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 |
|---|---|---|---|---|---|---|---|---|
94771
|
Paul Gause, who is engaged to recording artist Arianna Grande, played baseball for Seton Hall University, but was not drafted out of college.
|
{
"evidence": [
"Paul Gause_sentence_21",
"Paul Gause_sentence_45"
],
"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:\nPaul Gause, who is engaged to recording artist Arianna Grande, played baseball for Seton Hall University, but was not drafted out of college.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Paul Gause_sentence_21",
"Paul Gause_sentence_45"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 784,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.01",
"value": "?search="
},
{
"operation": "search",
"time": "10.108",
"value": "Paul Gause"
},
{
"operation": "Now on",
"time": "11.162",
"value": "Paul Gause"
},
{
"operation": "Highlighting",
"time": "72.307",
"value": "Paul Gause_sentence_21"
},
{
"operation": "Highlighting",
"time": "106.246",
"value": "Paul Gause_sentence_45"
},
{
"operation": "finish",
"time": "112.163",
"value": "finish"
}
]
}
|
exfever_3536
|
Loki is a god in Norse mythology, who is married to Sigyn and had a son that was killed by Váli, according to the Gylfaginning section of Snorri Sturluson's Prose Edda.
|
{
"evidence": [
"Loki",
"Narfi and Nari"
],
"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:\nLoki is a god in Norse mythology, who is married to Sigyn and had a son that was killed by Váli, according to the Gylfaginning section of Snorri Sturluson's Prose Edda.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Loki",
"Narfi and Nari"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 785,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
70879
|
CrossLink International was founded in November 1996, it was inspired when a Baptist Sunday school class visited a hospital in Moscow which was established in 1147.
|
{
"evidence": [
"CrossLink International_sentence_4",
"CrossLink International_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:\nCrossLink International was founded in November 1996, it was inspired when a Baptist Sunday school class visited a hospital in Moscow which was established in 1147.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"CrossLink International_sentence_4",
"CrossLink International_sentence_5"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 786,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.388",
"value": "?search="
},
{
"operation": "search",
"time": "15.335",
"value": "CrossLink International"
},
{
"operation": "Now on",
"time": "16.761",
"value": "CrossLink International"
},
{
"operation": "Highlighting",
"time": "24.137",
"value": "CrossLink International_sentence_4"
},
{
"operation": "Highlighting",
"time": "29.013",
"value": "CrossLink International_sentence_5"
},
{
"operation": "Page search",
"time": "70.659",
"value": "1147"
},
{
"operation": "finish",
"time": "88.68",
"value": "finish"
}
]
}
|
91758
|
Ray Bolger demanded that the producers expand his role, then several rewrites later, de Mille herself was fired and replaced by Burt Shevelove (an American musical theater playwright); but only a few days after that, Shevelove exited.
|
{
"evidence": [
"Agnes de Mille_sentence_0",
"Agnes de Mille_sentence_1",
"Burt Shevelove_sentence_0"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nRay Bolger demanded that the producers expand his role, then several rewrites later, de Mille herself was fired and replaced by Burt Shevelove (an American musical theater playwright); but only a few days after that, Shevelove exited.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Agnes de Mille_sentence_0",
"Agnes de Mille_sentence_1",
"Burt Shevelove_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 787,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.714",
"value": "undefined"
},
{
"operation": "search",
"time": "9.606",
"value": "Roy Bolger"
},
{
"operation": "Now on",
"time": "11.962",
"value": "undefined"
},
{
"operation": "search",
"time": "19.238",
"value": "Ray Bolger"
},
{
"operation": "Now on",
"time": "20.157",
"value": "Ray Bolger"
},
{
"operation": "search",
"time": "122.15",
"value": "Burt Shevelove"
},
{
"operation": "Now on",
"time": "122.753",
"value": "Burt Shevelove"
},
{
"operation": "Highlighting",
"time": "125.15",
"value": "Burt Shevelove_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "126.576",
"value": "Burt Shevelove_sentence_0"
},
{
"operation": "search",
"time": "150.082",
"value": "De Mille"
},
{
"operation": "Now on",
"time": "151.024",
"value": "DeMille"
},
{
"operation": "hyperlink",
"time": "169.501",
"value": "Katherine DeMille"
},
{
"operation": "Now on",
"time": "170.276",
"value": "Katherine DeMille"
},
{
"operation": "search",
"time": "270.556",
"value": "Ray Bolger"
},
{
"operation": "Now on",
"time": "271.189",
"value": "Ray Bolger"
},
{
"operation": "hyperlink",
"time": "280.807",
"value": "Scarecrow"
},
{
"operation": "Now on",
"time": "281.592",
"value": "Scarecrow (Oz)"
},
{
"operation": "search",
"time": "340.304",
"value": "Ray Bolger"
},
{
"operation": "Now on",
"time": "341.429",
"value": "Ray Bolger"
},
{
"operation": "hyperlink",
"time": "354.526",
"value": "Babes in Toyland"
},
{
"operation": "Now on",
"time": "355.271",
"value": "Babes in Toyland (1961 film)"
},
{
"operation": "back-button-clicked",
"time": "386.674",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "386.782",
"value": "Ray Bolger"
},
{
"operation": "hyperlink",
"time": "409.56",
"value": "The Great Ziegfeld"
},
{
"operation": "Now on",
"time": "410.366",
"value": "The Great Ziegfeld"
},
{
"operation": "back-button-clicked",
"time": "456.892",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "457.008",
"value": "Ray Bolger"
},
{
"operation": "hyperlink",
"time": "461.634",
"value": "Sweethearts"
},
{
"operation": "Now on",
"time": "462.422",
"value": "Sweethearts (1938 film)"
},
{
"operation": "hyperlink",
"time": "476.331",
"value": "Ray Bolger"
},
{
"operation": "Now on",
"time": "476.755",
"value": "Ray Bolger"
},
{
"operation": "hyperlink",
"time": "503.061",
"value": "The Harvey Girls"
},
{
"operation": "Now on",
"time": "503.798",
"value": "The Harvey Girls"
},
{
"operation": "back-button-clicked",
"time": "528.554",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "528.67",
"value": "Ray Bolger"
},
{
"operation": "search",
"time": "591.202",
"value": "Burt Shevelove"
},
{
"operation": "Now on",
"time": "591.767",
"value": "Burt Shevelove"
},
{
"operation": "search",
"time": "622.358",
"value": "Contains...de Mille"
},
{
"operation": "Now on",
"time": "625.116",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "634.41",
"value": "Brigadoon"
},
{
"operation": "Now on",
"time": "635.223",
"value": "Brigadoon"
},
{
"operation": "back-button-clicked",
"time": "734.746",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "735.381",
"value": "undefined"
},
{
"operation": "search",
"time": "745.672",
"value": "Agnes de Mille"
},
{
"operation": "Now on",
"time": "746.701",
"value": "Agnes de Mille"
},
{
"operation": "Highlighting",
"time": "748.409",
"value": "Agnes de Mille_sentence_0"
},
{
"operation": "Highlighting",
"time": "816.728",
"value": "Agnes de Mille_sentence_1"
},
{
"operation": "search",
"time": "829.569",
"value": "Burt Shevelove"
},
{
"operation": "Now on",
"time": "830.149",
"value": "Burt Shevelove"
},
{
"operation": "Highlighting",
"time": "851.901",
"value": "Burt Shevelove_sentence_0"
},
{
"operation": "finish",
"time": "863.66",
"value": "finish"
}
]
}
|
exfever_665
|
Jennifer Garner was born in Houston, in a state in the South Central region that shares borders to the northeast with a landlocked state in the South Central United States.
|
{
"evidence": [
"Jennifer Garner",
"Texas",
"Arkansas"
],
"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:\nJennifer Garner was born in Houston, in a state in the South Central region that shares borders to the northeast with a landlocked state in the South Central United States.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jennifer Garner",
"Texas",
"Arkansas"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 788,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
58191
|
Misaje is both a town and commune in the Northwest Region of the country of Cameroon, whose coastline touches the Bight of Biafra, the Atlantic Ocean and the Gulf of Guinea.
|
{
"evidence": [
"Misaje_sentence_0",
"Cameroon_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:\nMisaje is both a town and commune in the Northwest Region of the country of Cameroon, whose coastline touches the Bight of Biafra, the Atlantic Ocean and the Gulf of Guinea.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Misaje_sentence_0",
"Cameroon_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 789,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.321",
"value": "?search="
},
{
"operation": "search",
"time": "10.018",
"value": "Misaje"
},
{
"operation": "Now on",
"time": "11.744",
"value": "Misaje"
},
{
"operation": "Highlighting",
"time": "20.006",
"value": "Misaje_sentence_0"
},
{
"operation": "hyperlink",
"time": "65.553",
"value": "Cameroon"
},
{
"operation": "Now on",
"time": "67.7",
"value": "Cameroon"
},
{
"operation": "Highlighting",
"time": "72.194",
"value": "Cameroon_sentence_4"
},
{
"operation": "finish",
"time": "102.595",
"value": "finish"
}
]
}
|
60943
|
Juliana Geran Pilon (Born in Romania) worked at a University in Atlanta before relocating to Stanford University, and she was never able to do a fellowship.
|
{
"evidence": [
"Juliana Geran Pilon_sentence_12"
],
"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:\nJuliana Geran Pilon (Born in Romania) worked at a University in Atlanta before relocating to Stanford University, and she was never able to do a fellowship.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Juliana Geran Pilon_sentence_12"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 790,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "9.482",
"value": "?search="
},
{
"operation": "search",
"time": "28.422",
"value": "Juliana Geran Pilon"
},
{
"operation": "Now on",
"time": "29.319",
"value": "Juliana Geran Pilon"
},
{
"operation": "Highlighting",
"time": "48.363",
"value": "Juliana Geran Pilon_sentence_0"
},
{
"operation": "Highlighting",
"time": "76.276",
"value": "Juliana Geran Pilon_sentence_10"
},
{
"operation": "Highlighting deleted",
"time": "89.378",
"value": "Juliana Geran Pilon_sentence_10"
},
{
"operation": "Highlighting",
"time": "91.271",
"value": "Juliana Geran Pilon_sentence_12"
},
{
"operation": "Highlighting deleted",
"time": "107.756",
"value": "Juliana Geran Pilon_sentence_0"
},
{
"operation": "finish",
"time": "116.118",
"value": "finish"
}
]
}
|
exfever_3825
|
Franklin Delano Roosevelt was an American politician who implemented a series of programs, including both laws passed by the legislature of the federal government of Canada.
|
{
"evidence": [
"Franklin D. Roosevelt",
"New Deal",
"United States Congress"
],
"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:\nFranklin Delano Roosevelt was an American politician who implemented a series of programs, including both laws passed by the legislature of the federal government of Canada.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Franklin D. Roosevelt",
"New Deal",
"United States Congress"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 791,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6840
|
Paul Samuel Feig is an American actor, comedian, and director who directed a remake of the 1984 film of the same name in the 2016, an American genre of speculative fiction that exploits or is centered on supernatural themes.
|
{
"evidence": [
"Paul Feig",
"Ghostbusters (2016 film)",
"Supernatural fiction"
],
"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:\nPaul Samuel Feig is an American actor, comedian, and director who directed a remake of the 1984 film of the same name in the 2016, an American genre of speculative fiction that exploits or is centered on supernatural themes.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Paul Feig",
"Ghostbusters (2016 film)",
"Supernatural fiction"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 792,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
94565
|
Vidame de Chartres was put in the Bastille as told by the novel in La Princesse de Clèves, authored by Madame de La Fayette.
|
{
"evidence": [
"La Princesse de Clèves_sentence_0",
"La Princesse de Clèves_sentence_2"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nVidame de Chartres was put in the Bastille as told by the novel in La Princesse de Clèves, authored by Madame de La Fayette.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"La Princesse de Clèves_sentence_0",
"La Princesse de Clèves_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 793,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.26",
"value": "?search="
},
{
"operation": "search",
"time": "16.907",
"value": "La Princesse de Clèves"
},
{
"operation": "Now on",
"time": "17.817",
"value": "La Princesse de Clèves"
},
{
"operation": "Highlighting",
"time": "24.719",
"value": "La Princesse de Clèves_sentence_0"
},
{
"operation": "Page search",
"time": "34.354",
"value": "Madame"
},
{
"operation": "Highlighting",
"time": "38.702",
"value": "La Princesse de Clèves_sentence_2"
},
{
"operation": "Page search",
"time": "57.033",
"value": "Bastille"
},
{
"operation": "Page search",
"time": "97.123",
"value": "Chartres"
},
{
"operation": "page-search-reset",
"time": "110.02",
"value": "page-search-reset"
},
{
"operation": "Page search",
"time": "124.631",
"value": "put in"
},
{
"operation": "Highlighting deleted",
"time": "148.587",
"value": "La Princesse de Clèves_sentence_2"
},
{
"operation": "Highlighting",
"time": "149.875",
"value": "La Princesse de Clèves_sentence_2"
},
{
"operation": "finish",
"time": "157.25",
"value": "finish"
}
]
}
|
67405
|
İbrahim Balaban was sentenced to six months in Bursa Prison and payment of a fine for growing cannabis (a psychoactive drug from the Cannabis plant used primarily for medical or recreational purposes) in 1937, and was subsequently increased to three years in prison because he was unable to pay the fine, which resulted in him jobbing in the prison as a barber to earn money.
|
{
"evidence": [
"Ä°brahim Balaban_sentence_5",
"Cannabis (drug)_sentence_5",
"Ä°brahim Balaban_sentence_6",
"Ä°brahim Balaban_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:\nİbrahim Balaban was sentenced to six months in Bursa Prison and payment of a fine for growing cannabis (a psychoactive drug from the Cannabis plant used primarily for medical or recreational purposes) in 1937, and was subsequently increased to three years in prison because he was unable to pay the fine, which resulted in him jobbing in the prison as a barber to earn money.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Ä°brahim Balaban_sentence_5",
"Cannabis (drug)_sentence_5",
"Ä°brahim Balaban_sentence_6",
"Ä°brahim Balaban_sentence_7"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 794,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "3.485",
"value": "?search="
},
{
"operation": "search",
"time": "17.481",
"value": "İbrahim Balaban"
},
{
"operation": "Now on",
"time": "18.442",
"value": "Ä°brahim Balaban"
},
{
"operation": "Highlighting",
"time": "92.803",
"value": "Ä°brahim Balaban_sentence_5"
},
{
"operation": "hyperlink",
"time": "104.122",
"value": "cannabis"
},
{
"operation": "Now on",
"time": "107.706",
"value": "Cannabis (drug)"
},
{
"operation": "Highlighting",
"time": "110.374",
"value": "Cannabis (drug)_sentence_5"
},
{
"operation": "back-button-clicked",
"time": "112.309",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "112.442",
"value": "Ä°brahim Balaban"
},
{
"operation": "Highlighting",
"time": "120.492",
"value": "Ä°brahim Balaban_sentence_6"
},
{
"operation": "Highlighting",
"time": "122.815",
"value": "Ä°brahim Balaban_sentence_7"
},
{
"operation": "finish",
"time": "175.638",
"value": "finish"
}
]
}
|
68607
|
Upon arrival, Black Lightning fights Anissa, but the latter manages to escape, hence her identity remains unknown.
|
{
"evidence": [
"List of Black Lightning characters_sentence_28"
],
"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:\nUpon arrival, Black Lightning fights Anissa, but the latter manages to escape, hence her identity remains unknown.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"List of Black Lightning characters_sentence_28"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 795,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.212",
"value": "undefined"
},
{
"operation": "search",
"time": "18.531",
"value": "Contains...Upon arrival, Black Lightning fights Anissa, but the latter manages to escape, hence her identity remains unknown."
