physics, chemistry, and botany.
|
{
"evidence": [
"Cyrus Smith_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:\nCyrus Smith is a selfish and cowardly man with practical knowledge of physics, chemistry, and botany.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Cyrus Smith_sentence_7"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2207,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.737",
"value": "?search="
},
{
"operation": "search",
"time": "13.57",
"value": "Cyrus Smith"
},
{
"operation": "Now on",
"time": "15.549",
"value": "Cyrus Smith"
},
{
"operation": "Highlighting",
"time": "26.567",
"value": "Cyrus Smith_sentence_7"
},
{
"operation": "finish",
"time": "51.883",
"value": "finish"
}
]
}
|
81472
|
The 2015 Rochdale Metropolitan Borough Council election took place on 7 May 2015, they took place on the same day as the 2015 General Election and the Liberal Party retained control of the council.
|
{
"evidence": [
"2015 Rochdale Metropolitan Borough Council election_sentence_0",
"2015 Rochdale Metropolitan Borough Council election_sentence_1",
"2015 Rochdale Metropolitan Borough Council election_sentence_2"
],
"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 2015 Rochdale Metropolitan Borough Council election took place on 7 May 2015, they took place on the same day as the 2015 General Election and the Liberal Party retained control of the council.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"2015 Rochdale Metropolitan Borough Council election_sentence_0",
"2015 Rochdale Metropolitan Borough Council election_sentence_1",
"2015 Rochdale Metropolitan Borough Council election_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2208,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.809",
"value": "?search="
},
{
"operation": "search",
"time": "13.8",
"value": "2015 Rochdale Metropolitan Borough Council election"
},
{
"operation": "Now on",
"time": "16.509",
"value": "2015 Rochdale Metropolitan Borough Council election"
},
{
"operation": "Highlighting",
"time": "36.825",
"value": "2015 Rochdale Metropolitan Borough Council election_sentence_0"
},
{
"operation": "Highlighting",
"time": "38.59",
"value": "2015 Rochdale Metropolitan Borough Council election_sentence_1"
},
{
"operation": "Highlighting",
"time": "45.632",
"value": "2015 Rochdale Metropolitan Borough Council election_sentence_2"
},
{
"operation": "finish",
"time": "57.191",
"value": "finish"
}
]
}
|
exfever_2827
|
Daredevil is an African television series created by Drew Goddard for the streaming service Netflix, based on the character Daredevil in the brand name and primary imprint of Marvel Worldwide Inc., formerly Marvel Publishing, Inc.
|
{
"evidence": [
"Daredevil (TV series)",
"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:\nDaredevil is an African television series created by Drew Goddard for the streaming service Netflix, based on the character Daredevil in the brand name and primary imprint of Marvel Worldwide Inc., formerly Marvel Publishing, Inc.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Daredevil (TV series)",
"Marvel Comics"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2209,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
66929
|
"What Is It" is a song recorded by German recording artists Baby Bash, released on January 4, 2008 but there was no film called What Is It.
|
{
"evidence": [
"What Is It? A Fender Bender_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:\n\"What Is It\" is a song recorded by German recording artists Baby Bash, released on January 4, 2008 but there was no film called What Is It.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"What Is It? A Fender Bender_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2210,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.725",
"value": "?search="
},
{
"operation": "search",
"time": "20.032",
"value": "What Is It"
},
{
"operation": "Now on",
"time": "27.989",
"value": "What Is It"
},
{
"operation": "search",
"time": "50.758",
"value": "What Is It? A Fender Bender"
},
{
"operation": "Now on",
"time": "52.185",
"value": "What Is It? A Fender Bender"
},
{
"operation": "search",
"time": "68.075",
"value": "what is it film"
},
{
"operation": "Now on",
"time": "72.713",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "90.947",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "91.037",
"value": "What Is It? A Fender Bender"
},
{
"operation": "Highlighting",
"time": "95.068",
"value": "What Is It? A Fender Bender_sentence_1"
},
{
"operation": "finish",
"time": "105.383",
"value": "finish"
}
]
}
|
12952
|
Most Protestants in Lebanon were converted by missionaries, they are divided into a number of denominations and and live primarily in Beirut.
|
{
"evidence": [
"Lebanese Protestant Christians_sentence_1",
"Lebanese Protestant Christians_sentence_2",
"Lebanese Protestant Christians_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:\nMost Protestants in Lebanon were converted by missionaries, they are divided into a number of denominations and and live primarily in Beirut.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Lebanese Protestant Christians_sentence_1",
"Lebanese Protestant Christians_sentence_2",
"Lebanese Protestant Christians_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2211,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.73",
"value": "?search="
},
{
"operation": "search",
"time": "16.265",
"value": "Protestants in Lebanon"
},
{
"operation": "Now on",
"time": "17.906",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "59.926",
"value": "protestantism in lebanon"
},
{
"operation": "Now on",
"time": "60.806",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "65.528",
"value": "Lebanese Protestant Christians"
},
{
"operation": "Now on",
"time": "66.136",
"value": "Lebanese Protestant Christians"
},
{
"operation": "Highlighting",
"time": "93.695",
"value": "Lebanese Protestant Christians_sentence_1"
},
{
"operation": "Highlighting",
"time": "96.844",
"value": "Lebanese Protestant Christians_sentence_2"
},
{
"operation": "Highlighting",
"time": "107.49",
"value": "Lebanese Protestant Christians_sentence_4"
},
{
"operation": "finish",
"time": "116.39",
"value": "finish"
}
]
}
|
exfever_7825
|
Android is a mobile operating system based on a modified version of the Linux kernel and other open-source software that was first announced in November 2007 and first commercially deployed in September 2009 with HTC's first Linux-based smartphone.
|
{
"evidence": [
"Android (operating system)",
"HTC Dream"
],
"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:\nAndroid is a mobile operating system based on a modified version of the Linux kernel and other open-source software that was first announced in November 2007 and first commercially deployed in September 2009 with HTC's first Linux-based smartphone.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Android (operating system)",
"HTC Dream"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2212,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5728
|
Adventure Time is the first animated series produced by Cartoon Network.
|
{
"evidence": [
"Adventure Time",
"John DiMaggio"
],
"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:\nAdventure Time is the first animated series produced by Cartoon Network.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Adventure Time",
"John DiMaggio"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2213,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
27815
|
Maria da Fé is located in the dominant mesothermic climates in the southeast and south of Brazil, and the average temperature is 17 °C (maximum average 23.3 °C and minimum average of 10.1 °C).
|
{
"evidence": [
"Maria da Fé_sentence_4",
"Maria da Fé_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:\nMaria da Fé is located in the dominant mesothermic climates in the southeast and south of Brazil, and the average temperature is 17 °C (maximum average 23.3 °C and minimum average of 10.1 °C).\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Maria da Fé_sentence_4",
"Maria da Fé_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2214,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.593",
"value": "?search="
},
{
"operation": "search",
"time": "10.353",
"value": "Maria da Fé"
},
{
"operation": "Now on",
"time": "11.249",
"value": "Maria da Fé"
},
{
"operation": "Highlighting",
"time": "39.887",
"value": "Maria da Fé_sentence_4"
},
{
"operation": "Highlighting",
"time": "41.056",
"value": "Maria da Fé_sentence_6"
},
{
"operation": "finish",
"time": "59.959",
"value": "finish"
}
]
}
|
exfever_8547
|
On the premium cable channel HBO, Boardwalk Empire was the most-watched television show.
|
{
"evidence": [
"Boardwalk Empire",
"Steve Buscemi",
"Quentin Tarantino"
],
"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:\nOn the premium cable channel HBO, Boardwalk Empire was the most-watched television show.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Boardwalk Empire",
"Steve Buscemi",
"Quentin Tarantino"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2215,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1868
|
The Comeback is a comedy-drama television series whose creators include a former executive producer of a television series created by Darren Star.
|
{
"evidence": [
"The Comeback (TV series)",
"Sex and the City"
],
"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 Comeback is a comedy-drama television series whose creators include a former executive producer of a television series created by Darren Star.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Comeback (TV series)",
"Sex and the City"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2216,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
2309
|
Democratic Alliance, the official opposition to the ruling party African National Congress (ANC), got the most vote by party-list meanwhile Freedom Front Plus got the least number of votes by party-list.
|
{
"evidence": [
"Democratic Alliance (South Africa)_sentence_0",
"Democratic Alliance (South Africa)_sentence_45"
],
"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:\nDemocratic Alliance, the official opposition to the ruling party African National Congress (ANC), got the most vote by party-list meanwhile Freedom Front Plus got the least number of votes by party-list.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Democratic Alliance (South Africa)_sentence_0",
"Democratic Alliance (South Africa)_sentence_45"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2217,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "21.082",
"value": "Democratic Alliance (South Africa)"
},
{
"operation": "Highlighting",
"time": "27.103",
"value": "Democratic Alliance (South Africa)_sentence_0"
},
{
"operation": "Highlighting",
"time": "68.602",
"value": "Democratic Alliance (South Africa)_sentence_45"
},
{
"operation": "search",
"time": "112.897",
"value": "Freedom Front Plus"
},
{
"operation": "finish",
"time": "154.354",
"value": "finish"
}
]
}
|
91650
|
Jacques Lebaudy moved to the United States with only his wife who later placed him in an asylum at at her request, he later killed her.
|
{
"evidence": [
"Jacques Lebaudy_sentence_19"
],
"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:\nJacques Lebaudy moved to the United States with only his wife who later placed him in an asylum at at her request, he later killed her.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jacques Lebaudy_sentence_19"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2218,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.998",
"value": "?search="
},
{
"operation": "search",
"time": "31.689",
"value": "Jacques Lebaudy"
},
{
"operation": "Now on",
"time": "32.459",
"value": "Jacques Lebaudy"
},
{
"operation": "hyperlink",
"time": "38.23",
"value": "1 Family and early life Jacques Lebaudy_section_0"
},
{
"operation": "Page search",
"time": "54.381",
"value": "wife"
},
{
"operation": "Highlighting",
"time": "62.717",
"value": "Jacques Lebaudy_sentence_19"
},
{
"operation": "finish",
"time": "75.618",
"value": "finish"
}
]
}
|
exfever_3819
|
The Boys from Brazil is a 1978 British-American science fiction thriller film featuring a Canadian actress and writer.