},
{
"operation": "Now on",
"time": "22.226",
"value": "undefined"
},
{
"operation": "search",
"time": "44.689",
"value": "Black Lightning fights Anissa"
},
{
"operation": "Now on",
"time": "45.706",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "80.212",
"value": "Black Lightning (season 2)"
},
{
"operation": "Now on",
"time": "81.498",
"value": "Black Lightning (season 2)"
},
{
"operation": "Page search",
"time": "84.744",
"value": "Black Lightning fights Anissa"
},
{
"operation": "Page search",
"time": "99.561",
"value": "Black lighteningAnissa"
},
{
"operation": "Page search",
"time": "100.648",
"value": "Black lightening Anissa"
},
{
"operation": "Page search",
"time": "115.747",
"value": "Black lightening fights"
},
{
"operation": "Page search",
"time": "131.213",
"value": "identity"
},
{
"operation": "back-button-clicked",
"time": "182.888",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "183.741",
"value": "undefined"
},
{
"operation": "search",
"time": "209.157",
"value": "list of black lightening episodes"
},
{
"operation": "Now on",
"time": "210.468",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "224.14",
"value": "list of black lightning episodes"
},
{
"operation": "Now on",
"time": "225.711",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "228.15",
"value": "List of Black Lightning episodes"
},
{
"operation": "Now on",
"time": "235.177",
"value": "List of Black Lightning episodes"
},
{
"operation": "back-button-clicked",
"time": "235.952",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "237.928",
"value": "undefined"
},
{
"operation": "search",
"time": "265.253",
"value": "Anissa escapes black lightning"
},
{
"operation": "Now on",
"time": "266.113",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "281.457",
"value": "List of Black Lightning characters"
},
{
"operation": "Now on",
"time": "283.094",
"value": "List of Black Lightning characters"
},
{
"operation": "Page search",
"time": "291.616",
"value": "identity"
},
{
"operation": "back-button-clicked",
"time": "327.946",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "328.668",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "375.128",
"value": "List of Black Lightning characters"
},
{
"operation": "Now on",
"time": "375.862",
"value": "List of Black Lightning characters"
},
{
"operation": "Page search",
"time": "381.488",
"value": "anissa"
},
{
"operation": "Page search",
"time": "419.858",
"value": "masked"
},
{
"operation": "Highlighting",
"time": "427.484",
"value": "List of Black Lightning characters_sentence_27"
},
{
"operation": "Highlighting",
"time": "495.85",
"value": "List of Black Lightning characters_sentence_28"
},
{
"operation": "Highlighting deleted",
"time": "497.235",
"value": "List of Black Lightning characters_sentence_27"
},
{
"operation": "finish",
"time": "512.564",
"value": "finish"
}
]
}
|
86552
|
The 2018 Offaly Senior Football Championship was the 121st edition of the competition, though it was not run that year by Offaly GAA, one of the GAA's 32 country boards.
|
{
"evidence": [
"2018 Offaly Senior Football Championship_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 2018 Offaly Senior Football Championship was the 121st edition of the competition, though it was not run that year by Offaly GAA, one of the GAA's 32 country boards.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"2018 Offaly Senior Football Championship_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 796,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.424",
"value": "?search="
},
{
"operation": "search",
"time": "13.121",
"value": "2018 Offaly Senior Football Championship"
},
{
"operation": "Now on",
"time": "13.846",
"value": "2018 Offaly Senior Football Championship"
},
{
"operation": "Highlighting",
"time": "17.708",
"value": "2018 Offaly Senior Football Championship_sentence_0"
},
{
"operation": "hyperlink",
"time": "92.447",
"value": "Offaly GAA's"
},
{
"operation": "Now on",
"time": "93.213",
"value": "Offaly GAA"
},
{
"operation": "back-button-clicked",
"time": "99.992",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "100.08",
"value": "2018 Offaly Senior Football Championship"
},
{
"operation": "finish",
"time": "108.589",
"value": "finish"
}
]
}
|
exfever_7919
|
A pet is a companion multicellular organism in the biological kingdom Plantae that is kept primarily for a person's company.
|
{
"evidence": [
"Pet",
"Animal"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nA pet is a companion multicellular organism in the biological kingdom Plantae that is kept primarily for a person's company.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Pet",
"Animal"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 797,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4896
|
Jack Black is an American actor, comedian, musician, and songwriter who starred in the 2011 American biographical black rom-com film.
|
{
"evidence": [
"Jack Black",
"Bernie (2011 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:\nJack Black is an American actor, comedian, musician, and songwriter who starred in the 2011 American biographical black rom-com film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jack Black",
"Bernie (2011 film)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 798,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
53495
|
Arpiar Aslanian and his wife moved to Paris in 1925, where Arpiar became a general laborer before joining the French Communist Party in 1940.
|
{
"evidence": [
"Arpiar Aslanian_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:\nArpiar Aslanian and his wife moved to Paris in 1925, where Arpiar became a general laborer before joining the French Communist Party in 1940.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Arpiar Aslanian_sentence_8"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 799,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.986",
"value": "?search="
},
{
"operation": "search",
"time": "8.207",
"value": "Arpiar Aslanian"
},
{
"operation": "Now on",
"time": "8.889",
"value": "Arpiar Aslanian"
},
{
"operation": "Highlighting",
"time": "107.778",
"value": "Arpiar Aslanian_sentence_8"
},
{
"operation": "finish",
"time": "113.546",
"value": "finish"
}
]
}
|
exfever_8388
|
Jay Sekulow appears frequently as a guest commentator in an American Christian media television network and production company located in the Mid-Atlantic and Southeastern regions of the United States.
|
{
"evidence": [
"Jay Sekulow",
"Christian Broadcasting Network",
"Virginia"
],
"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:\nJay Sekulow appears frequently as a guest commentator in an American Christian media television network and production company located in the Mid-Atlantic and Southeastern regions of the United States.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jay Sekulow",
"Christian Broadcasting Network",
"Virginia"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 800,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
35543
|
Lyn Bell played professional baseball as a second baseman from 1906 to 1914 – in the Southern Michigan League for Saginaw in 1906, and Kalamazoo in 1907 and 1908.
|
{
"evidence": [
"Lynn Bell_sentence_6",
"Lynn Bell_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:\nLyn Bell played professional baseball as a second baseman from 1906 to 1914 – in the Southern Michigan League for Saginaw in 1906, and Kalamazoo in 1907 and 1908.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Lynn Bell_sentence_6",
"Lynn Bell_sentence_7"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 801,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0",
"value": "?search="
},
{
"operation": "search",
"time": "0.009",
"value": "Lyn Bell"
},
{
"operation": "Now on",
"time": "0.01",
"value": "Lyn Bell"
},
{
"operation": "Highlighting",
"time": "0.025",
"value": "Lyn Bell_sentence_0"
},
{
"operation": "Highlighting",
"time": "0.025",
"value": "Lyn Bell_title"
},
{
"operation": "search",
"time": "0.049",
"value": "Southern Michigan League"
},
{
"operation": "Now on",
"time": "0.05",
"value": "Southern Michigan League"
},
{
"operation": "hyperlink",
"time": "0.064",
"value": "Saginaw Wa-was"
},
{
"operation": "Now on",
"time": "0.065",
"value": "Saginaw Bears"
},
{
"operation": "Page search",
"time": "0.079",
"value": "lyn"
},
{
"operation": "Highlighting",
"time": "0.089",
"value": "Saginaw Bears_sentence_0"
},
{
"operation": "Highlighting",
"time": "0.089",
"value": "Saginaw Bears_title"
},
{
"operation": "finish",
"time": "0.102",
"value": "finish"
},
{
"operation": "Now on",
"time": "1620412831.359",
"value": "Lyn Bell"
},
{
"operation": "search",
"time": "1620412849.84",
"value": "Lynn Bell"
},
{
"operation": "Now on",
"time": "1620412850.743",
"value": "Lynn Bell"
},
{
"operation": "Highlighting",
"time": "1620412860.171",
"value": "Lynn Bell_sentence_7"
},
{
"operation": "Highlighting deleted",
"time": "1620412864.819",
"value": "Lynn Bell_sentence_7"
},
{
"operation": "Highlighting",
"time": "1620412865.236",
"value": "Lynn Bell_sentence_6"
},
{
"operation": "Highlighting",
"time": "1620412865.752",
"value": "Lynn Bell_sentence_7"
},
{
"operation": "finish",
"time": "1620412872.06",
"value": "finish"
}
]
}
|
10718
|
European financial institutions could not easily lend to the workers, rendering labor immobile because of capital market imperfections; so to address this imperfection, the Virginia Company would allow laborers to borrow against their future earnings for a fixed number of years.
|
{
"evidence": [
"Plymouth Company_sentence_4",
"Virginia Company_sentence_0"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nEuropean financial institutions could not easily lend to the workers, rendering labor immobile because of capital market imperfections; so to address this imperfection, the Virginia Company would allow laborers to borrow against their future earnings for a fixed number of years.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Plymouth Company_sentence_4",
"Virginia Company_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 802,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.244",
"value": "?search="
},
{
"operation": "search",
"time": "25.826",
"value": "Virginia Company"
},
{
"operation": "Now on",
"time": "27.194",
"value": "Virginia Company"
},
{
"operation": "Highlighting",
"time": "44.901",
"value": "Virginia Company_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "55.288",
"value": "Virginia Company_sentence_1"
},
{
"operation": "hyperlink",
"time": "121.446",
"value": "Plymouth Company"
},
{
"operation": "Now on",
"time": "122.629",
"value": "Plymouth Company"
},
{
"operation": "Highlighting",
"time": "130.801",
"value": "Plymouth Company_sentence_4"
},
{
"operation": "hyperlink",
"time": "149.968",
"value": "Virginia Company#Plymouth Company"
},
{
"operation": "Now on",
"time": "150.483",
"value": "Virginia Company#Plymouth Company"
},
{
"operation": "hyperlink",
"time": "155.82",
"value": "London Company"
},
{
"operation": "Now on",
"time": "156.666",
"value": "London Company"
},
{
"operation": "hyperlink",
"time": "257.138",
"value": "Richard Hakluyt"
},
{
"operation": "Now on",
"time": "258.007",
"value": "Richard Hakluyt"
},
{
"operation": "back-button-clicked",
"time": "267.635",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "267.765",
"value": "London Company"
},
{
"operation": "search",
"time": "314.312",
"value": "Virginia Company"
},
{
"operation": "Now on",
"time": "315.216",
"value": "Virginia Company"
},
{
"operation": "Highlighting",
"time": "316.935",
"value": "Virginia Company_sentence_0"
},
{
"operation": "Highlighting",
"time": "324.66",
"value": "Virginia Company_cell_0_0_1"
},
{
"operation": "Highlighting",
"time": "324.663",
"value": "Virginia Company_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "381.221",
"value": "Virginia Company_cell_0_0_1"
},
{
"operation": "Highlighting deleted",
"time": "381.223",
"value": "Virginia Company_header_cell_0_0_0"
},
{
"operation": "hyperlink",
"time": "382.837",
"value": "London Company"
},
{
"operation": "Now on",
"time": "383.775",
"value": "London Company"
},
{
"operation": "finish",
"time": "433.925",
"value": "finish"
}
]
}
|
exfever_7690
|
Hotel Transylvania is a British animated media franchise produced by an American animation studio owned by an American diversified multinational mass media and entertainment studio conglomerate.
|
{
"evidence": [
"Hotel Transylvania",
"Sony Pictures Animation",
"Sony Pictures"
],
"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 British animated media franchise produced by an American animation studio owned by an American diversified multinational mass media and entertainment studio conglomerate.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Hotel Transylvania",
"Sony Pictures Animation",
"Sony Pictures"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 803,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7535
|
The World According to Paris is an American reality TV series filmed with Hilton's court-ordered community service stemming from her arrest in a major metropolitan area in the southern part of the U.S. state of Nevada.
|
{
"evidence": [
"The World According to Paris",
"Las Vegas Valley"
],
"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 World According to Paris is an American reality TV series filmed with Hilton's court-ordered community service stemming from her arrest in a major metropolitan area in the southern part of the U.S. state of Nevada.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The World According to Paris",
"Las Vegas Valley"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 804,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
76004
|
The Ballinora has a replica which is located in Munster, Ireland.
|
{
"evidence": [
"Ballinora_sentence_0"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Ballinora has a replica which is located in Munster, Ireland.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Ballinora_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 805,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.902",
"value": "?search="
},
{
"operation": "search",
"time": "12.091",
"value": "Ballinora"
},
{
"operation": "Now on",
"time": "13.035",
"value": "Ballinora"
},
{
"operation": "search",
"time": "44.745",
"value": "Contains...The Ballinora"
},
{
"operation": "Now on",
"time": "45.579",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "68.607",
"value": "Ballinora"
},
{
"operation": "Now on",
"time": "69.458",
"value": "Ballinora"
},
{
"operation": "Highlighting",
"time": "103.963",
"value": "Ballinora_sentence_0"
},
{
"operation": "finish",
"time": "149.293",
"value": "finish"
}
]
}
|
exfever_4526
|
Jon Snow is a fictional character in the A Song of Ice and Fire by George R. R. Martin, a speculative non-fiction novel involving magical elements.
|
{
"evidence": [
"Jon Snow (character)",
"Fantasy"
],
"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:\nJon Snow is a fictional character in the A Song of Ice and Fire by George R. R. Martin, a speculative non-fiction novel involving magical elements.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jon Snow (character)",
"Fantasy"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 806,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
43838
|
Donegal's county teams have played since their foundation neither in green nor gold kits; and the classic Donegal kit was composed of a green shirt with a golden hoop, green shorts and green and yellow socks (identical to Kerry).
|
{
"evidence": [
"Donegal county football team_sentence_12",
"Donegal county football team_sentence_14"
],
"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:\nDonegal's county teams have played since their foundation neither in green nor gold kits; and the classic Donegal kit was composed of a green shirt with a golden hoop, green shorts and green and yellow socks (identical to Kerry).\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Donegal county football team_sentence_12",
"Donegal county football team_sentence_14"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 807,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.977",
"value": "?search="
},
{
"operation": "search",
"time": "27.236",
"value": "donegal team"
},
{
"operation": "Now on",
"time": "28.87",
"value": "undefined"
},
{
"operation": "search",
"time": "41.203",
"value": "donegal county team"
},
{
"operation": "Now on",
"time": "42.444",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "58.953",
"value": "Neil Gallagher (Donegal footballer)"
},
{
"operation": "Now on",
"time": "59.617",
"value": "Neil Gallagher (Donegal footballer)"
},
{
"operation": "hyperlink",
"time": "62.791",
"value": "Donegal county team"
},
{
"operation": "Now on",
"time": "63.257",
"value": "Donegal county football team"
},
{
"operation": "Page search",
"time": "77.401",
"value": "green"
},
{
"operation": "Highlighting",
"time": "83.393",
"value": "Donegal county football team_sentence_12"
},
{
"operation": "Highlighting",
"time": "124.373",
"value": "Donegal county football team_sentence_14"
},
{
"operation": "finish",
"time": "136.149",
"value": "finish"
}
]
}
|
95246
|
Open Bible Standard Churches can be traced to the Azusa Street Revival, which took place in Los Angeles on April 9, 1906, and the early teachings of Martin Luther.
|
{
"evidence": [
"Open Bible Standard Churches_sentence_8",
"Azusa Street Revival_sentence_0",
"Azusa Street Revival_sentence_2",
"Azusa Street Revival_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:\nOpen Bible Standard Churches can be traced to the Azusa Street Revival, which took place in Los Angeles on April 9, 1906, and the early teachings of Martin Luther.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Open Bible Standard Churches_sentence_8",
"Azusa Street Revival_sentence_0",
"Azusa Street Revival_sentence_2",
"Azusa Street Revival_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 808,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.414",
"value": "?search="
},
{
"operation": "search",
"time": "15.856",
"value": "Open Bible Standard Churches"
},
{
"operation": "Now on",
"time": "16.738",
"value": "Open Bible Standard Churches"
},
{
"operation": "Highlighting",
"time": "39.615",
"value": "Open Bible Standard Churches_sentence_8"
},
{
"operation": "hyperlink",
"time": "66.148",
"value": "Azusa Street Revival"
},
{
"operation": "Now on",
"time": "67.659",
"value": "Azusa Street Revival"
},
{
"operation": "Highlighting",
"time": "73.629",
"value": "Azusa Street Revival_sentence_0"
},
{
"operation": "Highlighting",
"time": "76.312",
"value": "Azusa Street Revival_sentence_2"
},
{
"operation": "back-button-clicked",
"time": "149.667",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "149.738",
"value": "Open Bible Standard Churches"
},
{
"operation": "hyperlink",
"time": "304.321",
"value": "Azusa Street Revival"
},
{
"operation": "Now on",
"time": "304.999",
"value": "Azusa Street Revival"
},
{
"operation": "Highlighting",
"time": "316.605",
"value": "Azusa Street Revival_sentence_1"
},
{
"operation": "finish",
"time": "389.043",
"value": "finish"
}
]
}
|
exfever_3540
|
Jean Grey is a fictional character who experienced a transformation in the X-Men storyline in the fictional Marvel Comics Universe.
|
{
"evidence": [
"Jean Grey",
"The Dark Phoenix Saga"
],
"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:\nJean Grey is a fictional character who experienced a transformation in the X-Men storyline in the fictional Marvel Comics Universe.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jean Grey",
"The Dark Phoenix Saga"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 809,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
34093
|
The copyright of the Encyclopaedia passed into the hands of Adam Black, who was recognized as one of the principal booksellers in his city, and a few friends in 1827.
|
{
"evidence": [
"Adam Black_sentence_8",
"Adam Black_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 copyright of the Encyclopaedia passed into the hands of Adam Black, who was recognized as one of the principal booksellers in his city, and a few friends in 1827.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Adam Black_sentence_8",
"Adam Black_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 810,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.584",
"value": "?search="
},
{
"operation": "search",
"time": "59.716",
"value": "copyright of the Encyclopaedia"
},
{
"operation": "Now on",
"time": "62.12",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "68.325",
"value": "Adam Black"
},
{
"operation": "Now on",
"time": "69.367",
"value": "Adam Black"
},
{
"operation": "Page search",
"time": "96.01",
"value": "enclyopedia"
},
{
"operation": "Page search",
"time": "111.445",
"value": "enclyopaedia"
},
{
"operation": "Page search",
"time": "116.538",
"value": "enclyo"
},
{
"operation": "Highlighting",
"time": "129.609",
"value": "Adam Black_sentence_2"
},
{
"operation": "Highlighting",
"time": "138.81",
"value": "Adam Black_sentence_6"
},
{
"operation": "Highlighting",
"time": "148.538",
"value": "Adam Black_sentence_6"
},
{
"operation": "Highlighting",
"time": "158.51",
"value": "Adam Black_sentence_2"
},
{
"operation": "Page search",
"time": "166.314",
"value": "hands"
},
{
"operation": "Highlighting",
"time": "178.63",
"value": "Adam Black_sentence_8"
},
{
"operation": "Highlighting deleted",
"time": "182.124",
"value": "Adam Black_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "184.557",
"value": "Adam Black_sentence_8"
},
{
"operation": "Highlighting deleted",
"time": "187.761",
"value": "Adam Black_sentence_6"
},
{
"operation": "Highlighting",
"time": "188.788",
"value": "Adam Black_sentence_8"
},
{
"operation": "Highlighting",
"time": "199.682",
"value": "Adam Black_sentence_6"
},
{
"operation": "finish",
"time": "216.151",
"value": "finish"
}
]
}
|
80618
|
XCOR Lynx, a proposed suborbital horizontal-takeoff, horizontal-landing (HTHL), rocket-powered spaceplane, that only reached the stage one of its development.
|
{
"evidence": [
"XCOR Lynx_sentence_0",
"XCOR Lynx_sentence_5",
"XCOR Lynx_sentence_21"
],
"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:\nXCOR Lynx, a proposed suborbital horizontal-takeoff, horizontal-landing (HTHL), rocket-powered spaceplane, that only reached the stage one of its development.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"XCOR Lynx_sentence_0",
"XCOR Lynx_sentence_5",
"XCOR Lynx_sentence_21"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 811,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.301",
"value": "?search="
},
{
"operation": "search",
"time": "18.966",
"value": "XCOR Lynx"
},
{
"operation": "Now on",
"time": "19.921",
"value": "XCOR Lynx"
},
{
"operation": "Highlighting",
"time": "221.126",
"value": "XCOR Lynx_sentence_0"
},
{
"operation": "Page search",
"time": "265.424",
"value": "stage one"
},
{
"operation": "Highlighting",
"time": "293.184",
"value": "XCOR Lynx_sentence_5"
},
{
"operation": "Highlighting",
"time": "326.344",
"value": "XCOR Lynx_sentence_21"
},
{
"operation": "finish",
"time": "331.796",
"value": "finish"
}
]
}
|
exfever_5562
|
Mutiny on the Bounty is a 1962 epic historical drama film with a screenplay written by an American screenwriter and film director who was born into a theatrical family in New York.
|
{
"evidence": [
"Mutiny on the Bounty (1962 film)",
"Charles Lederer"
],
"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:\nMutiny on the Bounty is a 1962 epic historical drama film with a screenplay written by an American screenwriter and film director who was born into a theatrical family in New York.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Mutiny on the Bounty (1962 film)",
"Charles Lederer"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 812,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3555
|
Grace Avery VanderWaal is an American singer, songwriter, and actress who released the debut EP, the winner of the eleventh season of the American talent show competition series that was broadcast on NBC from May 31 to September 11, 2018.
|
{
"evidence": [
"Grace VanderWaal",
"Perfectly Imperfect (EP)",
"America's Got Talent (season 11)"
],
"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:\nGrace Avery VanderWaal is an American singer, songwriter, and actress who released the debut EP, the winner of the eleventh season of the American talent show competition series that was broadcast on NBC from May 31 to September 11, 2018.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Grace VanderWaal",
"Perfectly Imperfect (EP)",
"America's Got Talent (season 11)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 813,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
80434
|
The monkey saddle, belonging to the class of saddle surfaces, has an isolated umbilical point with zero Gaussian curvature or the product of the principal curvatures, κ1 and κ2 at the origin.
|
{
"evidence": [
"Monkey saddle_sentence_2",
"Monkey saddle_sentence_4",
"Gaussian curvature_sentence_0"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe monkey saddle, belonging to the class of saddle surfaces, has an isolated umbilical point with zero Gaussian curvature or the product of the principal curvatures, κ1 and κ2 at the origin.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Monkey saddle_sentence_2",
"Monkey saddle_sentence_4",
"Gaussian curvature_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 814,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.619",
"value": "undefined"
},
{
"operation": "search",
"time": "8.655",
"value": "monkey saddle"
},
{
"operation": "Now on",
"time": "9.707",
"value": "Monkey saddle"
},
{
"operation": "Highlighting",
"time": "12.662",
"value": "Monkey saddle_sentence_2"
},
{
"operation": "Highlighting",
"time": "191.033",
"value": "Monkey saddle_sentence_4"
},
{
"operation": "Highlighting",
"time": "440.335",
"value": "Monkey saddle_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "458.024",
"value": "Monkey saddle_sentence_4"
},
{
"operation": "Highlighting",
"time": "460.88",
"value": "Monkey saddle_sentence_2"
},
{
"operation": "Highlighting",
"time": "467.072",
"value": "Monkey saddle_sentence_4"
},
{
"operation": "hyperlink",
"time": "475.193",
"value": "Gaussian curvature"
},
{
"operation": "Now on",
"time": "476.603",
"value": "Gaussian curvature"
},
{
"operation": "Highlighting",
"time": "479.168",
"value": "Gaussian curvature_sentence_0"
},
{
"operation": "finish",
"time": "485.823",
"value": "finish"
}
]
}
|
75559
|
Petra Nielsen (born Petra Magdalena Nielsen 1 February 1965 in Stockholm the capital and most populous urban area of Sweden as well as in Scandinavia) is a Swedish singer and actress.
|
{
"evidence": [
"Petra Nielsen_sentence_0",
"Stockholm_sentence_3"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nPetra Nielsen (born Petra Magdalena Nielsen 1 February 1965 in Stockholm the capital and most populous urban area of Sweden as well as in Scandinavia) is a Swedish singer and actress.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Petra Nielsen_sentence_0",
"Stockholm_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 815,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.356",
"value": "?search="
},
{
"operation": "search",
"time": "14.674",
"value": "Petra Nielsen"
},
{
"operation": "Now on",
"time": "15.467",
"value": "Petra Nielsen"
},
{
"operation": "Highlighting",
"time": "26.057",
"value": "Petra Nielsen_sentence_0"
},
{
"operation": "hyperlink",
"time": "39.185",
"value": "Stockholm"
},
{
"operation": "Now on",
"time": "40.745",
"value": "Stockholm"
},
{
"operation": "Highlighting",
"time": "42.679",
"value": "Stockholm_sentence_3"
},
{
"operation": "finish",
"time": "183.209",
"value": "finish"
}
]
}
|
85714
|
Itaru Hinoue is the speudonym of a Japanese artist from Osaka which is a prefecture of Japan located in the Kansai region of Honshu.
|
{
"evidence": [
"Itaru Hinoue_sentence_0",
"Osaka Prefecture_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:\nItaru Hinoue is the speudonym of a Japanese artist from Osaka which is a prefecture of Japan located in the Kansai region of Honshu.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Itaru Hinoue_sentence_0",
"Osaka Prefecture_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 816,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.71",
"value": "?search="
},
{
"operation": "search",
"time": "25.384",
"value": "Itaru Hinoue"
},
{
"operation": "Now on",
"time": "26.095",
"value": "Itaru Hinoue"
},
{
"operation": "Highlighting",
"time": "51.045",
"value": "Itaru Hinoue_sentence_0"
},
{
"operation": "hyperlink",
"time": "56.502",
"value": "Osaka"
},
{
"operation": "Now on",
"time": "57.185",
"value": "Osaka Prefecture"
},
{
"operation": "Highlighting",
"time": "61.554",
"value": "Osaka Prefecture_sentence_0"
},
{
"operation": "finish",
"time": "69.774",
"value": "finish"
}
]
}
|
36673
|
Luigi Moretti was an Italian architect, he was born on via Napoleone III, on Esquiline Hill, in the same apartment where he lived almost his entire life.
|
{
"evidence": [
"Luigi Moretti_sentence_1",
"Luigi Moretti_sentence_2"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nLuigi Moretti was an Italian architect, he was born on via Napoleone III, on Esquiline Hill, in the same apartment where he lived almost his entire life.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Luigi Moretti_sentence_1",
"Luigi Moretti_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 817,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.725",
"value": "?search="
},
{
"operation": "search",
"time": "10.632",
"value": "Luigi Moretti"
},
{
"operation": "Now on",
"time": "11.674",
"value": "Luigi Moretti"
},
{
"operation": "Highlighting",
"time": "15.678",
"value": "Luigi Moretti_sentence_1"
},
{
"operation": "Page search",
"time": "61.71",
"value": "napoleone"
},
{
"operation": "Highlighting",
"time": "70.975",
"value": "Luigi Moretti_sentence_2"
},
{
"operation": "finish",
"time": "228.167",
"value": "finish"
}
]
}
|
5448
|
A Skuldelev ship known as The Sea Stallion from Glendalough, made of oak from Glendalough in County Wicklow, was found off the coast of Germany.
|
{
"evidence": [
"Havhingsten fra Glendalough_sentence_0",
"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, made of oak from Glendalough in County Wicklow, was found off the coast of Germany.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Havhingsten fra Glendalough_sentence_0",
"Skuldelev ships_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 818,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.087",
"value": "?search="
},
{
"operation": "search",
"time": "25.207",
"value": "Sea Stallion"
},
{
"operation": "Now on",
"time": "25.804",
"value": "Sea Stallion"
},
{
"operation": "hyperlink",
"time": "39.65",
"value": "Sea Stallion from Glendalough"
},
{
"operation": "Now on",
"time": "40.359",
"value": "Sea Stallion from Glendalough"
},
{
"operation": "Highlighting",
"time": "52.184",
"value": "Havhingsten fra Glendalough_sentence_0"
},
{
"operation": "Highlighting",
"time": "82.974",
"value": "Havhingsten fra Glendalough_sentence_1"
},
{
"operation": "Highlighting",
"time": "120.11",
"value": "Havhingsten fra Glendalough_sentence_4"
},
{
"operation": "Highlighting",
"time": "120.133",
"value": "Havhingsten fra Glendalough_section_0"
},
{
"operation": "Highlighting deleted",
"time": "130.199",
"value": "Havhingsten fra Glendalough_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "130.227",
"value": "Havhingsten fra Glendalough_section_0"
},
{
"operation": "hyperlink",
"time": "149.367",
"value": "Skuldelev ships"
},
{
"operation": "Now on",
"time": "150.228",
"value": "Skuldelev ships"
},
{
"operation": "Page search",
"time": "168.854",
"value": "germany"
},
{
"operation": "Highlighting",
"time": "224.676",
"value": "Skuldelev ships_sentence_18"
},
{
"operation": "Highlighting",
"time": "224.714",
"value": "Skuldelev ships_section_0"
},
{
"operation": "Highlighting",
"time": "224.733",
"value": "Skuldelev ships_section_2"
},
{
"operation": "Highlighting",
"time": "239.803",
"value": "Skuldelev ships_sentence_0"
},
{
"operation": "finish",
"time": "291.783",
"value": "finish"
}
]
}
|
51076
|
The Terry Biddlecombe Challenge Trophy was a Grade 2 National Hunt chase, later changed to Limited Handicap, that was named in honour of horse breeder Terry Biddlecombe.