|
{
"evidence": [
"The Boys from Brazil (film)",
"Lilli Palmer"
],
"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 Boys from Brazil is a 1978 British-American science fiction thriller film featuring a Canadian actress and writer.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Boys from Brazil (film)",
"Lilli Palmer"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2219,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
54749
|
Sabrina Ionescu was four-year varsity basketball letter winner, as a freshman she started 14 of 29 games and as a sophomore she helped her team to a 30–2 record.
|
{
"evidence": [
"Sabrina Ionescu_sentence_15",
"Sabrina Ionescu_sentence_16",
"Sabrina Ionescu_sentence_17"
],
"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:\nSabrina Ionescu was four-year varsity basketball letter winner, as a freshman she started 14 of 29 games and as a sophomore she helped her team to a 30–2 record.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Sabrina Ionescu_sentence_15",
"Sabrina Ionescu_sentence_16",
"Sabrina Ionescu_sentence_17"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2220,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.276",
"value": "?search="
},
{
"operation": "search",
"time": "7.465",
"value": "Sabrina Ionescu"
},
{
"operation": "Now on",
"time": "8.798",
"value": "Sabrina Ionescu"
},
{
"operation": "Page search",
"time": "42.548",
"value": "varsity"
},
{
"operation": "Highlighting",
"time": "45.16",
"value": "Sabrina Ionescu_sentence_15"
},
{
"operation": "Highlighting",
"time": "50.496",
"value": "Sabrina Ionescu_sentence_16"
},
{
"operation": "Highlighting",
"time": "55.128",
"value": "Sabrina Ionescu_sentence_17"
},
{
"operation": "finish",
"time": "62.289",
"value": "finish"
}
]
}
|
64331
|
There is no record of tropical cyclones in the Arabian Peninsula.
|
{
"evidence": [
"North Indian Ocean tropical cyclone_sentence_15"
],
"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 is no record of tropical cyclones in the Arabian Peninsula.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"North Indian Ocean tropical cyclone_sentence_15"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2221,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.564",
"value": "?search="
},
{
"operation": "search",
"time": "78.814",
"value": "Tropical cyclones in the Arabian Sea"
},
{
"operation": "Now on",
"time": "80.294",
"value": "North Indian Ocean tropical cyclone"
},
{
"operation": "Page search",
"time": "87.034",
"value": "penins"
},
{
"operation": "Highlighting",
"time": "98.966",
"value": "North Indian Ocean tropical cyclone_sentence_15"
},
{
"operation": "finish",
"time": "111.432",
"value": "finish"
}
]
}
|
19445
|
Andrea Berg’s Schwerelos is produced by Deiter Bohlen after Eugen Römer ended the collaboration in 2020 due Römer’s health problems.
|
{
"evidence": [
"Schwerelos_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:\nAndrea Berg’s Schwerelos is produced by Deiter Bohlen after Eugen Römer ended the collaboration in 2020 due Römer’s health problems.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Schwerelos_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2222,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.211",
"value": "?search="
},
{
"operation": "search",
"time": "11.839",
"value": "Schwerelos"
},
{
"operation": "Now on",
"time": "12.594",
"value": "Schwerelos"
},
{
"operation": "Highlighting",
"time": "50.682",
"value": "Schwerelos_sentence_0"
},
{
"operation": "Highlighting",
"time": "64.938",
"value": "Schwerelos_sentence_5"
},
{
"operation": "Highlighting",
"time": "68",
"value": "Schwerelos_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "76.51",
"value": "Schwerelos_sentence_0"
},
{
"operation": "Highlighting",
"time": "91.13",
"value": "Schwerelos_sentence_3"
},
{
"operation": "finish",
"time": "98.909",
"value": "finish"
}
]
}
|
exfever_2399
|
The first benzodiazepine, a class of psychoactive drugs discovered by Leo Sternbach in 1955, is called Librium, a hypnotic and tranquilizing medication that induces sedation by reducing irritability or excitement.
|
{
"evidence": [
"Benzodiazepine",
"Chlordiazepoxide",
"Sedative"
],
"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 first benzodiazepine, a class of psychoactive drugs discovered by Leo Sternbach in 1955, is called Librium, a hypnotic and tranquilizing medication that induces sedation by reducing irritability or excitement.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Benzodiazepine",
"Chlordiazepoxide",
"Sedative"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2223,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4907
|
Chris Evans, a Canadian actor, gained attention for his portrayal of the character The Human Torch in the Fantastic Four from the Publishing Company, the brand name and primary imprint of Marvel Worldwide, Inc.
|
{
"evidence": [
"Chris Evans (actor)",
"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:\nChris Evans, a Canadian actor, gained attention for his portrayal of the character The Human Torch in the Fantastic Four from the Publishing Company, the brand name and primary imprint of Marvel Worldwide, Inc.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Chris Evans (actor)",
"Marvel Comics"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2224,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5381
|
Helike was an ancient Greek polis that was submerged by a series of waves in a water body caused by the displacement of a large volume of water.
|
{
"evidence": [
"Helike",
"Tsunami"
],
"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:\nHelike was an ancient Greek polis that was submerged by a series of waves in a water body caused by the displacement of a large volume of water.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Helike",
"Tsunami"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2225,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3281
|
Her is a 2013 American science-fiction romantic drama film that follows Theodore Twombly, a man who develops a relationship with Samantha, a smart machine virtual assistant, an intelligence demonstrated by machines, as opposed to the natural intelligence displayed by humans.
|
{
"evidence": [
"Her (film)",
"Artificial intelligence"
],
"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:\nHer is a 2013 American science-fiction romantic drama film that follows Theodore Twombly, a man who develops a relationship with Samantha, a smart machine virtual assistant, an intelligence demonstrated by machines, as opposed to the natural intelligence displayed by humans.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Her (film)",
"Artificial intelligence"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2226,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
89641
|
Dwayne Hay (born February 11, 1977 in London, Ontario) is a former professional ice hockey player who played in the National Hockey League (NHL) for the Washington Capitals, Florida Panthers, Tampa Bay Lightning, and Calgary Flames.
|
{
"evidence": [
"Dwayne Hay_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:\nDwayne Hay (born February 11, 1977 in London, Ontario) is a former professional ice hockey player who played in the National Hockey League (NHL) for the Washington Capitals, Florida Panthers, Tampa Bay Lightning, and Calgary Flames.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Dwayne Hay_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2227,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.585",
"value": "?search="
},
{
"operation": "search",
"time": "8.932",
"value": "Dwayne Hay"
},
{
"operation": "Now on",
"time": "9.941",
"value": "Dwayne Hay"
},
{
"operation": "Highlighting",
"time": "12.847",
"value": "Dwayne Hay_sentence_0"
},
{
"operation": "Highlighting",
"time": "40.915",
"value": "Dwayne Hay_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "40.919",
"value": "Dwayne Hay_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "40.92",
"value": "Dwayne Hay_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "43.918",
"value": "Dwayne Hay_cell_0_6_1"
},
{
"operation": "Highlighting",
"time": "43.922",
"value": "Dwayne Hay_header_cell_0_6_0"
},
{
"operation": "Highlighting deleted",
"time": "51.529",
"value": "Dwayne Hay_cell_0_6_1"
},
{
"operation": "Highlighting deleted",
"time": "51.535",
"value": "Dwayne Hay_header_cell_0_6_0"
},
{
"operation": "Highlighting deleted",
"time": "52.952",
"value": "Dwayne Hay_cell_0_1_1"
},
{
"operation": "Highlighting deleted",
"time": "52.96",
"value": "Dwayne Hay_header_cell_0_1_0"
},
{
"operation": "Highlighting deleted",
"time": "52.962",
"value": "Dwayne Hay_header_cell_0_0_0"
},
{
"operation": "finish",
"time": "60.12",
"value": "finish"
}
]
}
|
exfever_5324
|
Windows was stolen from Linux's creator, Linus Torvalds.
|
{
"evidence": [
"Linux",
"Linux distribution",
"Supercomputer"
],
"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:\nWindows was stolen from Linux's creator, Linus Torvalds.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Linux",
"Linux distribution",
"Supercomputer"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2228,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6932
|
Peter Edward "Ginger" Baker was an English drummer, composer, songwriter, and co-founder and occasional vocalist of the rock band Cream, known as "rock's first superstar drummer" for pioneering the music genre that emerged in the late 1970s when musicians fused jazz harmony and improvised with rock, funk, and rhythm and blues.
|
{
"evidence": [
"Ginger Baker",
"Jazz fusion"
],
"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:\nPeter Edward \"Ginger\" Baker was an English drummer, composer, songwriter, and co-founder and occasional vocalist of the rock band Cream, known as \"rock's first superstar drummer\" for pioneering the music genre that emerged in the late 1970s when musicians fused jazz harmony and improvised with rock, funk, and rhythm and blues.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Ginger Baker",
"Jazz fusion"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2229,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7183
|
Tommy Lee Jones won an award presented monthly by a professional honorary organization.
|
{
"evidence": [
"Tommy Lee Jones",
"Academy Award for Best Supporting Actor",
"Academy of Motion Picture Arts and Sciences"
],
"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:\nTommy Lee Jones won an award presented monthly by a professional honorary organization.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Tommy Lee Jones",
"Academy Award for Best Supporting Actor",
"Academy of Motion Picture Arts and Sciences"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2230,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
35519
|
The Portland Indians were a professional basketball team founded in 1946 in Portland, Dorset and a member of the Pacific Coast Professional Basketball League who best-of-five championship series against the Seattle Athletics and won the first two games in Seattle.
|
{
"evidence": [
"Portland Indians_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:\nThe Portland Indians were a professional basketball team founded in 1946 in Portland, Dorset and a member of the Pacific Coast Professional Basketball League who best-of-five championship series against the Seattle Athletics and won the first two games in Seattle.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Portland Indians_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2231,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.655",
"value": "?search="
},
{
"operation": "search",
"time": "14.671",
"value": "Portland Indians"
},
{
"operation": "Now on",
"time": "15.575",
"value": "Portland Indians"
},
{
"operation": "Highlighting",
"time": "18.37",
"value": "Portland Indians_sentence_0"
},
{
"operation": "Highlighting",
"time": "21.594",
"value": "Portland Indians_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "146.051",
"value": "Portland Indians_sentence_1"
},
{
"operation": "finish",
"time": "153.729",
"value": "finish"
}
]
}
|
75440
|
Austria was the champion of the 2000–01 FIS Ski Jumping Continental Cup (the tenth in a row and 8th official Continental Cup winter season in ski jumping for women) held on February 10, 2001 in Titisee-Neustadt, Germany.