|
{
"evidence": [
"Terry Biddlecombe Challenge Trophy_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 Terry Biddlecombe Challenge Trophy was a Grade 2 National Hunt chase, later changed to Limited Handicap, that was named in honour of horse breeder Terry Biddlecombe.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Terry Biddlecombe Challenge Trophy_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 819,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.286",
"value": "?search="
},
{
"operation": "search",
"time": "16.93",
"value": "Terry Biddlecombe Challenge Trophy"
},
{
"operation": "Now on",
"time": "17.704",
"value": "Terry Biddlecombe Challenge Trophy"
},
{
"operation": "Highlighting",
"time": "30.073",
"value": "Terry Biddlecombe Challenge Trophy_sentence_0"
},
{
"operation": "Highlighting",
"time": "53.988",
"value": "Terry Biddlecombe Challenge Trophy_sentence_5"
},
{
"operation": "Page search",
"time": "65.762",
"value": "terry"
},
{
"operation": "Page search",
"time": "73.905",
"value": "breeder"
},
{
"operation": "Highlighting",
"time": "78.751",
"value": "Terry Biddlecombe Challenge Trophy_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "80.718",
"value": "Terry Biddlecombe Challenge Trophy_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "82.564",
"value": "Terry Biddlecombe Challenge Trophy_sentence_5"
},
{
"operation": "finish",
"time": "202.684",
"value": "finish"
}
]
}
|
63054
|
The local government in New Zealand has territorial authorities that consist of 13 city councils, 55 district councils, and one special council for the Chatham Islands in the east of the South Island.
|
{
"evidence": [
"Local government in New Zealand_sentence_63"
],
"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 local government in New Zealand has territorial authorities that consist of 13 city councils, 55 district councils, and one special council for the Chatham Islands in the east of the South Island.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Local government in New Zealand_sentence_63"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 820,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.031",
"value": "?search="
},
{
"operation": "search",
"time": "20.296",
"value": "Contains...New Zealand has territorial authorities"
},
{
"operation": "Now on",
"time": "23.4",
"value": "undefined"
},
{
"operation": "search",
"time": "35.636",
"value": "Local government in New Zealand"
},
{
"operation": "Now on",
"time": "37.276",
"value": "Local government in New Zealand"
},
{
"operation": "Page search",
"time": "56.318",
"value": "special council"
},
{
"operation": "Highlighting",
"time": "83.145",
"value": "Local government in New Zealand_sentence_63"
},
{
"operation": "hyperlink",
"time": "100.887",
"value": "Chatham Islands"
},
{
"operation": "Now on",
"time": "102.322",
"value": "Chatham Islands"
},
{
"operation": "Highlighting",
"time": "113.127",
"value": "Chatham Islands_sentence_2"
},
{
"operation": "Highlighting",
"time": "113.129",
"value": "Chatham Islands_title"
},
{
"operation": "Highlighting deleted",
"time": "131.657",
"value": "Chatham Islands_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "131.66",
"value": "Chatham Islands_title"
},
{
"operation": "finish",
"time": "152.287",
"value": "finish"
}
]
}
|
exfever_2202
|
Inside Man is a 2009 American heist thriller film starring an artist who is known for his frequent collaborations with an English film director, producer, actor, screenwriter, and editor.
|
{
"evidence": [
"Inside Man",
"Denzel Washington",
"Tony Scott"
],
"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:\nInside Man is a 2009 American heist thriller film starring an artist who is known for his frequent collaborations with an English film director, producer, actor, screenwriter, and editor.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Inside Man",
"Denzel Washington",
"Tony Scott"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 821,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8249
|
Human condition is a very broad topic that has been and continues to be pondered and analyzed from many perspectives, including a social-cultural system of designated behaviors and practices, morals, beliefs, worldviews, texts, sanctified places, prophecies, ethics, or organizations, that generally relates humanity to supernatural, transcendental, and spiritual elements.
|
{
"evidence": [
"Human condition",
"Religion"
],
"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:\nHuman condition is a very broad topic that has been and continues to be pondered and analyzed from many perspectives, including a social-cultural system of designated behaviors and practices, morals, beliefs, worldviews, texts, sanctified places, prophecies, ethics, or organizations, that generally relates humanity to supernatural, transcendental, and spiritual elements.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Human condition",
"Religion"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 822,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_716
|
Selene of the Underworld film franchise, in which she is portrayed by Kate Beckinsale is characterized as the film's main character that makes key decisions that affect the plot and appear in a second strand of the plot that is a supporting side story for any story or for the main plot.
|
{
"evidence": [
"Selene (Underworld)",
"Protagonist",
"Subplot"
],
"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:\nSelene of the Underworld film franchise, in which she is portrayed by Kate Beckinsale is characterized as the film's main character that makes key decisions that affect the plot and appear in a second strand of the plot that is a supporting side story for any story or for the main plot.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Selene (Underworld)",
"Protagonist",
"Subplot"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 823,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4386
|
Roger Daltrey was the first member of the Who to leave the band.
|
{
"evidence": [
"The Who",
"Pete Townshend"
],
"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:\nRoger Daltrey was the first member of the Who to leave the band.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Who",
"Pete Townshend"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 824,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_281
|
Nick Nolte received an Academy Award nomination for the 2011 film about two estranged brothers who enter a full-contact combat sport incorporating techniques from various combat sports from around the world.
|
{
"evidence": [
"Nick Nolte",
"Warrior (2011 film)",
"Mixed martial arts"
],
"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:\nNick Nolte received an Academy Award nomination for the 2011 film about two estranged brothers who enter a full-contact combat sport incorporating techniques from various combat sports from around the world.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Nick Nolte",
"Warrior (2011 film)",
"Mixed martial arts"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 825,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
36777
|
Pseudotomentella is a genus of corticioid moth with 17 known species of the family Thelephoracea, order Thelephorales of the kingdom Fungi which was described by the mycologist Mirko Svrček in 1958.
|
{
"evidence": [
"Pseudotomentella_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:\nPseudotomentella is a genus of corticioid moth with 17 known species of the family Thelephoracea, order Thelephorales of the kingdom Fungi which was described by the mycologist Mirko Svrček in 1958.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Pseudotomentella_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 826,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.987",
"value": "?search="
},
{
"operation": "search",
"time": "11.96",
"value": "Pseudotomentella"
},
{
"operation": "Now on",
"time": "12.726",
"value": "Pseudotomentella"
},
{
"operation": "Highlighting",
"time": "14.496",
"value": "Pseudotomentella_sentence_0"
},
{
"operation": "hyperlink",
"time": "38.355",
"value": "corticioid fungi"
},
{
"operation": "Now on",
"time": "38.788",
"value": "Corticioid fungi"
},
{
"operation": "back-button-clicked",
"time": "45.122",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "45.195",
"value": "Pseudotomentella"
},
{
"operation": "finish",
"time": "60.504",
"value": "finish"
}
]
}
|
16316
|
Beechcraft is a prototype airliner.
|
{
"evidence": [
"Beechcraft Model 34_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:\nBeechcraft is a prototype airliner.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Beechcraft Model 34_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 827,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.895",
"value": "?search="
},
{
"operation": "search",
"time": "11.944",
"value": "Beechcraft"
},
{
"operation": "Now on",
"time": "12.644",
"value": "Beechcraft"
},
{
"operation": "search",
"time": "48.635",
"value": "beechcraft prototype"
},
{
"operation": "Now on",
"time": "49.347",
"value": "undefined"
},
{
"operation": "search",
"time": "61.031",
"value": "beechcraft"
},
{
"operation": "Now on",
"time": "61.656",
"value": "Beechcraft"
},
{
"operation": "search",
"time": "75.48",
"value": "beechcraft airliner"
},
{
"operation": "Now on",
"time": "76.378",
"value": "undefined"
},
{
"operation": "search",
"time": "115.924",
"value": "Contains...Beechcraft Model 34"
},
{
"operation": "Now on",
"time": "116.845",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "121.587",
"value": "Beechcraft Model 34"
},
{
"operation": "Now on",
"time": "122.255",
"value": "Beechcraft Model 34"
},
{
"operation": "Highlighting",
"time": "139.365",
"value": "Beechcraft Model 34_sentence_0"
},
{
"operation": "finish",
"time": "160.451",
"value": "finish"
}
]
}
|
exfever_4365
|
Christopher Ryan Hardwick hosted a plinko-inspired gameshow on an American English-language commercial broadcast television and radio network.
|
{
"evidence": [
"Chris Hardwick",
"NBC"
],
"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:\nChristopher Ryan Hardwick hosted a plinko-inspired gameshow on an American English-language commercial broadcast television and radio network.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Chris Hardwick",
"NBC"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 828,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2162
|
The Vandals were a Spanish people who first inhabited what is now southern Poland which established Vandal kingdoms on a peninsula in southwestern Europe, defining the westernmost edge of Eurasia.
|
{
"evidence": [
"Vandals",
"Iberian Peninsula"
],
"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 Vandals were a Spanish people who first inhabited what is now southern Poland which established Vandal kingdoms on a peninsula in southwestern Europe, defining the westernmost edge of Eurasia.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Vandals",
"Iberian Peninsula"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 829,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
34138
|
Japan's Shinano, an aircraft carrier built by the Imperial Japanese Navy (IJN) during World War II, had the thickest hangar deck (7.5 in) among some of the World War II era aircraft carriers.
|
{
"evidence": [
"Japanese aircraft carrier Shinano_sentence_0",
"Japanese aircraft carrier Shinano_sentence_37"
],
"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:\nJapan's Shinano, an aircraft carrier built by the Imperial Japanese Navy (IJN) during World War II, had the thickest hangar deck (7.5 in) among some of the World War II era aircraft carriers.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Japanese aircraft carrier Shinano_sentence_0",
"Japanese aircraft carrier Shinano_sentence_37"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 830,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.725",
"value": "?search="
},
{
"operation": "search",
"time": "13.04",
"value": "Shinano"
},
{
"operation": "Now on",
"time": "14.124",
"value": "Shinano"
},
{
"operation": "hyperlink",
"time": "20.042",
"value": "Japanese aircraft carrier Shinano"
},
{
"operation": "Now on",
"time": "20.815",
"value": "Japanese aircraft carrier Shinano"
},
{
"operation": "Highlighting",
"time": "28.107",
"value": "Japanese aircraft carrier Shinano_sentence_0"
},
{
"operation": "Highlighting",
"time": "148.947",
"value": "Japanese aircraft carrier Shinano_sentence_37"
},
{
"operation": "finish",
"time": "206.029",
"value": "finish"
}
]
}
|
exfever_2568
|
A hate group is a majority that advocates and practices the use of physical force so as to injure, abuse, damage, or destroy.
|
{
"evidence": [
"Hate group",
"Violence"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nA hate group is a majority that advocates and practices the use of physical force so as to injure, abuse, damage, or destroy.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Hate group",
"Violence"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 831,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
41131
|
Palazzo Grimani di San Luca was built in the mid-16th century for procurator Gerolamo Grimani by architect Sanmicheli with a classical plan and a central atrium.
|
{
"evidence": [
"Palazzo Grimani di San Luca_sentence_1",
"Palazzo Grimani di San Luca_sentence_2"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nPalazzo Grimani di San Luca was built in the mid-16th century for procurator Gerolamo Grimani by architect Sanmicheli with a classical plan and a central atrium.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Palazzo Grimani di San Luca_sentence_1",
"Palazzo Grimani di San Luca_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 832,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.038",
"value": "?search="
},
{
"operation": "search",
"time": "10.851",
"value": "Palazzo Grimani di San Luca"
},
{
"operation": "Now on",
"time": "11.526",
"value": "Palazzo Grimani di San Luca"
},
{
"operation": "Highlighting",
"time": "19.478",
"value": "Palazzo Grimani di San Luca_sentence_1"
},
{
"operation": "Highlighting",
"time": "35.816",
"value": "Palazzo Grimani di San Luca_sentence_2"
},
{
"operation": "finish",
"time": "43.013",
"value": "finish"
}
]
}
|
exfever_2921
|
Steven George Gerrard is an English professional football manager and former player, who manages an English professional football club that played since 1897 at their home ground in a football stadium in Aston, Birmingham, California.
|
{
"evidence": [
"Steven Gerrard",
"Aston Villa F.C.",
"Villa Park"
],
"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:\nSteven George Gerrard is an English professional football manager and former player, who manages an English professional football club that played since 1897 at their home ground in a football stadium in Aston, Birmingham, California.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Steven Gerrard",
"Aston Villa F.C.",
"Villa Park"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 833,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
94298
|
Pierce County, established on December 22, 1852, is home to the Nisqually Indian Reservation and the Puyallup Indian Reservation.
|
{
"evidence": [
"Nisqually Indian Tribe of the Nisqually Reservation_sentence_4",
"Nisqually Reservation_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:\nPierce County, established on December 22, 1852, is home to the Nisqually Indian Reservation and the Puyallup Indian Reservation.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Nisqually Indian Tribe of the Nisqually Reservation_sentence_4",
"Nisqually Reservation_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 834,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.668",
"value": "?search="
},
{
"operation": "search",
"time": "165.207",
"value": "Pierce County"
},
{
"operation": "Now on",
"time": "166.267",
"value": "Pierce County"
},
{
"operation": "hyperlink",
"time": "210.185",
"value": "Pierce County, Washington"
},
{
"operation": "Now on",
"time": "211.082",
"value": "Pierce County, Washington"
},
{
"operation": "Highlighting",
"time": "238.123",
"value": "Pierce County, Washington_sentence_4Pierce County, Washington_sentence_5"
},
{
"operation": "Highlighting",
"time": "238.125",
"value": "Pierce County, Washington_title"
},
{
"operation": "hyperlink",
"time": "242.057",
"value": "Oregon Territory"
},
{
"operation": "Now on",
"time": "242.78",
"value": "Oregon Territory"
},
{
"operation": "back-button-clicked",
"time": "244.105",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "244.336",
"value": "Pierce County, Washington"
},
{
"operation": "Highlighting deleted",
"time": "245.963",
"value": "Pierce County, Washington_sentence_4Pierce County, Washington_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "245.964",
"value": "Pierce County, Washington_title"
},
{
"operation": "Highlighting",
"time": "251.121",
"value": "Pierce County, Washington_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "251.122",
"value": "Pierce County, Washington_title"
},
{
"operation": "Highlighting",
"time": "253.497",
"value": "Pierce County, Washington_header_cell_0_3_0"
},
{
"operation": "Highlighting",
"time": "254.361",
"value": "Pierce County, Washington_cell_0_3_1"
},
{
"operation": "Highlighting",
"time": "254.372",
"value": "Pierce County, Washington_header_cell_0_3_0"
},
{
"operation": "Highlighting",
"time": "254.375",
"value": "Pierce County, Washington_header_cell_0_0_0"
},
{
"operation": "hyperlink",
"time": "401.907",
"value": "National Register of Historic Places listings in Pierce County, Washington"
},
{
"operation": "Now on",
"time": "405.981",
"value": "National Register of Historic Places listings in Pierce County, Washington"
},
{
"operation": "hyperlink",
"time": "546.728",
"value": "List of National Historic Landmarks in Washington"
},
{
"operation": "Now on",
"time": "547.905",
"value": "List of National Historic Landmarks in Washington (state)"
},
{
"operation": "hyperlink",
"time": "594.376",
"value": "Historic preservation"
},
{
"operation": "Now on",
"time": "595.553",
"value": "Historic preservation"
},
{
"operation": "search",
"time": "674.18",
"value": "Pierce County, Washington"
},
{
"operation": "Now on",
"time": "674.819",
"value": "Pierce County, Washington"
},
{
"operation": "search",
"time": "898.386",
"value": "Contains...Nisqually Indian Reservation and the Puyallup Indian Reservation"
},
{
"operation": "Now on",
"time": "900.656",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "942.431",
"value": "Leschi (Nisqually)"
},
{
"operation": "Now on",
"time": "943.21",
"value": "Leschi (Nisqually)"
},
{
"operation": "hyperlink",
"time": "995.566",
"value": "Nisqually Indian Tribe"
},
{
"operation": "Now on",
"time": "996.139",
"value": "Nisqually Indian Tribe of the Nisqually Reservation"
},
{
"operation": "Highlighting",
"time": "1071.887",
"value": "Nisqually Indian Tribe of the Nisqually Reservation_sentence_4"
},
{
"operation": "search",
"time": "1131.945",
"value": "Puyallup Indian Reservation"
},
{
"operation": "Now on",
"time": "1132.673",
"value": "Puyallup people"
},
{
"operation": "search",
"time": "1220.815",
"value": "Nisqually Indian Reservation"
},
{
"operation": "Now on",
"time": "1221.751",
"value": "Nisqually Indian Reservation"
},
{
"operation": "Highlighting",
"time": "1246.543",
"value": "Nisqually Reservation_sentence_0"
},
{
"operation": "Now on",
"time": "1274.044",
"value": "Nisqually Reservation"
},
{
"operation": "finish",
"time": "1313.831",
"value": "finish"
}
]
}
|
exfever_4389
|
Niall Horan is a record producer.
|
{
"evidence": [
"One Direction",
"Liam Payne"
],
"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:\nNiall Horan is a record producer.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"One Direction",
"Liam Payne"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 835,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
51021
|
Artūras Fomenka played for Lokomotiv Tashkent (owned and sponsored by Uzbek Railways) in 2012 and for Shurtan Guzar in 2013.
|
{
"evidence": [
"Artūras Fomenka_sentence_4",
"PFC Lokomotiv Tashkent_sentence_1",
"Artūras Fomenka_sentence_5"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nArtūras Fomenka played for Lokomotiv Tashkent (owned and sponsored by Uzbek Railways) in 2012 and for Shurtan Guzar in 2013.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Artūras Fomenka_sentence_4",
"PFC Lokomotiv Tashkent_sentence_1",
"Artūras Fomenka_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 836,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.961",
"value": "?search="
},
{
"operation": "search",
"time": "11.09",
"value": "Artūras Fomenka"
},
{
"operation": "Now on",
"time": "12.15",
"value": "Artūras Fomenka"
},
{
"operation": "Page search",
"time": "21.28",
"value": "lokomotiv"
},
{
"operation": "Highlighting",
"time": "24.54",
"value": "Artūras Fomenka_sentence_4"
},
{
"operation": "hyperlink",
"time": "27.788",
"value": "Lokomotiv Tashkent"
},
{
"operation": "Now on",
"time": "29.237",
"value": "PFC Lokomotiv Tashkent"
},
{
"operation": "Highlighting",
"time": "37.806",
"value": "PFC Lokomotiv Tashkent_sentence_1"
},
{
"operation": "back-button-clicked",
"time": "49.565",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "49.739",
"value": "Artūras Fomenka"
},
{
"operation": "Page search",
"time": "60.967",
"value": "shurtan"
},
{
"operation": "Highlighting",
"time": "67.516",
"value": "Artūras Fomenka_sentence_5"
},
{
"operation": "finish",
"time": "152.908",
"value": "finish"
}
]
}
|
83497
|
Shahodra is a village in India with a total population made up of 54 male and 59 female, as of 2011.
|
{
"evidence": [
"Ashoknagar district_sentence_9",
"Ashoknagar district_sentence_11"
],
"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:\nShahodra is a village in India with a total population made up of 54 male and 59 female, as of 2011.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Ashoknagar district_sentence_9",
"Ashoknagar district_sentence_11"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 837,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.839",
"value": "?search="
},
{
"operation": "search",
"time": "5.703",
"value": "Shadora"
},
{
"operation": "Now on",
"time": "6.303",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "15.036",
"value": "Bamori (Vidhan Sabha constituency)"
},
{
"operation": "Now on",
"time": "15.888",
"value": "Bamori (Vidhan Sabha constituency)"
},
{
"operation": "back-button-clicked",
"time": "44.389",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "44.918",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "46.56",
"value": "Ashoknagar district"
},
{
"operation": "Now on",
"time": "47.673",
"value": "Ashoknagar district"
},
{
"operation": "Highlighting",
"time": "55.582",
"value": "Ashoknagar district_sentence_9"
},
{
"operation": "hyperlink",
"time": "59.969",
"value": "tehsils"
},
{
"operation": "Now on",
"time": "60.594",
"value": "Tehsil"
},
{
"operation": "Highlighting",
"time": "64.481",
"value": "Tehsil_sentence_2"
},
{
"operation": "Highlighting",
"time": "64.481",
"value": "Tehsil_title"
},
{
"operation": "hyperlink",
"time": "72.873",
"value": "List of subdistricts in India"
},
{
"operation": "Now on",
"time": "73.683",
"value": "List of subdistricts in India"
},
{
"operation": "search",
"time": "109.53",
"value": "list of villages in India"
},
{
"operation": "Now on",
"time": "114.951",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "121.71",
"value": "List of villages Amer, India_section_2"
},
{
"operation": "Now on",
"time": "122.558",
"value": "Amer, India#List of villages Amer.2C India section 2"
},
{
"operation": "back-button-clicked",
"time": "132.173",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "133.306",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "134.378",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "134.383",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "134.53",
"value": "List of subdistricts in India"
},
{
"operation": "back-button-clicked",
"time": "147.586",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "147.589",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "147.778",
"value": "Tehsil"
},
{
"operation": "back-button-clicked",
"time": "152.626",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "152.63",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "153.047",
"value": "Ashoknagar district"
},
{
"operation": "Highlighting",
"time": "155.831",
"value": "Ashoknagar district_sentence_11"
},
{
"operation": "hyperlink",
"time": "188.367",
"value": "2011 census"
},
{
"operation": "Now on",
"time": "190.4",
"value": "2011 Census of India"
},
{
"operation": "hyperlink",
"time": "300.44",
"value": "Demographics of India"
},
{
"operation": "Now on",
"time": "304.536",
"value": "Demographics of India"
},
{
"operation": "hyperlink",
"time": "317.079",
"value": "India"
},
{
"operation": "Now on",
"time": "319.289",
"value": "India"
},
{
"operation": "hyperlink",
"time": "330.422",
"value": "Outline of India"
},
{
"operation": "Now on",
"time": "332.489",
"value": "Outline of India"
},
{
"operation": "back-button-clicked",
"time": "344.98",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "345.228",
"value": "India"
},
{
"operation": "back-button-clicked",
"time": "345.587",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "345.592",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "346.098",
"value": "Demographics of India"
},
{
"operation": "back-button-clicked",
"time": "346.442",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "346.447",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "346.673",
"value": "2011 Census of India"
},
{
"operation": "back-button-clicked",
"time": "347.174",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "347.178",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "347.325",
"value": "Ashoknagar district"
},
{
"operation": "back-button-clicked",
"time": "353.26",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "353.265",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "353.268",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "354.699",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "359.233",
"value": "Bamori (Vidhan Sabha constituency)"
},
{
"operation": "Now on",
"time": "359.719",
"value": "Bamori (Vidhan Sabha constituency)"
},
{
"operation": "back-button-clicked",
"time": "369.629",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "370.16",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "382.026",
"value": "Bamori (Vidhan Sabha constituency)"
},
{
"operation": "Now on",
"time": "382.788",
"value": "Bamori (Vidhan Sabha constituency)"
},
{
"operation": "hyperlink",
"time": "395.503",
"value": "delimitation"
},
{
"operation": "Now on",
"time": "396.221",
"value": "Boundary delimitation"
},
{
"operation": "back-button-clicked",
"time": "403.098",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "403.195",
"value": "Bamori (Vidhan Sabha constituency)"
},
{
"operation": "back-button-clicked",
"time": "408.633",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "408.637",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "409.422",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "411.175",
"value": "Ashoknagar district"
},
{
"operation": "Now on",
"time": "411.768",
"value": "Ashoknagar district"
},
{
"operation": "finish",
"time": "474.031",
"value": "finish"
}
]
}
|
37344
|
There are three gold medals achieved from the 2013 - 2017 performances of SpVgg Neckarelz, a German association football club from Neckarelz.
|
{
"evidence": [
"SpVgg Neckarelz_sentence_0"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThere are three gold medals achieved from the 2013 - 2017 performances of SpVgg Neckarelz, a German association football club from Neckarelz.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"SpVgg Neckarelz_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 838,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.792",
"value": "?search="
},
{
"operation": "search",
"time": "21.04",
"value": "SpVgg Neckarelz"
},
{
"operation": "Now on",
"time": "21.625",
"value": "SpVgg Neckarelz"
},
{
"operation": "Highlighting",
"time": "28.883",
"value": "SpVgg Neckarelz_sentence_0"
},
{
"operation": "hyperlink",
"time": "103.408",
"value": "Oberliga Baden-Württemberg"
},
{
"operation": "Now on",
"time": "104.668",
"value": "Oberliga Baden-Württemberg"
},
{
"operation": "finish",
"time": "125.321",
"value": "finish"
}
]
}
|
exfever_717
|
The United Nations (UN) is an intergovernmental organization headquartered on international territory in the most populous city in the United States.
|
{
"evidence": [
"United Nations",
"New York 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 United Nations (UN) is an intergovernmental organization headquartered on international territory in the most populous city in the United States.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"United Nations",
"New York City"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 839,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
17147
|
In 2016, Rochester Rhino, which had eleven out of the 33 players from the United States and two players from Canada, were eliminated in the conference semi-finals by the New York Red Bulls II, an American professional soccer team based in Harrison, New Jersey.
|
{
"evidence": [
"2016 U.S. Open Cup_sentence_2"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nIn 2016, Rochester Rhino, which had eleven out of the 33 players from the United States and two players from Canada, were eliminated in the conference semi-finals by the New York Red Bulls II, an American professional soccer team based in Harrison, New Jersey.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"2016 U.S. Open Cup_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 840,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.469",
"value": "?search="
},
{
"operation": "search",
"time": "14.172",
"value": "Rochester Rhino"
},
{
"operation": "Now on",
"time": "15.252",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "25.692",
"value": "rochester rhinos"
},
{
"operation": "Now on",
"time": "26.491",
"value": "undefined"
},
{
"operation": "search",
"time": "76.913",
"value": "Rochester Rhinos 2016"
},
{
"operation": "Now on",
"time": "78.323",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "84.344",
"value": "2016 U.S. Open Cup"
},
{
"operation": "Now on",
"time": "85.831",
"value": "2016 U.S. Open Cup"
},
{
"operation": "Page search",
"time": "103.09",
"value": "rhinos"
},
{
"operation": "Highlighting",
"time": "142.649",
"value": "2016 U.S. Open Cup_sentence_2"
},
{
"operation": "finish",
"time": "167.323",
"value": "finish"
}
]
}
|
exfever_3727
|
Nicholas King Nolte was nominated for the Academy Award for Best Actor for the 1991 film directed and co-produced by Barbra Streisand, whose category of narrative fiction intended to be more serious than humorous in tone.
|
{
"evidence": [
"Nick Nolte",
"The Prince of Tides",
"Drama (film and television)"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nNicholas King Nolte was nominated for the Academy Award for Best Actor for the 1991 film directed and co-produced by Barbra Streisand, whose category of narrative fiction intended to be more serious than humorous in tone.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Nick Nolte",
"The Prince of Tides",
"Drama (film and television)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 841,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1036
|
Road House is a 1990 American film that protects a small town in Missouri from a corrupt businessman whose genre events typically involve violence and physical feats.
|
{
"evidence": [
"Road House (1989 film)",
"Action 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:\nRoad House is a 1990 American film that protects a small town in Missouri from a corrupt businessman whose genre events typically involve violence and physical feats.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Road House (1989 film)",
"Action film"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 842,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7627
|
The Godfather Part III is a 1995 American crime film produced and directed by an American film director, producer, and screenwriter.
|
{
"evidence": [
"The Godfather Part III",
"Francis Ford Coppola"
],
"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 Godfather Part III is a 1995 American crime film produced and directed by an American film director, producer, and screenwriter.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Godfather Part III",
"Francis Ford Coppola"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 843,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8906
|
Stockard Channing, a Canadian actress, is known for playing Betty Rizzo in a 1978 American musical romantic comedy film based on the 1971 musical of the same name.
|
{
"evidence": [
"Stockard Channing",
"Grease (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:\nStockard Channing, a Canadian actress, is known for playing Betty Rizzo in a 1978 American musical romantic comedy film based on the 1971 musical of the same name.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Stockard Channing",
"Grease (film)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 844,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
77197
|
Jimmie Hall's breakout rookie season was more than enough for him to supplant Green as the Twins' center fielder and started the 1964 season.