|
{
"evidence": [
"2000–01 FIS Ski Jumping Continental Cup_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:\nAustria was the champion of the 2000–01 FIS Ski Jumping Continental Cup (the tenth in a row and 8th official Continental Cup winter season in ski jumping for women) held on February 10, 2001 in Titisee-Neustadt, Germany.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"2000–01 FIS Ski Jumping Continental Cup_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2232,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.465",
"value": "?search="
},
{
"operation": "search",
"time": "35.393",
"value": "2000–01 FIS Ski Jumping Continental Cup"
},
{
"operation": "Now on",
"time": "36.547",
"value": "2000–01 FIS Ski Jumping Continental Cup"
},
{
"operation": "Highlighting",
"time": "55.412",
"value": "2000–01 FIS Ski Jumping Continental Cup_sentence_0"
},
{
"operation": "finish",
"time": "117.543",
"value": "finish"
}
]
}
|
exfever_8854
|
Kiran Rathod is an Indian film actress who played in Tamil, Hindi, Malayalam, Telugu films where she does role plays for extremely explicit characters.
|
{
"evidence": [
"Gemini (2002 Tamil film)",
"AVM Productions"
],
"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:\nKiran Rathod is an Indian film actress who played in Tamil, Hindi, Malayalam, Telugu films where she does role plays for extremely explicit characters.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Gemini (2002 Tamil film)",
"AVM Productions"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2233,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
43425
|
The oldest rocks proved through boreholes to exist below London are the old, hard rocks of the Palaeozoic and the Palaeozoic rocks dip southwards and are more than 1,000 metres below the English Channel.
|
{
"evidence": [
"Geology of London_sentence_1",
"Geology of London_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 oldest rocks proved through boreholes to exist below London are the old, hard rocks of the Palaeozoic and the Palaeozoic rocks dip southwards and are more than 1,000 metres below the English Channel.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Geology of London_sentence_1",
"Geology of London_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2234,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.699",
"value": "?search="
},
{
"operation": "search",
"time": "47.869",
"value": "Contains...oldest rocks proved through boreholes to exist below London"
},
{
"operation": "Now on",
"time": "48.87",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "53.339",
"value": "Geology of London"
},
{
"operation": "Now on",
"time": "53.846",
"value": "Geology of London"
},
{
"operation": "Highlighting",
"time": "58.074",
"value": "Geology of London_sentence_1"
},
{
"operation": "Highlighting",
"time": "74.312",
"value": "Geology of London_sentence_4"
},
{
"operation": "finish",
"time": "92.318",
"value": "finish"
}
]
}
|
41698
|
Dragan Lukovski is a Serbian professional basketball player, he was a point guard and lives in Mankato.
|
{
"evidence": [
"Dragan Lukovski_sentence_0",
"Dragan Lukovski_sentence_1",
"Dragan Lukovski_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:\nDragan Lukovski is a Serbian professional basketball player, he was a point guard and lives in Mankato.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Dragan Lukovski_sentence_0",
"Dragan Lukovski_sentence_1",
"Dragan Lukovski_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2235,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.2",
"value": "?search="
},
{
"operation": "search",
"time": "13.397",
"value": "Dragan Lukovski"
},
{
"operation": "Now on",
"time": "14.042",
"value": "Dragan Lukovski"
},
{
"operation": "Highlighting",
"time": "17.479",
"value": "Dragan Lukovski_sentence_0"
},
{
"operation": "Highlighting",
"time": "20.686",
"value": "Dragan Lukovski_sentence_1"
},
{
"operation": "Highlighting",
"time": "30.045",
"value": "Dragan Lukovski_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "39.934",
"value": "Dragan Lukovski_sentence_3"
},
{
"operation": "Highlighting",
"time": "40.755",
"value": "Dragan Lukovski_sentence_3"
},
{
"operation": "finish",
"time": "54.018",
"value": "finish"
}
]
}
|
89318
|
The 1864 Hackney London Borough Council election was joined by a full slate of Independent Labour, 36 candidates from the Conservative Party, 32 candidates from the Liberal Party, and eight candidates from the Communist Party.
|
{
"evidence": [
"Independent Labour Party_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 1864 Hackney London Borough Council election was joined by a full slate of Independent Labour, 36 candidates from the Conservative Party, 32 candidates from the Liberal Party, and eight candidates from the Communist Party.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Independent Labour Party_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2236,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.484",
"value": "?search="
},
{
"operation": "search",
"time": "20.091",
"value": "1864 Hackney London Borough Council election"
},
{
"operation": "Now on",
"time": "21.468",
"value": "undefined"
},
{
"operation": "search",
"time": "59.688",
"value": "Hackney London Borough Council election"
},
{
"operation": "Now on",
"time": "61.815",
"value": "undefined"
},
{
"operation": "search",
"time": "94.587",
"value": "Hackney London Borough Council election, 1864"
},
{
"operation": "Now on",
"time": "95.453",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "134.632",
"value": "Middlesex"
},
{
"operation": "Now on",
"time": "136.237",
"value": "Middlesex"
},
{
"operation": "search",
"time": "242.939",
"value": "Hackney London Borough Council elections"
},
{
"operation": "Now on",
"time": "247.86",
"value": "Hackney London Borough Council elections"
},
{
"operation": "hyperlink",
"time": "397.57",
"value": "4.1 1964–1968 Hackney London Borough Council elections_section_4"
},
{
"operation": "search",
"time": "434.856",
"value": "1864 Hackney London Borough Council election"
},
{
"operation": "Now on",
"time": "436.517",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "531.422",
"value": "List of Acts of the Parliament of the United Kingdom, 1840–1859"
},
{
"operation": "Now on",
"time": "538.401",
"value": "List of Acts of the Parliament of the United Kingdom, 1840–1859"
},
{
"operation": "search",
"time": "576.114",
"value": "candidates from the Communist Party"
},
{
"operation": "Now on",
"time": "580.678",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "638.648",
"value": "Communist union leader Harry Pollitt_section_2"
},
{
"operation": "Now on",
"time": "639.586",
"value": "Harry Pollitt#Communist union leader Harry Pollitt section 2"
},
{
"operation": "search",
"time": "675.028",
"value": "36 candidates from the Conservative Party"
},
{
"operation": "Now on",
"time": "677.634",
"value": "undefined"
},
{
"operation": "search",
"time": "703.944",
"value": "Contains... 1864 Hackney London Borough"
},
{
"operation": "Now on",
"time": "704.78",
"value": "undefined"
},
{
"operation": "search",
"time": "765.111",
"value": "Contains...1864 Hackney"
},
{
"operation": "Now on",
"time": "766.177",
"value": "undefined"
},
{
"operation": "search",
"time": "876.313",
"value": "Hackney Council election, 1864"
},
{
"operation": "Now on",
"time": "877.244",
"value": "undefined"
},
{
"operation": "search",
"time": "996.939",
"value": "East End election 1864"
},
{
"operation": "Now on",
"time": "998.532",
"value": "undefined"
},
{
"operation": "search",
"time": "1067.402",
"value": "\"was joined by a full slate of Independent Labour\""
},
{
"operation": "Now on",
"time": "1069.213",
"value": "undefined"
},
{
"operation": "search",
"time": "1101.641",
"value": "\"full slate of Independent Labour\""
},
{
"operation": "Now on",
"time": "1102.387",
"value": "undefined"
},
{
"operation": "search",
"time": "1133.258",
"value": "Independent Labour Party election results"
},
{
"operation": "Now on",
"time": "1137.033",
"value": "Independent Labour Party election results"
},
{
"operation": "search",
"time": "1205.506",
"value": "Independent Labour Party"
},
{
"operation": "Now on",
"time": "1207.235",
"value": "Independent Labour Party"
},
{
"operation": "Highlighting",
"time": "1218.518",
"value": "Independent Labour Party_sentence_1"
},
{
"operation": "finish",
"time": "1264.57",
"value": "finish"
}
]
}
|
17369
|
The district resources were built between about 1883 and about 1945; includes the Anderson and Rion Quarry sites, commercial buildings and structures associated with limestone quarrying and finishing operations.
|
{
"evidence": [
"Rockton and Rion Railroad Historic District_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 district resources were built between about 1883 and about 1945; includes the Anderson and Rion Quarry sites, commercial buildings and structures associated with limestone quarrying and finishing operations.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Rockton and Rion Railroad Historic District_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2237,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.406",
"value": "?search="
},
{
"operation": "search",
"time": "12.613",
"value": "Contains...Rion Quarry"
},
{
"operation": "Now on",
"time": "13.552",
"value": "undefined"
},
{
"operation": "search",
"time": "38.006",
"value": "\"district resources were built \""
},
{
"operation": "Now on",
"time": "39.169",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "40.968",
"value": "Rockton and Rion Railroad Historic District"
},
{
"operation": "Now on",
"time": "41.916",
"value": "Rockton and Rion Railroad Historic District"
},
{
"operation": "Highlighting",
"time": "46.056",
"value": "Rockton and Rion Railroad Historic District_sentence_2"
},
{
"operation": "Highlighting",
"time": "53.293",
"value": "Rockton and Rion Railroad Historic District_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "73.403",
"value": "Rockton and Rion Railroad Historic District_sentence_2"
},
{
"operation": "finish",
"time": "93.102",
"value": "finish"
}
]
}
|
38771
|
Kongbap is generally acknowledged as a healthful food and has long been a staple of Korean prison food.
|
{
"evidence": [
"Kongbap_sentence_5",
"Kongbap_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:\nKongbap is generally acknowledged as a healthful food and has long been a staple of Korean prison food.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Kongbap_sentence_5",
"Kongbap_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2238,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.552",
"value": "?search="
},
{
"operation": "search",
"time": "15.629",
"value": "Kongbap"
},
{
"operation": "Now on",
"time": "16.636",
"value": "Kongbap"
},
{
"operation": "Page search",
"time": "42.328",
"value": "kore"
},
{
"operation": "Page search",
"time": "51.815",
"value": "prison"
},
{
"operation": "Highlighting",
"time": "63.71",
"value": "Kongbap_sentence_5"
},
{
"operation": "Highlighting",
"time": "71.721",
"value": "Kongbap_sentence_6"
},
{
"operation": "finish",
"time": "113.331",
"value": "finish"
}
]
}
|
67576
|
Lisa De Vanna was the 18th overall selection in the 2008 Women's Professional Soccer International Draft when she was chosen by the Washington Freedom (an American professional soccer club based in the Washington, D.C., suburb of Germantown, Maryland), whom she officially signed with in March 2009 and played for for three years.
|
{
"evidence": [
"Lisa De Vanna_sentence_11",
"Lisa De Vanna_sentence_10",
"Washington Freedom_sentence_0",
"Lisa De Vanna_sentence_12",
"Lisa De Vanna_sentence_13"
],
"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:\nLisa De Vanna was the 18th overall selection in the 2008 Women's Professional Soccer International Draft when she was chosen by the Washington Freedom (an American professional soccer club based in the Washington, D.C., suburb of Germantown, Maryland), whom she officially signed with in March 2009 and played for for three years.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Lisa De Vanna_sentence_11",
"Lisa De Vanna_sentence_10",
"Washington Freedom_sentence_0",
"Lisa De Vanna_sentence_12",
"Lisa De Vanna_sentence_13"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2239,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.379",
"value": "?search="
},
{
"operation": "search",
"time": "9.247",
"value": "Lisa De Vanna"
},
{
"operation": "Now on",
"time": "11.167",
"value": "Lisa De Vanna"
},
{
"operation": "search",
"time": "91.586",
"value": "2008 Women's Professional Soccer International Draft"
},
{
"operation": "Now on",
"time": "94.637",
"value": "undefined"
},
{
"operation": "search",
"time": "115.535",
"value": "2008 WPS General Draft"
},
{
"operation": "Now on",
"time": "117.762",
"value": "2008 WPS General Draft"
},
{
"operation": "hyperlink",
"time": "130.942",
"value": "List of foreign WPS players"
},
{
"operation": "Now on",
"time": "135.3",
"value": "List of foreign WPS players"
},
{
"operation": "back-button-clicked",
"time": "148.515",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "148.561",
"value": "2008 WPS General Draft"
},
{
"operation": "back-button-clicked",
"time": "151.2",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "151.203",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "151.278",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "156.951",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "156.955",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "157.117",
"value": "Lisa De Vanna"
},
{
"operation": "Page search",
"time": "162.813",
"value": "draft"
},
{
"operation": "Highlighting",
"time": "166.396",
"value": "Lisa De Vanna_sentence_11"
},
{
"operation": "Highlighting",
"time": "174.527",
"value": "Lisa De Vanna_sentence_12"
},
{
"operation": "Highlighting",
"time": "177.334",
"value": "Lisa De Vanna_sentence_10"
},
{
"operation": "Highlighting deleted",
"time": "178.12",
"value": "Lisa De Vanna_sentence_12"
},
{
"operation": "hyperlink",
"time": "184.496",
"value": "Washington Freedom"
},
{
"operation": "Now on",
"time": "185.391",
"value": "Washington Freedom"
},
{
"operation": "Highlighting",
"time": "190.758",
"value": "Washington Freedom_sentence_0"
},
{
"operation": "back-button-clicked",
"time": "195.307",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "195.457",
"value": "Lisa De Vanna"
},
{
"operation": "Highlighting",
"time": "197.371",
"value": "Lisa De Vanna_sentence_12"
},
{
"operation": "Highlighting",
"time": "198.603",
"value": "Lisa De Vanna_sentence_13"
},
{
"operation": "finish",
"time": "205.832",
"value": "finish"
}
]
}
|
68914
|
Brahman Mirza and his family relocated to Karabakh in 1853 where they lived a simple life.
|
{
"evidence": [
"Mirza_sentence_1",
"Mirza_sentence_2",
"Mirza_sentence_3",
"Mirza_sentence_4",
"Brahman_sentence_2",
"Karabakh_sentence_2",
"Karabakh_sentence_52",
"Karabakh_sentence_53"
],
"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:\nBrahman Mirza and his family relocated to Karabakh in 1853 where they lived a simple life.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Mirza_sentence_1",
"Mirza_sentence_2",
"Mirza_sentence_3",
"Mirza_sentence_4",
"Brahman_sentence_2",
"Karabakh_sentence_2",
"Karabakh_sentence_52",
"Karabakh_sentence_53"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2240,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.447",
"value": "undefined"
},
{
"operation": "search",
"time": "13.75",
"value": "brahman mirza"
},
{
"operation": "Now on",
"time": "17.266",
"value": "undefined"
},
{
"operation": "search",
"time": "41.316",
"value": "Karabakh"
},
{
"operation": "Now on",
"time": "43.458",
"value": "Karabakh"
},
{
"operation": "Page search",
"time": "51.466",
"value": "mirza"
},
{
"operation": "Page search",
"time": "58.049",
"value": "brahman"
},
{
"operation": "search",
"time": "63.91",
"value": "mirza"
},
{
"operation": "Now on",
"time": "88.428",
"value": "Mirza"
},
{
"operation": "Page search",
"time": "105.074",
"value": "brah*"
},
{
"operation": "Highlighting",
"time": "133.642",
"value": "Mirza_item_9_77"
},
{
"operation": "Highlighting",
"time": "133.648",
"value": "Mirza_section_16"
},
{
"operation": "Highlighting",
"time": "133.649",
"value": "Mirza_section_17"
},
{
"operation": "Highlighting deleted",
"time": "136.962",
"value": "Mirza_item_9_77"
},
{
"operation": "Highlighting deleted",
"time": "136.968",
"value": "Mirza_section_16"
},
{
"operation": "Highlighting deleted",
"time": "136.971",
"value": "Mirza_section_17"
},
{
"operation": "Page search",
"time": "152.818",
"value": "braman"
},
{
"operation": "Highlighting",
"time": "169.493",
"value": "Mirza_sentence_1"
},
{
"operation": "Highlighting",
"time": "171.128",
"value": "Mirza_sentence_2"
},
{
"operation": "Highlighting",
"time": "173.689",
"value": "Mirza_sentence_3"
},
{
"operation": "Highlighting",
"time": "175.76",
"value": "Mirza_sentence_4"
},
{
"operation": "Page search",
"time": "188.598",
"value": "karab*"
},
{
"operation": "search",
"time": "206.468",
"value": "Brahman"
},
{
"operation": "Now on",
"time": "240.413",
"value": "Brahman"
},
{
"operation": "Highlighting",
"time": "260.587",
"value": "Brahman_sentence_2"
},
{
"operation": "Page search",
"time": "268.173",
"value": "mirza"
},
{
"operation": "search",
"time": "297.896",
"value": "Karabakh"
},
{
"operation": "Now on",
"time": "298.98",
"value": "Karabakh"
},
{
"operation": "Highlighting",
"time": "301.835",
"value": "Karabakh_sentence_2"
},
{
"operation": "Page search",
"time": "309.22",
"value": "1853"
},
{
"operation": "Highlighting",
"time": "322.245",
"value": "Karabakh_sentence_52"
},
{
"operation": "Highlighting",
"time": "323.333",
"value": "Karabakh_sentence_53"
},
{
"operation": "search",
"time": "337.763",
"value": "brahman mirza"
},
{
"operation": "Now on",
"time": "343.14",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "357.089",
"value": "Akbar"
},
{
"operation": "finish",
"time": "392.819",
"value": "finish"
}
]
}
|
exfever_5636
|
The Anschluss was the annexation of Austria into Nazi Germany began after the unification of Germany excluded Austria and the German Austrians from the Prussian-dominated period of the German Reich founded on 18 January 1875 also known as the Deutsche Reichsgründung.
|
{
"evidence": [
"Anschluss",
"German Empire",
"Proclamation of the German Empire"
],
"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 Anschluss was the annexation of Austria into Nazi Germany began after the unification of Germany excluded Austria and the German Austrians from the Prussian-dominated period of the German Reich founded on 18 January 1875 also known as the Deutsche Reichsgründung.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Anschluss",
"German Empire",
"Proclamation of the German Empire"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2241,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
65423
|
Riemannian geometry, a concept first generalized in the 19th century by Bernhard Riemann, deals with geometric shapes that are defined in nature.
|
{
"evidence": [
"Riemannian geometry_sentence_7"
],
"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:\nRiemannian geometry, a concept first generalized in the 19th century by Bernhard Riemann, deals with geometric shapes that are defined in nature.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Riemannian geometry_sentence_7"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2242,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.791",
"value": "undefined"
},
{
"operation": "search",
"time": "7.412",
"value": "Riemannian geometry"
},
{
"operation": "Now on",
"time": "8.627",
"value": "Riemannian geometry"
},
{
"operation": "Highlighting",
"time": "78.888",
"value": "Riemannian geometry_sentence_7"
},
{
"operation": "Page search",
"time": "156.412",
"value": "nature"
},
{
"operation": "Page search",
"time": "168.846",
"value": "geometric"
},
{
"operation": "Page search",
"time": "183.884",
"value": "shapes"
},
{
"operation": "search",
"time": "304.614",
"value": "geometric shapes that are defined in nature"
},
{
"operation": "Now on",
"time": "307.475",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "329.505",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "329.734",
"value": "Riemannian geometry"
},
{
"operation": "finish",
"time": "352.71",
"value": "finish"
}
]
}
|
37982
|
Frederick Borden, the Minister of Militia and Defence, announced in May that a 200-strong force would be deployed to Fort Selkirk; and one of the arguments put forward in favour of this option was that it was much cheaper than sending additional police, who enjoyed higher pay than soldiers.