|
{
"evidence": [
"Jimmie Hall_sentence_22",
"Jimmie Hall_sentence_23"
],
"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:\nJimmie Hall's breakout rookie season was more than enough for him to supplant Green as the Twins' center fielder and started the 1964 season.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jimmie Hall_sentence_22",
"Jimmie Hall_sentence_23"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 845,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.625",
"value": "?search="
},
{
"operation": "search",
"time": "24.36",
"value": "Jimmie Hall"
},
{
"operation": "Now on",
"time": "25.806",
"value": "Jimmie Hall"
},
{
"operation": "Page search",
"time": "57.87",
"value": "rockie"
},
{
"operation": "Page search",
"time": "58.209",
"value": "rockie"
},
{
"operation": "Page search",
"time": "58.474",
"value": "rockie"
},
{
"operation": "Highlighting",
"time": "117.929",
"value": "Jimmie Hall_sentence_17"
},
{
"operation": "Highlighting deleted",
"time": "118.621",
"value": "Jimmie Hall_sentence_17"
},
{
"operation": "Highlighting",
"time": "119.536",
"value": "Jimmie Hall_sentence_16"
},
{
"operation": "Highlighting",
"time": "119.959",
"value": "Jimmie Hall_sentence_17"
},
{
"operation": "Highlighting",
"time": "182.537",
"value": "Jimmie Hall_sentence_22"
},
{
"operation": "Highlighting deleted",
"time": "185.206",
"value": "Jimmie Hall_sentence_17"
},
{
"operation": "Highlighting deleted",
"time": "186.805",
"value": "Jimmie Hall_sentence_16"
},
{
"operation": "Highlighting",
"time": "246.313",
"value": "Jimmie Hall_sentence_23"
},
{
"operation": "finish",
"time": "290.622",
"value": "finish"
}
]
}
|
exfever_8056
|
Radiohead is a Japanese rock band formed in a historic market town and civil parish.
|
{
"evidence": [
"Radiohead",
"Abingdon-on-Thames"
],
"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:\nRadiohead is a Japanese rock band formed in a historic market town and civil parish.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Radiohead",
"Abingdon-on-Thames"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 846,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5725
|
The Northeast megalopolis is the most populous in the United States, stretching primarily from the northern Boston suburbs to the suburbs of the widespread region radiating westward and southward from Santa Marta.
|
{
"evidence": [
"Northeast megalopolis",
"Northern Virginia"
],
"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 Northeast megalopolis is the most populous in the United States, stretching primarily from the northern Boston suburbs to the suburbs of the widespread region radiating westward and southward from Santa Marta.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Northeast megalopolis",
"Northern Virginia"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 847,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
33887
|
The 1964 Wandsworth London Borough Council election had a total of 169 candidates inclusive of Conservative, Labour, Liberal, Communists, Independent, and Rad Lib. parties wherein the election was only based on aldermen—a member of a municipal assembly or council chosen by the elected members themselves.
|
{
"evidence": [
"1964 Wandsworth London Borough Council election_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:\nThe 1964 Wandsworth London Borough Council election had a total of 169 candidates inclusive of Conservative, Labour, Liberal, Communists, Independent, and Rad Lib. parties wherein the election was only based on aldermen—a member of a municipal assembly or council chosen by the elected members themselves.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"1964 Wandsworth London Borough Council election_sentence_8"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 848,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.607",
"value": "?search="
},
{
"operation": "search",
"time": "13.21",
"value": "1964 Wandsworth London Borough Council"
},
{
"operation": "Now on",
"time": "14.973",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "20.545",
"value": "1964 Wandsworth London Borough Council election"
},
{
"operation": "Now on",
"time": "21.465",
"value": "1964 Wandsworth London Borough Council election"
},
{
"operation": "Highlighting",
"time": "52.883",
"value": "1964 Wandsworth London Borough Council election_sentence_5"
},
{
"operation": "Highlighting",
"time": "66.752",
"value": "1964 Wandsworth London Borough Council election_sentence_6"
},
{
"operation": "Highlighting",
"time": "71.624",
"value": "1964 Wandsworth London Borough Council election_sentence_7"
},
{
"operation": "Highlighting",
"time": "75.873",
"value": "1964 Wandsworth London Borough Council election_sentence_8"
},
{
"operation": "hyperlink",
"time": "80.689",
"value": "aldermen"
},
{
"operation": "Now on",
"time": "81.377",
"value": "Alderman"
},
{
"operation": "Highlighting",
"time": "83.656",
"value": "Alderman_sentence_3"
},
{
"operation": "Highlighting",
"time": "83.657",
"value": "Alderman_title"
},
{
"operation": "back-button-clicked",
"time": "139.537",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "139.624",
"value": "1964 Wandsworth London Borough Council election"
},
{
"operation": "Highlighting",
"time": "155.624",
"value": "1964 Wandsworth London Borough Council election_sentence_8"
},
{
"operation": "finish",
"time": "172.728",
"value": "finish"
}
]
}
|
74470
|
Tōkyū Tōyoko Line (a major railway line connecting Tokyo (Shibuya) to Yokohama) Express does not stop at the Motosumiyoshi Station, as well as Tōkyū Meguro Line (MG12) Express.
|
{
"evidence": [
"Tōkyū Tōyoko Line_sentence_0",
"Tōkyū Tōyoko Line_sentence_4",
"Tōkyū Tōyoko Line_sentence_47"
],
"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:\nTōkyū Tōyoko Line (a major railway line connecting Tokyo (Shibuya) to Yokohama) Express does not stop at the Motosumiyoshi Station, as well as Tōkyū Meguro Line (MG12) Express.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Tōkyū Tōyoko Line_sentence_0",
"Tōkyū Tōyoko Line_sentence_4",
"Tōkyū Tōyoko Line_sentence_47"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 849,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.724",
"value": "?search="
},
{
"operation": "search",
"time": "24.088",
"value": "Tōkyū Tōyoko Line"
},
{
"operation": "Now on",
"time": "25.935",
"value": "Tōkyū Tōyoko Line"
},
{
"operation": "Highlighting",
"time": "29.614",
"value": "Tōkyū Tōyoko Line_sentence_0"
},
{
"operation": "Page search",
"time": "53.843",
"value": "stop"
},
{
"operation": "Page search",
"time": "86.491",
"value": "motosum"
},
{
"operation": "Page search",
"time": "137.323",
"value": "meguro"
},
{
"operation": "Highlighting",
"time": "146.07",
"value": "Tōkyū Tōyoko Line_sentence_4"
},
{
"operation": "Page search",
"time": "153.539",
"value": "motosum"
},
{
"operation": "Highlighting",
"time": "158.057",
"value": "Tōkyū Tōyoko Line_sentence_47"
},
{
"operation": "finish",
"time": "164.162",
"value": "finish"
}
]
}
|
89680
|
Alton line is a railway line in Hampshire and Surrey, England operated by South Western Railway as a relatively long branch of the South Western Main Line and leaves the main line at Pirbright Junction to the west of Brookwood station, Surrey, then turns to the southwest and crosses and recrosses the Surrey/Hampshire border.
|
{
"evidence": [
"Alton line_sentence_0",
"Alton line_sentence_1",
"Alton line_sentence_2"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAlton line is a railway line in Hampshire and Surrey, England operated by South Western Railway as a relatively long branch of the South Western Main Line and leaves the main line at Pirbright Junction to the west of Brookwood station, Surrey, then turns to the southwest and crosses and recrosses the Surrey/Hampshire border.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Alton line_sentence_0",
"Alton line_sentence_1",
"Alton line_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 850,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.922",
"value": "undefined"
},
{
"operation": "search",
"time": "9.697",
"value": "Alton line"
},
{
"operation": "Now on",
"time": "11.307",
"value": "Alton line"
},
{
"operation": "Highlighting",
"time": "16.577",
"value": "Alton line_sentence_0"
},
{
"operation": "Highlighting",
"time": "25.422",
"value": "Alton line_sentence_1"
},
{
"operation": "Highlighting",
"time": "41.957",
"value": "Alton line_sentence_2"
},
{
"operation": "finish",
"time": "59.118",
"value": "finish"
}
]
}
|
exfever_5441
|
Mark Anthony “Baz” is best known for a 1992 Australian romantic comedy film.
|
{
"evidence": [
"Baz Luhrmann",
"Strictly Ballroom"
],
"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:\nMark Anthony “Baz” is best known for a 1992 Australian romantic comedy film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Baz Luhrmann",
"Strictly Ballroom"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 851,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
60808
|
The United States International University Africa (a private university in Uganda) was established in 1969 as the Nairobi Campus of United States International University (USIU), a San Diego -based institution; then in 1999, the USIU, Nairobi Campus, established itself as a separate university under its new name: USIU Africa.
|
{
"evidence": [
"United States International University Africa_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 United States International University Africa (a private university in Uganda) was established in 1969 as the Nairobi Campus of United States International University (USIU), a San Diego -based institution; then in 1999, the USIU, Nairobi Campus, established itself as a separate university under its new name: USIU Africa.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"United States International University Africa_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 852,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.83",
"value": "?search="
},
{
"operation": "search",
"time": "17.926",
"value": "United States International University Africa"
},
{
"operation": "Now on",
"time": "19.099",
"value": "United States International University Africa"
},
{
"operation": "Highlighting",
"time": "28.871",
"value": "United States International University Africa_sentence_0"
},
{
"operation": "finish",
"time": "52.869",
"value": "finish"
}
]
}
|
exfever_5253
|
Susan Sarandon is an American actress and activist who received an honor for the best British and international contributions to film and broadcast first on the BBC in 1957 with Vivien Leigh. Vivien Leigh was a British actress who played on stage in London's West End in 1949.
|
{
"evidence": [
"Susan Sarandon",
"British Academy Film Awards",
"Vivien Leigh"
],
"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:\nSusan Sarandon is an American actress and activist who received an honor for the best British and international contributions to film and broadcast first on the BBC in 1957 with Vivien Leigh. Vivien Leigh was a British actress who played on stage in London's West End in 1949.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Susan Sarandon",
"British Academy Film Awards",
"Vivien Leigh"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 853,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5732
|
The phalanx was composed of heavy infantry armed with a pole weapon consisting of shaft wood or may be made of durable material, such as a chemical element with the symbol Fe and atomic number 26.
|
{
"evidence": [
"Phalanx",
"Spear",
"Iron"
],
"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 phalanx was composed of heavy infantry armed with a pole weapon consisting of shaft wood or may be made of durable material, such as a chemical element with the symbol Fe and atomic number 26.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Phalanx",
"Spear",
"Iron"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 854,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5100
|
Taylor Sheridan is an Irish screenwriter, producer, film director, and actor who first reached prominence for portraying Danny Boyd in a teen noir mystery drama television series created by Rob Thomas.
|
{
"evidence": [
"Taylor Sheridan",
"Veronica Mars"
],
"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:\nTaylor Sheridan is an Irish screenwriter, producer, film director, and actor who first reached prominence for portraying Danny Boyd in a teen noir mystery drama television series created by Rob Thomas.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Taylor Sheridan",
"Veronica Mars"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 855,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
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": 856,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
4535
|
The largest city in Shangqu is Yong Cheng City which also has the highest area and population density.
|
{
"evidence": [
"Provinces of China_sentence_0"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe largest city in Shangqu is Yong Cheng City which also has the highest area and population density.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Provinces of China_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 857,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "26.63",
"value": "yong Cheng city"
},
{
"operation": "hyperlink",
"time": "30.229",
"value": "young chang city"
},
{
"operation": "search",
"time": "45.1",
"value": "Shangqu"
},
{
"operation": "back-button-clicked",
"time": "49.524",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "50.004",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "50.006",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "51.828",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "51.83",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "52.7",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "52.702",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "52.704",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "54.748",
"value": "back-button-clicked"
},
{
"operation": "search",
"time": "59.451",
"value": "Chinese provinces"
},
{
"operation": "Highlighting",
"time": "81.211",
"value": "Provinces of China_sentence_0"
},
{
"operation": "finish",
"time": "87.146",
"value": "finish"
}
]
}
|
76362
|
John Fettiplace who was a London draper who possessed the manors of East Shefford and had two sons is a member of the family Fettiplace (allegedly of Norman descent)
|
{
"evidence": [
"Fettiplace_sentence_10"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJohn Fettiplace who was a London draper who possessed the manors of East Shefford and had two sons is a member of the family Fettiplace (allegedly of Norman descent)\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Fettiplace_sentence_10"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 858,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.355",
"value": "?search="
},
{
"operation": "search",
"time": "13.088",
"value": "John Fettiplace"
},
{
"operation": "Now on",
"time": "14.116",
"value": "John Fettiplace"
},
{
"operation": "hyperlink",
"time": "108.701",
"value": "John Fettiplace (politician died 1580)"
},
{
"operation": "Now on",
"time": "109.484",
"value": "John Fettiplace (politician died 1580)"
},
{
"operation": "Page search",
"time": "263.773",
"value": "draper"
},
{
"operation": "back-button-clicked",
"time": "268.109",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "268.161",
"value": "John Fettiplace"
},
{
"operation": "hyperlink",
"time": "270.239",
"value": "John Fettiplace (politician died 1658)"
},
{
"operation": "Now on",
"time": "271.753",
"value": "John Fettiplace (politician died 1658)"
},
{
"operation": "Page search",
"time": "279.664",
"value": "draper"
},
{
"operation": "Page search",
"time": "290.383",
"value": "shefford"
},
{
"operation": "back-button-clicked",
"time": "295.386",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "295.438",
"value": "John Fettiplace"
},
{
"operation": "hyperlink",
"time": "303.356",
"value": "John Fettiplace (politician died 1580)"
},
{
"operation": "Now on",
"time": "304.077",
"value": "John Fettiplace (politician died 1580)"
},
{
"operation": "Page search",
"time": "308.421",
"value": "shefford"
},
{
"operation": "search",
"time": "328.939",
"value": "manors of east shefford"
},
{
"operation": "Now on",
"time": "330.624",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "333.386",
"value": "Fettiplace"
},
{
"operation": "Now on",
"time": "333.783",
"value": "Fettiplace"
},
{
"operation": "Page search",
"time": "459.428",
"value": "draper"
},
{
"operation": "Page search",
"time": "460.444",
"value": "draper"
},
{
"operation": "Highlighting",
"time": "464.44",
"value": "Fettiplace_sentence_8"
},
{
"operation": "Highlighting",
"time": "469.649",
"value": "Fettiplace_sentence_9"
},
{
"operation": "Highlighting",
"time": "479.193",
"value": "Fettiplace_sentence_10"
},
{
"operation": "Highlighting deleted",
"time": "479.856",
"value": "Fettiplace_sentence_9"
},
{
"operation": "Highlighting deleted",
"time": "480.729",
"value": "Fettiplace_sentence_8"
},
{
"operation": "finish",
"time": "487.745",
"value": "finish"
}
]
}
|
2761
|
The Man from Hong Kong was a 1975 action film starring Jimmy Wang Yu and funded by Golden Harvest, Greater Union, and the Australian Film Development Commission.