|
{
"evidence": [
"Frederick William Borden_sentence_1",
"Frederick William Borden_sentence_17",
"Frederick William Borden_sentence_18"
],
"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:\nFrederick Borden, the Minister of Militia and Defence, announced in May that a 200-strong force would be deployed to Fort Selkirk; and one of the arguments put forward in favour of this option was that it was much cheaper than sending additional police, who enjoyed higher pay than soldiers.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Frederick William Borden_sentence_1",
"Frederick William Borden_sentence_17",
"Frederick William Borden_sentence_18"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2243,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.076",
"value": "?search="
},
{
"operation": "search",
"time": "14.676",
"value": "Frederick Borden"
},
{
"operation": "Now on",
"time": "16.052",
"value": "Frederick William Borden"
},
{
"operation": "Highlighting",
"time": "33.967",
"value": "Frederick William Borden_sentence_1"
},
{
"operation": "search",
"time": "60.663",
"value": "Fort Selkirk"
},
{
"operation": "Now on",
"time": "61.784",
"value": "Fort Selkirk"
},
{
"operation": "back-button-clicked",
"time": "81.151",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "82.402",
"value": "Frederick William Borden"
},
{
"operation": "hyperlink",
"time": "84.951",
"value": "Second Boer War"
},
{
"operation": "Now on",
"time": "88.615",
"value": "Second Boer War"
},
{
"operation": "search",
"time": "146.294",
"value": "Fort Selkirk"
},
{
"operation": "Now on",
"time": "147.555",
"value": "Fort Selkirk"
},
{
"operation": "back-button-clicked",
"time": "172.849",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "173.233",
"value": "Second Boer War"
},
{
"operation": "back-button-clicked",
"time": "173.885",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "173.895",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "174.092",
"value": "Frederick William Borden"
},
{
"operation": "Highlighting",
"time": "233.757",
"value": "Frederick William Borden_sentence_17"
},
{
"operation": "Highlighting",
"time": "234.407",
"value": "Frederick William Borden_sentence_18"
},
{
"operation": "finish",
"time": "254.048",
"value": "finish"
}
]
}
|
47957
|
In the Ninth Dynasty of Egypt according to Haynes, Mreyibre Khety I was of no importance in the dynasty.
|
{
"evidence": [
"Meryibre Khety_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:\nIn the Ninth Dynasty of Egypt according to Haynes, Mreyibre Khety I was of no importance in the dynasty.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Meryibre Khety_sentence_4"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2244,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.917",
"value": "?search="
},
{
"operation": "search",
"time": "18.521",
"value": "Ninth Dynasty of Egypt"
},
{
"operation": "Now on",
"time": "19.211",
"value": "Ninth Dynasty of Egypt"
},
{
"operation": "Page search",
"time": "33.608",
"value": "haynes"
},
{
"operation": "Page search",
"time": "43.471",
"value": "haynes"
},
{
"operation": "search",
"time": "60.056",
"value": "Mreyibre Kety"
},
{
"operation": "Now on",
"time": "60.782",
"value": "undefined"
},
{
"operation": "search",
"time": "81.919",
"value": "Khety I"
},
{
"operation": "Now on",
"time": "83.018",
"value": "Khety I"
},
{
"operation": "Page search",
"time": "96.359",
"value": "haynes"
},
{
"operation": "search",
"time": "151.79",
"value": "Haynes Ninth Dynasty"
},
{
"operation": "Now on",
"time": "152.686",
"value": "undefined"
},
{
"operation": "search",
"time": "161.997",
"value": "Haynes Khety"
},
{
"operation": "Now on",
"time": "162.309",
"value": "undefined"
},
{
"operation": "search",
"time": "173.262",
"value": "Khety I (nomarch)"
},
{
"operation": "Now on",
"time": "173.902",
"value": "Khety I (nomarch)"
},
{
"operation": "Page search",
"time": "189.013",
"value": "Haynes"
},
{
"operation": "search",
"time": "225.926",
"value": "Khety I"
},
{
"operation": "Now on",
"time": "226.345",
"value": "Khety I"
},
{
"operation": "search",
"time": "244.213",
"value": "Meryibtawy"
},
{
"operation": "Now on",
"time": "244.687",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "251.862",
"value": "List of ancient Egyptians"
},
{
"operation": "Now on",
"time": "254.22",
"value": "List of ancient Egyptians"
},
{
"operation": "Page search",
"time": "259.809",
"value": "Khety"
},
{
"operation": "hyperlink",
"time": "288.027",
"value": "Khety I"
},
{
"operation": "Now on",
"time": "288.399",
"value": "Khety I (nomarch)"
},
{
"operation": "search",
"time": "338.899",
"value": "The Ninth Dynasty of Egypt"
},
{
"operation": "Now on",
"time": "340.565",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "354.268",
"value": "Ninth Dynasty of Egypt"
},
{
"operation": "Now on",
"time": "354.803",
"value": "Ninth Dynasty of Egypt"
},
{
"operation": "hyperlink",
"time": "466.689",
"value": "Meryibre Khety"
},
{
"operation": "Now on",
"time": "467.269",
"value": "Meryibre Khety"
},
{
"operation": "Highlighting",
"time": "493.185",
"value": "Meryibre Khety_sentence_4"
},
{
"operation": "finish",
"time": "533.975",
"value": "finish"
}
]
}
|
exfever_6434
|
Boromir is a fictional character appears in the second volume of J. R. R. Tolkien's high fantasy novel The Lord of the Rings.
|
{
"evidence": [
"Boromir",
"The Two Towers"
],
"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:\nBoromir is a fictional character appears in the second volume of J. R. R. Tolkien's high fantasy novel The Lord of the Rings.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Boromir",
"The Two Towers"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2245,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
68914
|
Brahman Mirza and his family relocated to Karabakh in 1853 where they lived a simple life.
|
{
"evidence": [
"Mirza_sentence_1",
"Mirza_sentence_2",
"Mirza_sentence_3",
"Mirza_sentence_4",
"Brahman_sentence_2",
"Karabakh_sentence_2",
"Karabakh_sentence_52",
"Karabakh_sentence_53"
],
"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:\nBrahman Mirza and his family relocated to Karabakh in 1853 where they lived a simple life.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Mirza_sentence_1",
"Mirza_sentence_2",
"Mirza_sentence_3",
"Mirza_sentence_4",
"Brahman_sentence_2",
"Karabakh_sentence_2",
"Karabakh_sentence_52",
"Karabakh_sentence_53"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2246,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.447",
"value": "undefined"
},
{
"operation": "search",
"time": "13.75",
"value": "brahman mirza"
},
{
"operation": "Now on",
"time": "17.266",
"value": "undefined"
},
{
"operation": "search",
"time": "41.316",
"value": "Karabakh"
},
{
"operation": "Now on",
"time": "43.458",
"value": "Karabakh"
},
{
"operation": "Page search",
"time": "51.466",
"value": "mirza"
},
{
"operation": "Page search",
"time": "58.049",
"value": "brahman"
},
{
"operation": "search",
"time": "63.91",
"value": "mirza"
},
{
"operation": "Now on",
"time": "88.428",
"value": "Mirza"
},
{
"operation": "Page search",
"time": "105.074",
"value": "brah*"
},
{
"operation": "Highlighting",
"time": "133.642",
"value": "Mirza_item_9_77"
},
{
"operation": "Highlighting",
"time": "133.648",
"value": "Mirza_section_16"
},
{
"operation": "Highlighting",
"time": "133.649",
"value": "Mirza_section_17"
},
{
"operation": "Highlighting deleted",
"time": "136.962",
"value": "Mirza_item_9_77"
},
{
"operation": "Highlighting deleted",
"time": "136.968",
"value": "Mirza_section_16"
},
{
"operation": "Highlighting deleted",
"time": "136.971",
"value": "Mirza_section_17"
},
{
"operation": "Page search",
"time": "152.818",
"value": "braman"
},
{
"operation": "Highlighting",
"time": "169.493",
"value": "Mirza_sentence_1"
},
{
"operation": "Highlighting",
"time": "171.128",
"value": "Mirza_sentence_2"
},
{
"operation": "Highlighting",
"time": "173.689",
"value": "Mirza_sentence_3"
},
{
"operation": "Highlighting",
"time": "175.76",
"value": "Mirza_sentence_4"
},
{
"operation": "Page search",
"time": "188.598",
"value": "karab*"
},
{
"operation": "search",
"time": "206.468",
"value": "Brahman"
},
{
"operation": "Now on",
"time": "240.413",
"value": "Brahman"
},
{
"operation": "Highlighting",
"time": "260.587",
"value": "Brahman_sentence_2"
},
{
"operation": "Page search",
"time": "268.173",
"value": "mirza"
},
{
"operation": "search",
"time": "297.896",
"value": "Karabakh"
},
{
"operation": "Now on",
"time": "298.98",
"value": "Karabakh"
},
{
"operation": "Highlighting",
"time": "301.835",
"value": "Karabakh_sentence_2"
},
{
"operation": "Page search",
"time": "309.22",
"value": "1853"
},
{
"operation": "Highlighting",
"time": "322.245",
"value": "Karabakh_sentence_52"
},
{
"operation": "Highlighting",
"time": "323.333",
"value": "Karabakh_sentence_53"
},
{
"operation": "search",
"time": "337.763",
"value": "brahman mirza"
},
{
"operation": "Now on",
"time": "343.14",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "357.089",
"value": "Akbar"
},
{
"operation": "finish",
"time": "392.819",
"value": "finish"
}
]
}
|
exfever_6568
|
The Smurfs is the first 3D live-action/computer-animated comedy film directed by Raja Gosnell.
|
{
"evidence": [
"The Smurfs (film)",
"Neil Patrick Harris",
"Golden Globe Award for Best Actor – Television Series Musical or Comedy"
],
"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 Smurfs is the first 3D live-action/computer-animated comedy film directed by Raja Gosnell.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Smurfs (film)",
"Neil Patrick Harris",
"Golden Globe Award for Best Actor – Television Series Musical or Comedy"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2247,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
38344
|
Songs for the Poor Man is the an album by Kenyan artist Remmy Ongala and his band Orchestre Super Matimila which received a favourable rating from Folk Roots and 7/10 from NME
|
{
"evidence": [
"Songs for the Poor Man_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:\nSongs for the Poor Man is the an album by Kenyan artist Remmy Ongala and his band Orchestre Super Matimila which received a favourable rating from Folk Roots and 7/10 from NME\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Songs for the Poor Man_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2248,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.719",
"value": "?search="
},
{
"operation": "search",
"time": "5.306",
"value": "Songs for the Poor Man"
},
{
"operation": "Now on",
"time": "6.133",
"value": "Songs for the Poor Man"
},
{
"operation": "Highlighting",
"time": "9.685",
"value": "Songs for the Poor Man_sentence_0"
},
{
"operation": "finish",
"time": "17.807",
"value": "finish"
}
]
}
|
87939
|
According to Bostrom, a computer program that faithfully emulates a network of human-level intelligences but with processing speeds faster than a human when strictly comparing speeds as Biological neurons operate at about 200 Hz, while a modern microprocessor operates at 2,000,000,000 Hz; same with comparing the human axons that travel at around 120m/s while a computer signal travels at the speed of sound.
|
{
"evidence": [
"AI takeover_sentence_41"
],
"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:\nAccording to Bostrom, a computer program that faithfully emulates a network of human-level intelligences but with processing speeds faster than a human when strictly comparing speeds as Biological neurons operate at about 200 Hz, while a modern microprocessor operates at 2,000,000,000 Hz; same with comparing the human axons that travel at around 120m/s while a computer signal travels at the speed of sound.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"AI takeover_sentence_41"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2249,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.2",
"value": "?search="
},
{
"operation": "search",
"time": "15.286",
"value": "Contains...According to Bostrom, a computer program that faithfully emulates"
},
{
"operation": "Now on",
"time": "16.862",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "26.267",
"value": "AI takeover"
},
{
"operation": "Now on",
"time": "27.22",
"value": "AI takeover"
},
{
"operation": "Page search",
"time": "34.624",
"value": "According to Bostrom"
},
{
"operation": "Highlighting",
"time": "46.006",
"value": "AI takeover_sentence_39"
},
{
"operation": "Highlighting",
"time": "64.027",
"value": "AI takeover_sentence_42"
},
{
"operation": "Highlighting",
"time": "90.229",
"value": "AI takeover_sentence_40"
},
{
"operation": "Highlighting",
"time": "127.03",
"value": "AI takeover_sentence_41"
},
{
"operation": "Highlighting deleted",
"time": "141.407",
"value": "AI takeover_sentence_42"
},
{
"operation": "Highlighting deleted",
"time": "142.358",
"value": "AI takeover_sentence_40"
},
{
"operation": "Highlighting deleted",
"time": "142.999",
"value": "AI takeover_sentence_39"
},
{
"operation": "finish",
"time": "159.319",
"value": "finish"
}
]
}
|
exfever_4452
|
Outkast was an American hip hop duo who achieved both critical acclaim and commercial success from the mid-1990s to the early 2000s, helping to popularize a blanket term for a regional genre of American hip hop music.
|
{
"evidence": [
"Outkast",
"Southern hip hop"
],
"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:\nOutkast was an American hip hop duo who achieved both critical acclaim and commercial success from the mid-1990s to the early 2000s, helping to popularize a blanket term for a regional genre of American hip hop music.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Outkast",
"Southern hip hop"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2250,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6068
|
The ATAS award is the highest award an artist can receive.
|
{
"evidence": [
"Donald Glover",
"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:\nThe ATAS award is the highest award an artist can receive.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Donald Glover",
"Primetime Emmy Award"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2251,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_728
|
J. Cole is an African rapper, singer, songwriter, and record producer who released an album release by Roc Nation.
|
{
"evidence": [
"J. Cole",
"Born Sinner"
],
"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:\nJ. Cole is an African rapper, singer, songwriter, and record producer who released an album release by Roc Nation.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"J. Cole",
"Born Sinner"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2252,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
78445
|
Driven by Takuma Sato, the Super Aguri SA06 was the car with which the Super Aguri team competed in the latter part of the 2006 Formula One season.
|
{
"evidence": [
"Super Aguri SA06_sentence_1",
"Super Aguri SA06_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:\nDriven by Takuma Sato, the Super Aguri SA06 was the car with which the Super Aguri team competed in the latter part of the 2006 Formula One season.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Super Aguri SA06_sentence_1",
"Super Aguri SA06_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2253,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.855",
"value": "?search="
},
{
"operation": "search",
"time": "8.824",
"value": "Takuma Sato"
},
{
"operation": "Now on",
"time": "10.378",
"value": "undefined"
},
{
"operation": "search",
"time": "26.73",
"value": "Super Aguri SA06"
},
{
"operation": "Now on",
"time": "27.616",
"value": "Super Aguri SA06"
},
{
"operation": "Highlighting",
"time": "31.123",
"value": "Super Aguri SA06_sentence_1"
},
{
"operation": "Highlighting",
"time": "45.099",
"value": "Super Aguri SA06_sentence_0"
},
{
"operation": "finish",
"time": "51.354",
"value": "finish"
}
]
}
|
exfever_8658
|
War of the Worlds is a 2005 film written by Josh Friedman and an American screenwriter and film director who has achieved both critical and commercial success in a wide variety of genres, including a broad genre that evokes excitement and suspense.
|
{
"evidence": [
"War of the Worlds (2005 film)",
"David Koepp",
"Thriller 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:\nWar of the Worlds is a 2005 film written by Josh Friedman and an American screenwriter and film director who has achieved both critical and commercial success in a wide variety of genres, including a broad genre that evokes excitement and suspense.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"War of the Worlds (2005 film)",
"David Koepp",
"Thriller film"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2254,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7212
|
Cory Monteith was a musician best known for his role as Finn Hudson on a commercial broadcast television network owned by Fox Corporation.
|
{
"evidence": [
"Cory Monteith",
"Fox Broadcasting Company"
],
"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:\nCory Monteith was a musician best known for his role as Finn Hudson on a commercial broadcast television network owned by Fox Corporation.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Cory Monteith",
"Fox Broadcasting Company"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2255,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8150
|
Geronimo is the first film of William West Anderson.
|
{
"evidence": [
"Adam West",
"Batman (1966 film)",
"DC Comics"
],
"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:\nGeronimo is the first film of William West Anderson.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Adam West",
"Batman (1966 film)",
"DC Comics"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2256,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1998
|
A Thousand Suns is the fourth studio album by the American rock band Linkin Park produced by an American record producer who is also the former co-president of an American record label owned by Sony Music Entertainment, a subsidiary of Sony Corporation of America, the North American division of Japanese conglomerate Sony.
|
{
"evidence": [
"A Thousand Suns",
"Rick Rubin",
"Columbia Records"
],
"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 Thousand Suns is the fourth studio album by the American rock band Linkin Park produced by an American record producer who is also the former co-president of an American record label owned by Sony Music Entertainment, a subsidiary of Sony Corporation of America, the North American division of Japanese conglomerate Sony.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"A Thousand Suns",
"Rick Rubin",
"Columbia Records"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2257,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7679
|
A Crown was a territory subject to a form of foreign rule administered by The Crown within the British Empire.
|
{
"evidence": [
"Crown colony",
"Colony"
],
"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 Crown was a territory subject to a form of foreign rule administered by The Crown within the British Empire.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Crown colony",
"Colony"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2258,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
1515
|
Craig Paul Tracey (born 21 August 1974) has never run for political office.
|
{
"evidence": [
"Craig Tracey_sentence_2"
],
"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:\nCraig Paul Tracey (born 21 August 1974) has never run for political office.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Craig Tracey_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2259,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "36.182",
"value": "Craig Paul Tracey"
},
{
"operation": "hyperlink",
"time": "71.64",
"value": "Craig Tracey"
},
{
"operation": "Highlighting",
"time": "95.556",
"value": "Craig Tracey_sentence_2"
},
{
"operation": "finish",
"time": "118.484",
"value": "finish"
}
]
}
|
29792
|
WLNQ (104.7 FM), owned by Bristol Broadcasting Company, Inc., is in a pop music format serving Morristown, Tennessee.
|
{
"evidence": [
"WLNQ_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:\nWLNQ (104.7 FM), owned by Bristol Broadcasting Company, Inc., is in a pop music format serving Morristown, Tennessee.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"WLNQ_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2260,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.638",
"value": "?search="
},
{
"operation": "search",
"time": "12.296",
"value": "WLNQ"
},
{
"operation": "Now on",
"time": "12.987",
"value": "WLNQ"
},
{
"operation": "Highlighting",
"time": "16.644",
"value": "WLNQ_header_cell_0_6_0"
},
{
"operation": "Highlighting",
"time": "17.705",
"value": "WLNQ_cell_0_6_1"
},
{
"operation": "Highlighting",
"time": "17.716",
"value": "WLNQ_header_cell_0_6_0"
},
{
"operation": "Highlighting",
"time": "17.716",
"value": "WLNQ_header_cell_0_5_0"
},
{
"operation": "Highlighting deleted",
"time": "22.567",
"value": "WLNQ_cell_0_6_1"
},
{
"operation": "Highlighting deleted",
"time": "22.579",
"value": "WLNQ_header_cell_0_6_0"
},
{
"operation": "Highlighting deleted",
"time": "22.581",
"value": "WLNQ_header_cell_0_5_0"
},
{
"operation": "Highlighting",
"time": "24.954",
"value": "WLNQ_sentence_0"
},
{
"operation": "finish",
"time": "32.705",
"value": "finish"
}
]
}
|
94460
|
Bavaria is connected to Hungary through a bicycle path, as well as Budapest to Serbia.