|
{
"evidence": [
"The Man from Hong Kong_sentence_2",
"The Man from Hong Kong_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:\nThe Man from Hong Kong was a 1975 action film starring Jimmy Wang Yu and funded by Golden Harvest, Greater Union, and the Australian Film Development Commission.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"The Man from Hong Kong_sentence_2",
"The Man from Hong Kong_sentence_7"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 859,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "17.283",
"value": "The Man from Hong Kong"
},
{
"operation": "Highlighting",
"time": "29.029",
"value": "The Man from Hong Kong_sentence_2"
},
{
"operation": "Highlighting",
"time": "60.174",
"value": "The Man from Hong Kong_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "64.73",
"value": "The Man from Hong Kong_sentence_5"
},
{
"operation": "Highlighting",
"time": "76.624",
"value": "The Man from Hong Kong_sentence_7"
},
{
"operation": "finish",
"time": "87.308",
"value": "finish"
}
]
}
|
77672
|
A masking agent is a reagent used in chemical analysis which reacts with chemical species that may interfere in the analysis, while in sports it is used to hide or prevent detection of a banned substance or illegal drugs like anabolic steroids (which include natural androgens like testosterone) or stimulants.
|
{
"evidence": [
"Masking agent_sentence_1",
"Masking agent_sentence_2",
"Anabolic steroid_sentence_2"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nA masking agent is a reagent used in chemical analysis which reacts with chemical species that may interfere in the analysis, while in sports it is used to hide or prevent detection of a banned substance or illegal drugs like anabolic steroids (which include natural androgens like testosterone) or stimulants.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Masking agent_sentence_1",
"Masking agent_sentence_2",
"Anabolic steroid_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 860,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.03",
"value": "?search="
},
{
"operation": "search",
"time": "20.126",
"value": "Masking agent"
},
{
"operation": "Now on",
"time": "20.82",
"value": "Masking agent"
},
{
"operation": "Highlighting",
"time": "31.873",
"value": "Masking agent_sentence_1"
},
{
"operation": "Highlighting",
"time": "34.432",
"value": "Masking agent_sentence_2"
},
{
"operation": "hyperlink",
"time": "43.872",
"value": "anabolic steroids"
},
{
"operation": "Now on",
"time": "45.919",
"value": "Anabolic steroid"
},
{
"operation": "Highlighting",
"time": "56.912",
"value": "Anabolic steroid_sentence_2"
},
{
"operation": "finish",
"time": "63.64",
"value": "finish"
}
]
}
|
7766
|
Emma Albani was a soloist in the world premiere of Charles Wugk Sabatier's Cantata, and was was also awarded a gold medal for musical composition from that convent.
|
{
"evidence": [
"Emma Albani_sentence_12",
"Emma Albani_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:\nEmma Albani was a soloist in the world premiere of Charles Wugk Sabatier's Cantata, and was was also awarded a gold medal for musical composition from that convent.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Emma Albani_sentence_12",
"Emma Albani_sentence_13"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 861,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.572",
"value": "?search="
},
{
"operation": "search",
"time": "12.173",
"value": "Emma Albani"
},
{
"operation": "Now on",
"time": "13.076",
"value": "Emma Albani"
},
{
"operation": "Highlighting",
"time": "41.494",
"value": "Emma Albani_sentence_12"
},
{
"operation": "Highlighting",
"time": "58.399",
"value": "Emma Albani_sentence_13"
},
{
"operation": "finish",
"time": "74.862",
"value": "finish"
}
]
}
|
75476
|
Fauske Lysverk is a private power company that operates the power grid in Bergen, Norway.
|
{
"evidence": [
"Fauske Lysverk_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:\nFauske Lysverk is a private power company that operates the power grid in Bergen, Norway.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Fauske Lysverk_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 862,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.942",
"value": "?search="
},
{
"operation": "search",
"time": "9.999",
"value": "Fauske Lysverk"
},
{
"operation": "Now on",
"time": "10.917",
"value": "Fauske Lysverk"
},
{
"operation": "Highlighting",
"time": "16.355",
"value": "Fauske Lysverk_sentence_0"
},
{
"operation": "finish",
"time": "38.141",
"value": "finish"
}
]
}
|
51359
|
Based on evidences of the isolated 20S proteasome complex crystal structure, protein proteasome subunit beta type-3 contributes to form a proteolytic environment for substrate degradation, as one of 28 subunits of 20S proteasome.
|
{
"evidence": [
"Proteasome (prosome, macropain) subunit, alpha 1_sentence_13",
"PSMB3_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:\nBased on evidences of the isolated 20S proteasome complex crystal structure, protein proteasome subunit beta type-3 contributes to form a proteolytic environment for substrate degradation, as one of 28 subunits of 20S proteasome.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Proteasome (prosome, macropain) subunit, alpha 1_sentence_13",
"PSMB3_sentence_14"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 863,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.492",
"value": "?search="
},
{
"operation": "search",
"time": "127.066",
"value": "Isolated 20 S proteasome complex crystal structure"
},
{
"operation": "Now on",
"time": "129.05",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "149.299",
"value": "isolated 20 s protease complex crystal structure"
},
{
"operation": "Now on",
"time": "150.354",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "154.356",
"value": "isolated 20 s proteinase complex crystal structure"
},
{
"operation": "Now on",
"time": "155.612",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "180.723",
"value": "Proteasome (prosome, macropain) subunit, alpha 1"
},
{
"operation": "Now on",
"time": "181.848",
"value": "Proteasome (prosome, macropain) subunit, alpha 1"
},
{
"operation": "search",
"time": "256.721",
"value": "Proteasome 20s complex crystal structure"
},
{
"operation": "Now on",
"time": "257.778",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "268.865",
"value": "Proteasome (prosome, macropain) subunit, alpha 1"
},
{
"operation": "Now on",
"time": "269.772",
"value": "Proteasome (prosome, macropain) subunit, alpha 1"
},
{
"operation": "Highlighting",
"time": "321.536",
"value": "Proteasome (prosome, macropain) subunit, alpha 1_sentence_13"
},
{
"operation": "Highlighting",
"time": "558.039",
"value": "Proteasome (prosome, macropain) subunit, alpha 1_sentence_18"
},
{
"operation": "Highlighting",
"time": "605.1",
"value": "Proteasome (prosome, macropain) subunit, alpha 1_sentence_6"
},
{
"operation": "Highlighting",
"time": "605.103",
"value": "Proteasome (prosome, macropain) subunit, alpha 1_section_0"
},
{
"operation": "Highlighting",
"time": "605.104",
"value": "Proteasome (prosome, macropain) subunit, alpha 1_section_1"
},
{
"operation": "search",
"time": "724.63",
"value": "Sub Unit Beta Type 3"
},
{
"operation": "Now on",
"time": "727.753",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "782.164",
"value": "Tertiary structure Protein domain_section_3"
},
{
"operation": "Now on",
"time": "783.746",
"value": "Protein domain#Tertiary structure Protein domain section 3"
},
{
"operation": "search",
"time": "874.618",
"value": "Protein sub unit beta type 3"
},
{
"operation": "Now on",
"time": "875.754",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "889.1",
"value": "Protein–protein interactions Opioid receptor_section_9"
},
{
"operation": "Now on",
"time": "890.273",
"value": "Opioid receptor#Protein.E2.80.93protein interactions Opioid receptor section 9"
},
{
"operation": "back-button-clicked",
"time": "1026.511",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "1027.185",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "1028.275",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "1029.2",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "1030.042",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "1030.051",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "1030.217",
"value": "Proteasome (prosome, macropain) subunit, alpha 1"
},
{
"operation": "search",
"time": "1058.986",
"value": "Proteasome subunit beta type-3"
},
{
"operation": "Now on",
"time": "1060.082",
"value": "PSMB3"
},
{
"operation": "Highlighting",
"time": "1089.541",
"value": "PSMB3_sentence_2"
},
{
"operation": "Highlighting",
"time": "1140.414",
"value": "PSMB3_sentence_14"
},
{
"operation": "Highlighting",
"time": "1169.582",
"value": "PSMB3_sentence_18"
},
{
"operation": "finish",
"time": "1526.189",
"value": "finish"
}
]
}
|
exfever_8132
|
Wentworth was filmed on purpose-built sets in the suburbs of Clayton, Victoria.
|
{
"evidence": [
"Wentworth (TV series)",
"Reg Watson"
],
"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:\nWentworth was filmed on purpose-built sets in the suburbs of Clayton, Victoria.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Wentworth (TV series)",
"Reg Watson"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 864,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
79920
|
Allan Pred served as the chair of the UC Berkeley, his books are required reading in multiple college courses and had a son called Michele Pred who was born in San Francisco. .
|
{
"evidence": [
"Allan Pred_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:\nAllan Pred served as the chair of the UC Berkeley, his books are required reading in multiple college courses and had a son called Michele Pred who was born in San Francisco. .\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Allan Pred_sentence_5"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 865,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.255",
"value": "?search="
},
{
"operation": "search",
"time": "240.137",
"value": "Allan Pred"
},
{
"operation": "Now on",
"time": "241.246",
"value": "Allan Pred"
},
{
"operation": "Highlighting",
"time": "290.559",
"value": "Allan Pred_sentence_4"
},
{
"operation": "Highlighting",
"time": "337.311",
"value": "Allan Pred_sentence_7"
},
{
"operation": "Highlighting",
"time": "361.366",
"value": "Allan Pred_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "383.542",
"value": "Allan Pred_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "385.838",
"value": "Allan Pred_sentence_7"
},
{
"operation": "finish",
"time": "408.254",
"value": "finish"
}
]
}
|
exfever_8548
|
Factory Girl is a true story based on the rapid rise and fall of 1960s underground film star and socialite Edie Sedgwick.
|
{
"evidence": [
"Sienna Miller",
"The Edge of Love",
"Biographical film"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nFactory Girl is a true story based on the rapid rise and fall of 1960s underground film star and socialite Edie Sedgwick.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Sienna Miller",
"The Edge of Love",
"Biographical film"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 866,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6889
|
Houston is the most populous city in the second-largest U.S. state by population after a state in the Western United States that has over 39.5 million residents.
|
{
"evidence": [
"Houston",
"Texas",
"California"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nHouston is the most populous city in the second-largest U.S. state by population after a state in the Western United States that has over 39.5 million residents.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Houston",
"Texas",
"California"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 867,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
72485
|
The Pacific Center for Human Growth is known for their eclecticism and liberalism, and offers peer support groups.
|
{
"evidence": [
"Pacific Center for Human Growth_sentence_12",
"Pacific Center for Human Growth_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:\nThe Pacific Center for Human Growth is known for their eclecticism and liberalism, and offers peer support groups.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Pacific Center for Human Growth_sentence_12",
"Pacific Center for Human Growth_sentence_14"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 868,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.809",
"value": "?search="
},
{
"operation": "search",
"time": "13.903",
"value": "The Pacific Center for Human Growth"
},
{
"operation": "Now on",
"time": "16.517",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "25.898",
"value": "Pacific Center for Human Growth"
},
{
"operation": "Now on",
"time": "26.562",
"value": "Pacific Center for Human Growth"
},
{
"operation": "Highlighting",
"time": "99.552",
"value": "Pacific Center for Human Growth_sentence_12"
},
{
"operation": "Highlighting",
"time": "120.717",
"value": "Pacific Center for Human Growth_sentence_14"
},
{
"operation": "finish",
"time": "133.9",
"value": "finish"
}
]
}
|
exfever_5917
|
Winona Ryder gained attention with her performance in Tim Burton's 1988 African fantasy comedy film.
|
{
"evidence": [
"Winona Ryder",
"Beetlejuice"
],
"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:\nWinona Ryder gained attention with her performance in Tim Burton's 1988 African fantasy comedy film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Winona Ryder",
"Beetlejuice"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 869,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2324
|
Timur gained control of the western Chagatai Khanate by September 1370.
|
{
"evidence": [
"Timur",
"Turco-Mongol tradition"
],
"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:\nTimur gained control of the western Chagatai Khanate by September 1370.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Timur",
"Turco-Mongol tradition"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 870,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
81558
|
After retiring as a player, Pennock (regarded as one of the greatest left-handed pitchers in baseball history) served as a coach and farm system director for the Red Sox, and as general manager of the Philadelphia Phillies.
|
{
"evidence": [
"Herb Pennock_sentence_7",
"Herb Pennock_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:\nAfter retiring as a player, Pennock (regarded as one of the greatest left-handed pitchers in baseball history) served as a coach and farm system director for the Red Sox, and as general manager of the Philadelphia Phillies.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Herb Pennock_sentence_7",
"Herb Pennock_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 871,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.075",
"value": "?search="
},
{
"operation": "search",
"time": "16.794",
"value": "Pennock"
},
{
"operation": "Now on",
"time": "17.625",
"value": "Pennock"
},
{
"operation": "hyperlink",
"time": "22.823",
"value": "Pennock (surname)"
},
{
"operation": "Now on",
"time": "23.495",
"value": "Pennock (surname)"
},
{
"operation": "hyperlink",
"time": "30.535",
"value": "Herb Pennock"
},
{
"operation": "Now on",
"time": "31.571",
"value": "Herb Pennock"
},
{
"operation": "Highlighting",
"time": "54.284",
"value": "Herb Pennock_sentence_7"
},
{
"operation": "Highlighting",
"time": "62.623",
"value": "Herb Pennock_sentence_6"
},
{
"operation": "finish",
"time": "77.311",
"value": "finish"
}
]
}
|
2187
|
The United Kingdom has had the same deputy prime minister from 1962 until 1979.
|
{
"evidence": [
"Deputy Prime Minister of the United Kingdom_sentence_17",
"Deputy Prime Minister of the United Kingdom_sentence_18",
"Deputy Prime Minister of the United Kingdom_sentence_19",
"Deputy Prime Minister of the United Kingdom_sentence_20",
"Deputy Prime Minister of the United Kingdom_sentence_21",
"Deputy Prime Minister of the United Kingdom_sentence_22"
],
"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 United Kingdom has had the same deputy prime minister from 1962 until 1979.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Deputy Prime Minister of the United Kingdom_sentence_17",
"Deputy Prime Minister of the United Kingdom_sentence_18",
"Deputy Prime Minister of the United Kingdom_sentence_19",
"Deputy Prime Minister of the United Kingdom_sentence_20",
"Deputy Prime Minister of the United Kingdom_sentence_21",
"Deputy Prime Minister of the United Kingdom_sentence_22"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 872,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "179.611",
"value": "United Kingdom deputy prime minister"
},
{
"operation": "hyperlink",
"time": "195.944",
"value": "Deputy Prime Minister of the United Kingdom"
},
{
"operation": "Highlighting",
"time": "247.15",
"value": "Deputy Prime Minister of the United Kingdom_sentence_17"
},
{
"operation": "Highlighting",
"time": "254.283",
"value": "Deputy Prime Minister of the United Kingdom_sentence_18"
},
{
"operation": "Highlighting",
"time": "263.719",
"value": "Deputy Prime Minister of the United Kingdom_sentence_19"
},
{
"operation": "Highlighting",
"time": "269.458",
"value": "Deputy Prime Minister of the United Kingdom_sentence_20"
},
{
"operation": "Highlighting",
"time": "283.195",
"value": "Deputy Prime Minister of the United Kingdom_sentence_21"
},
{
"operation": "Highlighting",
"time": "289.825",
"value": "Deputy Prime Minister of the United Kingdom_sentence_22"
},
{
"operation": "finish",
"time": "298.317",
"value": "finish"
}
]
}
|
18475
|
Vanu is a large city in the rural district of Kakavand-e Sharqi.