|
{
"evidence": [
"EV6 The Rivers Route_sentence_0",
"EV6 The Rivers Route_sentence_27"
],
"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:\nBavaria is connected to Hungary through a bicycle path, as well as Budapest to Serbia.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"EV6 The Rivers Route_sentence_0",
"EV6 The Rivers Route_sentence_27"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2261,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.452",
"value": "?search="
},
{
"operation": "search",
"time": "265.529",
"value": "Budapest"
},
{
"operation": "Now on",
"time": "269.88",
"value": "Budapest"
},
{
"operation": "search",
"time": "1023.468",
"value": "Danube Cycle Path"
},
{
"operation": "Now on",
"time": "1024.529",
"value": "Danube Cycle Path"
},
{
"operation": "hyperlink",
"time": "1193.146",
"value": "holiday cycle route"
},
{
"operation": "Now on",
"time": "1194.089",
"value": "Bicycle touring"
},
{
"operation": "back-button-clicked",
"time": "1300.994",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "1301.56",
"value": "EV6 The Rivers Route"
},
{
"operation": "Highlighting",
"time": "1547.891",
"value": "EV6 The Rivers Route_sentence_27"
},
{
"operation": "Highlighting",
"time": "1664.087",
"value": "EV6 The Rivers Route_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "1702.626",
"value": "EV6 The Rivers Route_sentence_27"
},
{
"operation": "Highlighting deleted",
"time": "1706.71",
"value": "EV6 The Rivers Route_sentence_1"
},
{
"operation": "Highlighting",
"time": "1708.27",
"value": "EV6 The Rivers Route_sentence_0"
},
{
"operation": "Highlighting",
"time": "1720.582",
"value": "EV6 The Rivers Route_sentence_1"
},
{
"operation": "Highlighting",
"time": "1736.59",
"value": "EV6 The Rivers Route_sentence_27"
},
{
"operation": "Highlighting deleted",
"time": "1815.526",
"value": "EV6 The Rivers Route_sentence_1"
},
{
"operation": "finish",
"time": "1833.447",
"value": "finish"
}
]
}
|
1461
|
McCornack flew from California to Wisconsin in 1979 before being invited to fly an aircraft on ethanol, a simple alcohol produced by fermentation.
|
{
"evidence": [
"Pterodactyl Ascender_sentence_19",
"Pterodactyl Ascender_sentence_20",
"Ethanol_sentence_3",
"Ethanol_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:\nMcCornack flew from California to Wisconsin in 1979 before being invited to fly an aircraft on ethanol, a simple alcohol produced by fermentation.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Pterodactyl Ascender_sentence_19",
"Pterodactyl Ascender_sentence_20",
"Ethanol_sentence_3",
"Ethanol_sentence_7"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2262,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "16.099",
"value": "McCornack pilot"
},
{
"operation": "hyperlink",
"time": "25.77",
"value": "Pterodactyl Ascender"
},
{
"operation": "Highlighting",
"time": "36.978",
"value": "Pterodactyl Ascender_cell_0_4_1"
},
{
"operation": "Highlighting",
"time": "36.996",
"value": "Pterodactyl Ascender_header_cell_0_4_0"
},
{
"operation": "Highlighting",
"time": "37.001",
"value": "Pterodactyl Ascender_header_cell_0_0_0"
},
{
"operation": "search",
"time": "46.357",
"value": "Contains...Jack McCornack"
},
{
"operation": "hyperlink",
"time": "54.393",
"value": "jack mccormack"
},
{
"operation": "search",
"time": "67.144",
"value": "Jack McCornack"
},
{
"operation": "hyperlink",
"time": "73.777",
"value": "Cuyuna 430"
},
{
"operation": "hyperlink",
"time": "119.674",
"value": "Pterodactyl Pfledge"
},
{
"operation": "Highlighting",
"time": "154.092",
"value": "Pterodactyl Ascender_sentence_19"
},
{
"operation": "Highlighting",
"time": "156.692",
"value": "Pterodactyl Ascender_sentence_20"
},
{
"operation": "hyperlink",
"time": "182.779",
"value": "ethanol"
},
{
"operation": "Highlighting",
"time": "187.882",
"value": "Ethanol_sentence_3"
},
{
"operation": "Highlighting",
"time": "193.61",
"value": "Ethanol_sentence_7"
},
{
"operation": "finish",
"time": "249.123",
"value": "finish"
}
]
}
|
exfever_3973
|
"Wild Ones" is a song by Tramar Lacel Dillard, an American rapper that had a 2007 breakout single, "Low," which was number one for 12 weeks in the United States and broke the record for digital download sales at the time of its release.
|
{
"evidence": [
"Wild Ones (song)",
"Flo Rida"
],
"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:\n\"Wild Ones\" is a song by Tramar Lacel Dillard, an American rapper that had a 2007 breakout single, \"Low,\" which was number one for 12 weeks in the United States and broke the record for digital download sales at the time of its release.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Wild Ones (song)",
"Flo Rida"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2263,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
77239
|
Early Wynn excelled at both football and baseball but suffered a leg injury forcing him out of football and focusing on baseball.
|
{
"evidence": [
"Early Wynn_sentence_30",
"Early Wynn_sentence_31"
],
"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:\nEarly Wynn excelled at both football and baseball but suffered a leg injury forcing him out of football and focusing on baseball.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Early Wynn_sentence_30",
"Early Wynn_sentence_31"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2264,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.626",
"value": "undefined"
},
{
"operation": "search",
"time": "17.745",
"value": "Early Wynn"
},
{
"operation": "Now on",
"time": "18.709",
"value": "Early Wynn"
},
{
"operation": "Page search",
"time": "124.709",
"value": "football"
},
{
"operation": "Highlighting",
"time": "130.218",
"value": "Early Wynn_sentence_30"
},
{
"operation": "Highlighting",
"time": "139.256",
"value": "Early Wynn_sentence_31"
},
{
"operation": "finish",
"time": "187.217",
"value": "finish"
}
]
}
|
59671
|
Some time in the 9 year of his reign, Tutankhamun died suddenly, leaving Ankhesenamun alone and without an heir about the age 21, then a blue glass ring of unknown provenance obtained in 1931 depicts the prenomen of Ay and the name of Ankhesenamun enclosed in cartouches indicating that Ankhesenamun married Ay shortly before she disappeared from history, although no monuments show her as great royal wife to him.
|
{
"evidence": [
"Ankhesenamun_sentence_23",
"Ankhesenamun_sentence_24",
"Ankhesenamun_sentence_25"
],
"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:\nSome time in the 9 year of his reign, Tutankhamun died suddenly, leaving Ankhesenamun alone and without an heir about the age 21, then a blue glass ring of unknown provenance obtained in 1931 depicts the prenomen of Ay and the name of Ankhesenamun enclosed in cartouches indicating that Ankhesenamun married Ay shortly before she disappeared from history, although no monuments show her as great royal wife to him.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Ankhesenamun_sentence_23",
"Ankhesenamun_sentence_24",
"Ankhesenamun_sentence_25"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2265,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.659",
"value": "?search="
},
{
"operation": "search",
"time": "25.584",
"value": "Ankhesenamun"
},
{
"operation": "Now on",
"time": "26.578",
"value": "Ankhesenamun"
},
{
"operation": "Highlighting",
"time": "53.566",
"value": "Ankhesenamun_sentence_23"
},
{
"operation": "Highlighting",
"time": "61.119",
"value": "Ankhesenamun_sentence_24"
},
{
"operation": "Highlighting",
"time": "68.181",
"value": "Ankhesenamun_sentence_25"
},
{
"operation": "finish",
"time": "91.685",
"value": "finish"
}
]
}
|
exfever_8731
|
Peyton Manning is an American former football quarterback who spent 14 seasons with an American football team that competes in one of the major North American professional sports leagues and the highest professional level of American football in the world.
|
{
"evidence": [
"Peyton Manning",
"Indianapolis Colts",
"National Football League"
],
"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:\nPeyton Manning is an American former football quarterback who spent 14 seasons with an American football team that competes in one of the major North American professional sports leagues and the highest professional level of American football in the world.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Peyton Manning",
"Indianapolis Colts",
"National Football League"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2266,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4456
|
James Vernon Taylor had his first No.1 hit in 1971 with his recording of a song that has been recorded by many artists over the years, including an English singer whose career spanned over seven decades.
|
{
"evidence": [
"James Taylor",
"You've Got a Friend",
"Dusty Springfield"
],
"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:\nJames Vernon Taylor had his first No.1 hit in 1971 with his recording of a song that has been recorded by many artists over the years, including an English singer whose career spanned over seven decades.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"James Taylor",
"You've Got a Friend",
"Dusty Springfield"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2267,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2583
|
Jock Stein was the first manager of Celtic F.C.
|
{
"evidence": [
"Celtic F.C.",
"Glasgow"
],
"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:\nJock Stein was the first manager of Celtic F.C.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Celtic F.C.",
"Glasgow"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2268,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5098
|
Unforgettable is a 2017 American drama thriller film starring an American actress who made her film debut in the film The Ugly Truth.
|
{
"evidence": [
"Unforgettable (2017 film)",
"Katherine Heigl"
],
"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:\nUnforgettable is a 2017 American drama thriller film starring an American actress who made her film debut in the film The Ugly Truth.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Unforgettable (2017 film)",
"Katherine Heigl"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2269,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
41798
|
James Trow was a director for the Ontario Mutual Life Insurance Company of Waterloo and became a warden for Perth County in 1871.
|
{
"evidence": [
"James Trow_sentence_6",
"James Trow_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:\nJames Trow was a director for the Ontario Mutual Life Insurance Company of Waterloo and became a warden for Perth County in 1871.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"James Trow_sentence_6",
"James Trow_sentence_7"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2270,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1",
"value": "?search="
},
{
"operation": "search",
"time": "5.105",
"value": "James Trow"
},
{
"operation": "Now on",
"time": "6.114",
"value": "James Trow"
},
{
"operation": "Highlighting",
"time": "10.508",
"value": "James Trow_sentence_6"
},
{
"operation": "Highlighting",
"time": "15.061",
"value": "James Trow_sentence_7"
},
{
"operation": "finish",
"time": "22.056",
"value": "finish"
}
]
}
|
exfever_3214
|
The Comedian is a 2016 American comedy-drama film that stars an American actress who has appeared in numerous films, including The Cable Guy.
|
{
"evidence": [
"The Comedian (2016 film)",
"Leslie Mann"
],
"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 Comedian is a 2016 American comedy-drama film that stars an American actress who has appeared in numerous films, including The Cable Guy.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Comedian (2016 film)",
"Leslie Mann"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2271,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6214
|
Megan Fox is one of the highest-paid actresses of all time.
|
{
"evidence": [
"Judd Apatow",
"This Is 40",
"Megan Fox"
],
"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:\nMegan Fox is one of the highest-paid actresses of all time.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Judd Apatow",
"This Is 40",
"Megan Fox"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2272,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
15914
|
The 1948 Rhode Island State Rams football team was an American football team that represented Rhode Island State College and had Bill Beck as head coach and finished in last place in the conference.
|
{
"evidence": [
"1948 Rhode Island State Rams football team_sentence_0",
"1948 Rhode Island State Rams football team_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:\nThe 1948 Rhode Island State Rams football team was an American football team that represented Rhode Island State College and had Bill Beck as head coach and finished in last place in the conference.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"1948 Rhode Island State Rams football team_sentence_0",
"1948 Rhode Island State Rams football team_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2273,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.154",
"value": "?search="
},
{
"operation": "Now on",
"time": "8.611",
"value": "?search="
},
{
"operation": "search",
"time": "24.832",
"value": "1948 Rhode Island State Rams football team"
},
{
"operation": "Now on",
"time": "25.679",
"value": "1948 Rhode Island State Rams football team"
},
{
"operation": "Highlighting",
"time": "27.816",
"value": "1948 Rhode Island State Rams football team_sentence_0"
},
{
"operation": "Highlighting",
"time": "47.769",
"value": "1948 Rhode Island State Rams football team_sentence_1"
},
{
"operation": "finish",
"time": "66.241",
"value": "finish"
}
]
}
|
26776
|
Following his debut at Portman Road, Greenhoff was one of the most vital components of Docherty's exciting young team; then in the 1973–74 season, Greenhoff's performances caused him to be named the Supporters Player of the Season.
|
{
"evidence": [
"Brian Greenhoff_sentence_12",
"Brian Greenhoff_sentence_13"
],
"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:\nFollowing his debut at Portman Road, Greenhoff was one of the most vital components of Docherty's exciting young team; then in the 1973–74 season, Greenhoff's performances caused him to be named the Supporters Player of the Season.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Brian Greenhoff_sentence_12",
"Brian Greenhoff_sentence_13"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2274,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.679",
"value": "?search="
},
{
"operation": "search",
"time": "149.943",
"value": "portman road"
},
{
"operation": "Now on",
"time": "151.099",
"value": "Portman Road"
},
{
"operation": "search",
"time": "165.36",
"value": "Greenhoff, Brian"
},
{
"operation": "Now on",
"time": "166.214",
"value": "Brian Greenhoff"
},
{
"operation": "Highlighting",
"time": "223.008",
"value": "Brian Greenhoff_sentence_12"
},
{
"operation": "Highlighting",
"time": "241.325",
"value": "Brian Greenhoff_sentence_13"
},
{
"operation": "finish",
"time": "255.097",
"value": "finish"
}
]
}
|
exfever_1395
|
War of the Worlds is a 2005 American science fiction action film based on the 1898 novel by an Irish writer who wrote dozens of novels, short stories, and works of social commentary, history, satire, biography, and autobiography.
|
{
"evidence": [
"War of the Worlds (2005 film)",
"H. G. Wells"
],
"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:\nWar of the Worlds is a 2005 American science fiction action film based on the 1898 novel by an Irish writer who wrote dozens of novels, short stories, and works of social commentary, history, satire, biography, and autobiography.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"War of the Worlds (2005 film)",
"H. G. Wells"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2275,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
22318
|
Bicycle Network, which has an office in the least populous city of Tasmania, was formed in 1975 and now has 45,000 members with 60 permanent staff.
|
{
"evidence": [
"Hobart_sentence_2",
"Bicycle Network_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:\nBicycle Network, which has an office in the least populous city of Tasmania, was formed in 1975 and now has 45,000 members with 60 permanent staff.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Hobart_sentence_2",
"Bicycle Network_sentence_8"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2276,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.623",
"value": "?search="
},
{
"operation": "search",
"time": "4.959",
"value": "Bicycle Network"
},
{
"operation": "Now on",
"time": "6.096",
"value": "Bicycle Network"
},
{
"operation": "hyperlink",
"time": "18.383",
"value": "Hobart"
},
{
"operation": "Now on",
"time": "19.4",
"value": "Hobart"
},
{
"operation": "Highlighting",
"time": "20.98",
"value": "Hobart_sentence_2"
},
{
"operation": "back-button-clicked",
"time": "22.346",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "22.477",
"value": "Bicycle Network"
},
{
"operation": "Highlighting",
"time": "23.783",
"value": "Bicycle Network_sentence_8"
},
{
"operation": "finish",
"time": "42.661",
"value": "finish"
}
]
}
|
exfever_3600
|
The Muse co-written with Monica Johnson, is a 1999 horror film starring an American actor who received an Academy Award nomination for Best Supporting Actor for 1987's Broadcast News.
|
{
"evidence": [
"The Muse (1999 film)",
"Albert Brooks"
],
"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 Muse co-written with Monica Johnson, is a 1999 horror film starring an American actor who received an Academy Award nomination for Best Supporting Actor for 1987's Broadcast News.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Muse (1999 film)",
"Albert Brooks"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2277,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
77470
|
South Hadley Canal (operation commencing in 1795) funds were raised locally after John Hancock signed the charter.
|
{
"evidence": [
"South Hadley Canal_sentence_1",
"South Hadley Canal_sentence_5",
"South Hadley Canal_sentence_7"
],
"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:\nSouth Hadley Canal (operation commencing in 1795) funds were raised locally after John Hancock signed the charter.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"South Hadley Canal_sentence_1",
"South Hadley Canal_sentence_5",
"South Hadley Canal_sentence_7"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2278,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.2",
"value": "?search="
},
{
"operation": "search",
"time": "15.248",
"value": "South Hadley Canal"
},
{
"operation": "Now on",
"time": "16.082",
"value": "South Hadley Canal"
},
{
"operation": "Highlighting",
"time": "26.535",
"value": "South Hadley Canal_sentence_1"
},
{
"operation": "Page search",
"time": "38.751",
"value": "John Hancock"
},
{
"operation": "Highlighting",
"time": "42.581",
"value": "South Hadley Canal_sentence_5"
},
{
"operation": "Highlighting",
"time": "48.405",
"value": "South Hadley Canal_sentence_7"
},
{
"operation": "finish",
"time": "76.822",
"value": "finish"
}
]
}
|
exfever_540
|
Lorazepam is used to treat an eating disorder in which people have trouble sleeping.
|
{
"evidence": [
"Lorazepam",
"Insomnia"
],
"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:\nLorazepam is used to treat an eating disorder in which people have trouble sleeping.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Lorazepam",
"Insomnia"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2279,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
91912
|
The Khezhakeno administrative circle had the least villages in Phek district.
|
{
"evidence": [
"Khezhakeno_sentence_4",
"Khezhakeno_sentence_20"
],
"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 Khezhakeno administrative circle had the least villages in Phek district.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Khezhakeno_sentence_4",
"Khezhakeno_sentence_20"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2280,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.628",
"value": "?search="
},
{
"operation": "search",
"time": "16.592",
"value": "Khezhakeno administrative circle"
},
{
"operation": "Now on",
"time": "17.726",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "22.975",
"value": "Khezhakeno"
},
{
"operation": "Now on",
"time": "24.199",
"value": "Khezhakeno"
},
{
"operation": "search",
"time": "122.719",
"value": "Khezhakeno administrative circle"
},
{
"operation": "Now on",
"time": "123.758",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "132.395",
"value": "Phek district"
},
{
"operation": "Now on",
"time": "133.647",
"value": "Phek district"
},
{
"operation": "hyperlink",
"time": "157.681",
"value": "3 Administration Phek district_section_3"
},
{
"operation": "hyperlink",
"time": "218.953",
"value": "Khezhakeno"
},
{
"operation": "Now on",
"time": "219.394",
"value": "Khezhakeno"
},
{
"operation": "search",
"time": "366.991",
"value": "The Khezhakeno administrative circle had the least villages in Phek district."
},
{
"operation": "Now on",
"time": "368.548",
"value": "undefined"
},
{
"operation": "search",
"time": "415.315",
"value": "The Khezhakeno administrative circle"
},
{
"operation": "Now on",
"time": "416.087",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "421.744",
"value": "Khezhakeno"
},
{
"operation": "Now on",
"time": "422.567",
"value": "Khezhakeno"
},
{
"operation": "Highlighting",
"time": "438.567",
"value": "Khezhakeno_sentence_4"
},
{
"operation": "Highlighting",
"time": "466.816",
"value": "Khezhakeno_sentence_20"
},
{
"operation": "finish",
"time": "471.024",
"value": "finish"
}
]
}
|
exfever_4700
|
It's Always Sunny in Philadelphia is now available to watch on Netflix.
|
{
"evidence": [
"It's Always Sunny in Philadelphia",
"It's Always Sunny in Philadelphia (season 9)"
],
"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:\nIt's Always Sunny in Philadelphia is now available to watch on Netflix.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"It's Always Sunny in Philadelphia",
"It's Always Sunny in Philadelphia (season 9)"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2281,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
13730
|
The Glen Canyon National Recreation Area, which was established in 1972, was created to increase tourism and was developed to allow access to Lake Powell via five marinas.
|
{
"evidence": [
"Glen Canyon National Recreation Area_sentence_5"
],
"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 Glen Canyon National Recreation Area, which was established in 1972, was created to increase tourism and was developed to allow access to Lake Powell via five marinas.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Glen Canyon National Recreation Area_sentence_5"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2282,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.881",
"value": "?search="
},
{
"operation": "search",
"time": "9.958",
"value": "Glen Canyon National Recreation Area"
},
{
"operation": "Now on",
"time": "11.001",
"value": "Glen Canyon National Recreation Area"
},
{
"operation": "Highlighting",
"time": "18.816",
"value": "Glen Canyon National Recreation Area_sentence_5"
},
{
"operation": "Page search",
"time": "68.763",
"value": "tourism"
},
{
"operation": "finish",
"time": "147.779",
"value": "finish"
}
]
}
|
exfever_622
|
Peter Davison is an American actor who stars in an ITV situation comedy starring Patricia Hodge and Matthew Kelly.
|
{
"evidence": [
"Peter Davison",
"Holding the Fort"
],
"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:\nPeter Davison is an American actor who stars in an ITV situation comedy starring Patricia Hodge and Matthew Kelly.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Peter Davison",
"Holding the Fort"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2283,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.