|
{
"evidence": [
"Vanu_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:\nVanu is a large city in the rural district of Kakavand-e Sharqi.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Vanu_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 873,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.855",
"value": "?search="
},
{
"operation": "search",
"time": "6.299",
"value": "Vanu"
},
{
"operation": "Now on",
"time": "6.894",
"value": "Vanu"
},
{
"operation": "Highlighting",
"time": "27.093",
"value": "Vanu_cell_0_7_1"
},
{
"operation": "Highlighting",
"time": "27.097",
"value": "Vanu_header_cell_0_7_0"
},
{
"operation": "Highlighting",
"time": "27.097",
"value": "Vanu_header_cell_0_6_0"
},
{
"operation": "Highlighting",
"time": "38.711",
"value": "Vanu_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "40.819",
"value": "Vanu_cell_0_7_1"
},
{
"operation": "Highlighting deleted",
"time": "40.824",
"value": "Vanu_header_cell_0_7_0"
},
{
"operation": "Highlighting deleted",
"time": "40.825",
"value": "Vanu_header_cell_0_6_0"
},
{
"operation": "finish",
"time": "53.327",
"value": "finish"
}
]
}
|
79799
|
The Faversham Miniature Railway relocated to Norton Ash Garden Centre, and in 2002, relocated again to Brogdale Farm.
|
{
"evidence": [
"Faversham Miniature Railway_sentence_5",
"Faversham Miniature Railway_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:\nThe Faversham Miniature Railway relocated to Norton Ash Garden Centre, and in 2002, relocated again to Brogdale Farm.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Faversham Miniature Railway_sentence_5",
"Faversham Miniature Railway_sentence_8"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 874,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.333",
"value": "?search="
},
{
"operation": "search",
"time": "11.374",
"value": "Faversham Miniature Railway"
},
{
"operation": "Now on",
"time": "12.238",
"value": "Faversham Miniature Railway"
},
{
"operation": "Page search",
"time": "29.372",
"value": "Garden"
},
{
"operation": "Highlighting",
"time": "44.659",
"value": "Faversham Miniature Railway_sentence_5"
},
{
"operation": "Highlighting",
"time": "61.555",
"value": "Faversham Miniature Railway_sentence_8"
},
{
"operation": "Highlighting deleted",
"time": "64.731",
"value": "Faversham Miniature Railway_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "69.899",
"value": "Faversham Miniature Railway_sentence_8"
},
{
"operation": "Highlighting",
"time": "75.419",
"value": "Faversham Miniature Railway_sentence_5"
},
{
"operation": "Highlighting",
"time": "79.371",
"value": "Faversham Miniature Railway_sentence_8"
},
{
"operation": "finish",
"time": "87.013",
"value": "finish"
}
]
}
|
47576
|
The Danesbury Park, a 24.5 hectare public park and Local Nature Reserve in Welwyn in Hertfordshire, has grassland with many varieties of flowering plants; and has access from a number of roads including Codicote Road.
|
{
"evidence": [
"Danesbury Park_sentence_0",
"Danesbury Park_sentence_3",
"Danesbury Park_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 Danesbury Park, a 24.5 hectare public park and Local Nature Reserve in Welwyn in Hertfordshire, has grassland with many varieties of flowering plants; and has access from a number of roads including Codicote Road.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Danesbury Park_sentence_0",
"Danesbury Park_sentence_3",
"Danesbury Park_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 875,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.75",
"value": "?search="
},
{
"operation": "search",
"time": "13.952",
"value": "Danesbury Park"
},
{
"operation": "Now on",
"time": "14.834",
"value": "Danesbury Park"
},
{
"operation": "Highlighting",
"time": "22.947",
"value": "Danesbury Park_sentence_0"
},
{
"operation": "Highlighting",
"time": "29.301",
"value": "Danesbury Park_sentence_3"
},
{
"operation": "Highlighting",
"time": "36.607",
"value": "Danesbury Park_sentence_4"
},
{
"operation": "finish",
"time": "44.724",
"value": "finish"
}
]
}
|
44217
|
The 2012 Ghanaian parliamentary election in Buem resulted in Henry Ford Kofi Kamel achieving 73.8% of the votes for the National Democratic Congress.
|
{
"evidence": [
"Henry Ford Kamel_sentence_10",
"Henry Ford Kamel_sentence_11",
"Henry Ford Kamel_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:\nThe 2012 Ghanaian parliamentary election in Buem resulted in Henry Ford Kofi Kamel achieving 73.8% of the votes for the National Democratic Congress.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Henry Ford Kamel_sentence_10",
"Henry Ford Kamel_sentence_11",
"Henry Ford Kamel_sentence_7"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 876,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.968",
"value": "?search="
},
{
"operation": "search",
"time": "7.067",
"value": "2012 Ghanaian parliamentary election"
},
{
"operation": "Now on",
"time": "9.237",
"value": "2012 Ghanaian general election"
},
{
"operation": "Page search",
"time": "98.672",
"value": "buem"
},
{
"operation": "hyperlink",
"time": "122.779",
"value": "2012 Ghanaian parliamentary election"
},
{
"operation": "Now on",
"time": "124.254",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "125.486",
"value": "2012 Ghanaian general election"
},
{
"operation": "Now on",
"time": "127.032",
"value": "2012 Ghanaian general election"
},
{
"operation": "search",
"time": "132.258",
"value": "2012 Ghanaian parliamentary election"
},
{
"operation": "Now on",
"time": "133.27",
"value": "2012 Ghanaian parliamentary election"
},
{
"operation": "Page search",
"time": "172.862",
"value": "Henry Ford Kofi Kamel"
},
{
"operation": "Page search",
"time": "177.076",
"value": "Kofi Kamel"
},
{
"operation": "hyperlink",
"time": "181.276",
"value": "List of MPs elected in the 2012 Ghanaian parliamentary election"
},
{
"operation": "Now on",
"time": "182.312",
"value": "List of MPs elected in the 2012 Ghanaian parliamentary election"
},
{
"operation": "Page search",
"time": "190.453",
"value": "Kofi Kamel"
},
{
"operation": "search",
"time": "212.38",
"value": "Henry Ford Kofi Kamel"
},
{
"operation": "Now on",
"time": "213.529",
"value": "Henry Ford Kamel"
},
{
"operation": "Highlighting",
"time": "236.262",
"value": "Henry Ford Kamel_sentence_10"
},
{
"operation": "Highlighting",
"time": "239.254",
"value": "Henry Ford Kamel_sentence_11"
},
{
"operation": "Highlighting",
"time": "241.706",
"value": "Henry Ford Kamel_sentence_7"
},
{
"operation": "hyperlink",
"time": "244.599",
"value": "2008 Ghanaian general election"
},
{
"operation": "Now on",
"time": "245.699",
"value": "2008 Ghanaian general election"
},
{
"operation": "back-button-clicked",
"time": "254.274",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "255.026",
"value": "Henry Ford Kamel"
},
{
"operation": "finish",
"time": "258.037",
"value": "finish"
}
]
}
|
94103
|
The summer transfer window, which is the period during the year in which a football club can transfer players from other playing staff into their playing staff. that opened on 1 July 2015 and ended on 1 September 2015.
|
{
"evidence": [
"Transfer window_sentence_0",
"Transfer window_sentence_16"
],
"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 summer transfer window, which is the period during the year in which a football club can transfer players from other playing staff into their playing staff. that opened on 1 July 2015 and ended on 1 September 2015.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Transfer window_sentence_0",
"Transfer window_sentence_16"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 877,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.358",
"value": "?search="
},
{
"operation": "search",
"time": "11.454",
"value": "Contains...summer transfer window"
},
{
"operation": "Now on",
"time": "14.709",
"value": "undefined"
},
{
"operation": "search",
"time": "25.606",
"value": "\"summer transfer window\""
},
{
"operation": "Now on",
"time": "27.141",
"value": "undefined"
},
{
"operation": "search",
"time": "48.56",
"value": "\"summer transfer window 2015\""
},
{
"operation": "Now on",
"time": "49.885",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "62.456",
"value": "List of Norwegian football transfers summer 2015"
},
{
"operation": "Now on",
"time": "63.919",
"value": "List of Norwegian football transfers summer 2015"
},
{
"operation": "search",
"time": "90.065",
"value": "\"period during the year in which a football club can transfer players from other playing staff\""
},
{
"operation": "Now on",
"time": "91.945",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "93.571",
"value": "Transfer window"
},
{
"operation": "Now on",
"time": "94.575",
"value": "Transfer window"
},
{
"operation": "Highlighting",
"time": "97.162",
"value": "Transfer window_sentence_0"
},
{
"operation": "Page search",
"time": "121.836",
"value": "summer"
},
{
"operation": "Highlighting",
"time": "199.106",
"value": "Transfer window_cell_0_8_0"
},
{
"operation": "Highlighting",
"time": "199.111",
"value": "Transfer window_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "205.267",
"value": "Transfer window_cell_0_8_0"
},
{
"operation": "Highlighting deleted",
"time": "205.273",
"value": "Transfer window_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "215.447",
"value": "Transfer window_sentence_16"
},
{
"operation": "finish",
"time": "224.775",
"value": "finish"
}
]
}
|
exfever_7724
|
SpongeBob SquarePants is an Canadian comedy television series made using animation techniques with a common series title, usually related to one another.
|
{
"evidence": [
"SpongeBob SquarePants",
"Animated series"
],
"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:\nSpongeBob SquarePants is an Canadian comedy television series made using animation techniques with a common series title, usually related to one another.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"SpongeBob SquarePants",
"Animated series"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 878,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4329
|
iZombie is an American supernatural procedural crime drama television series that is a loose adaptation of the comic book series of the same name, co-created by an author who was best known for his alternate history novels and short stories.
|
{
"evidence": [
"IZombie (TV series)",
"Chris Roberson (author)"
],
"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:\niZombie is an American supernatural procedural crime drama television series that is a loose adaptation of the comic book series of the same name, co-created by an author who was best known for his alternate history novels and short stories.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"IZombie (TV series)",
"Chris Roberson (author)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 879,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3461
|
The Boeing 707 is an American long-range narrow-body airliner that was developed from the quadjet prototype aircraft built by Boeing to demonstrate the advantages of jet propulsion for commercial aviation.
|
{
"evidence": [
"Boeing 707",
"Boeing 367-80"
],
"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 Boeing 707 is an American long-range narrow-body airliner that was developed from the quadjet prototype aircraft built by Boeing to demonstrate the advantages of jet propulsion for commercial aviation.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Boeing 707",
"Boeing 367-80"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 880,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
24125
|
The Shaw Library, or the Founder's Room, is a general-purpose library accessible to all members of the university and a common room at the London School of Economics and Political Science located on the sixth floor of the Old Building.
|
{
"evidence": [
"LSE Shaw Library_sentence_0",
"LSE Shaw Library_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 Shaw Library, or the Founder's Room, is a general-purpose library accessible to all members of the university and a common room at the London School of Economics and Political Science located on the sixth floor of the Old Building.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"LSE Shaw Library_sentence_0",
"LSE Shaw Library_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 881,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0",
"value": "?search="
},
{
"operation": "search",
"time": "0.01",
"value": "Shaw Library"
},
{
"operation": "Now on",
"time": "0.012",
"value": "Shaw Library"
},
{
"operation": "search",
"time": "0.03",
"value": "Founder's Room"
},
{
"operation": "Now on",
"time": "0.032",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "0.039",
"value": "LSE Shaw Library"
},
{
"operation": "Now on",
"time": "0.039",
"value": "LSE Shaw Library"
},
{
"operation": "Highlighting",
"time": "0.042",
"value": "LSE Shaw Library_sentence_0"
},
{
"operation": "Highlighting",
"time": "0.05",
"value": "LSE Shaw Library_sentence_1"
},
{
"operation": "finish",
"time": "0.076",
"value": "finish"
},
{
"operation": "Now on",
"time": "1619982353.647",
"value": "LSE Shaw Library"
},
{
"operation": "search",
"time": "1619982366.989",
"value": "Shaw Library"
},
{
"operation": "Now on",
"time": "1619982367.539",
"value": "Shaw Library"
},
{
"operation": "finish",
"time": "1619982374.076",
"value": "finish"
}
]
}
|
exfever_964
|
The Sopranos is an American comedy drama television series created by David Chase that features a psychiatrist character named Jennifer Melfi, played by an American actress known for her husky voice and Brooklyn accent.
|
{
"evidence": [
"The Sopranos",
"Lorraine Bracco"
],
"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 Sopranos is an American comedy drama television series created by David Chase that features a psychiatrist character named Jennifer Melfi, played by an American actress known for her husky voice and Brooklyn accent.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Sopranos",
"Lorraine Bracco"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 882,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
35913
|
The Central Warwickshire Youth Football League had an Under 16s representative side who did not win against the Stratford-upon-Avon League and Notts Elizabethen League; then in 1978, "Gordon Beard era" and the famous Olton Ravens started.
|
{
"evidence": [
"Central Warwickshire Youth Football League_sentence_24"
],
"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 Central Warwickshire Youth Football League had an Under 16s representative side who did not win against the Stratford-upon-Avon League and Notts Elizabethen League; then in 1978, \"Gordon Beard era\" and the famous Olton Ravens started.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Central Warwickshire Youth Football League_sentence_24"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 883,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.884",
"value": "?search="
},
{
"operation": "search",
"time": "9.619",
"value": "Central Warwickshire Youth Football League"
},
{
"operation": "Now on",
"time": "11.03",
"value": "Central Warwickshire Youth Football League"
},
{
"operation": "Highlighting",
"time": "26.448",
"value": "Central Warwickshire Youth Football League_header_cell_2_0_10"
},
{
"operation": "Highlighting",
"time": "26.451",
"value": "Central Warwickshire Youth Football League_section_4"
},
{
"operation": "Highlighting deleted",
"time": "52.84",
"value": "Central Warwickshire Youth Football League_header_cell_2_0_10"
},
{
"operation": "Highlighting deleted",
"time": "52.846",
"value": "Central Warwickshire Youth Football League_section_4"
},
{
"operation": "search",
"time": "81.312",
"value": "Central Warwickshire Youth Football League under 16s"
},
{
"operation": "Now on",
"time": "84.011",
"value": "undefined"
},
{
"operation": "search",
"time": "106.347",
"value": "Contains...\"Gordon Beard era\""
},
{
"operation": "Now on",
"time": "107.632",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "109.686",
"value": "Central Warwickshire Youth Football League"
},
{
"operation": "Now on",
"time": "110.068",
"value": "Central Warwickshire Youth Football League"
},
{
"operation": "Page search",
"time": "112.711",
"value": "Gordon Beard era"
},
{
"operation": "Highlighting",
"time": "116.876",
"value": "Central Warwickshire Youth Football League_sentence_24"
},
{
"operation": "finish",
"time": "146.586",
"value": "finish"
}
]
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.