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 |
|---|---|---|---|---|---|---|---|---|
88156
|
Jamar Diggs played eight games in Baltic League, where he recorded 11.8 ppg, 3.6 rpg and 3.5 apg in 2012–13 season; then played at APOEL in the 2013–14 season, where he became a runner-up after winning the Cypriot 1st Division with the club.
|
{
"evidence": [
"Jamar Diggs_sentence_13"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJamar Diggs played eight games in Baltic League, where he recorded 11.8 ppg, 3.6 rpg and 3.5 apg in 2012–13 season; then played at APOEL in the 2013–14 season, where he became a runner-up after winning the Cypriot 1st Division with the club.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jamar Diggs_sentence_13"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3084,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.132",
"value": "?search="
},
{
"operation": "search",
"time": "8.564",
"value": "Jamar Diggs"
},
{
"operation": "Now on",
"time": "9.362",
"value": "Jamar Diggs"
},
{
"operation": "Page search",
"time": "30.329",
"value": "Baltic"
},
{
"operation": "Highlighting",
"time": "35.954",
"value": "Jamar Diggs_sentence_12"
},
{
"operation": "Highlighting",
"time": "45.954",
"value": "Jamar Diggs_sentence_13"
},
{
"operation": "Highlighting deleted",
"time": "47",
"value": "Jamar Diggs_sentence_12"
},
{
"operation": "finish",
"time": "60.609",
"value": "finish"
}
]
}
|
exfever_2841
|
Nicholas Jerry Jonas is an American singer who formed a band with his older brothers that appeared in the widely successful 2008 American musical television film directed by Matthew Diamond.
|
{
"evidence": [
"Nick Jonas",
"Camp Rock"
],
"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 Jerry Jonas is an American singer who formed a band with his older brothers that appeared in the widely successful 2008 American musical television film directed by Matthew Diamond.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Nick Jonas",
"Camp Rock"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3085,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
63405
|
The "Mirror of Reflection" was built to make the dead see their sins, such as having weak faith in the Buddha, the founder of the world religion of Buddhism.
|
{
"evidence": [
"Jade Record_sentence_4",
"Jade Record_sentence_5",
"Gautama Buddha_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 \"Mirror of Reflection\" was built to make the dead see their sins, such as having weak faith in the Buddha, the founder of the world religion of Buddhism.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Jade Record_sentence_4",
"Jade Record_sentence_5",
"Gautama Buddha_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3086,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.535",
"value": "?search="
},
{
"operation": "search",
"time": "3.645",
"value": "Mirror of Reflection"
},
{
"operation": "Now on",
"time": "5.422",
"value": "undefined"
},
{
"operation": "search",
"time": "29.725",
"value": "jade record"
},
{
"operation": "Now on",
"time": "32.295",
"value": "Jade Record"
},
{
"operation": "Highlighting",
"time": "60.89",
"value": "Jade Record_sentence_4"
},
{
"operation": "Highlighting",
"time": "65.844",
"value": "Jade Record_sentence_5"
},
{
"operation": "hyperlink",
"time": "69.416",
"value": "Buddha"
},
{
"operation": "Now on",
"time": "71.688",
"value": "Gautama Buddha"
},
{
"operation": "Highlighting",
"time": "73.31",
"value": "Gautama Buddha_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "74.206",
"value": "Gautama Buddha_sentence_5"
},
{
"operation": "Highlighting",
"time": "75.44",
"value": "Gautama Buddha_sentence_6"
},
{
"operation": "finish",
"time": "81.829",
"value": "finish"
}
]
}
|
exfever_5655
|
Spiders are air-breathing arthropods that have eight legs and belong to Chelicerata, wherein mouthparts are with fangs.
|
{
"evidence": [
"Spider",
"Chelicerae"
],
"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:\nSpiders are air-breathing arthropods that have eight legs and belong to Chelicerata, wherein mouthparts are with fangs.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Spider",
"Chelicerae"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3087,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8122
|
Glen Travis Campbell was a guitarist and singer who had several hit songs, including a song written by Jimmy Webb and released on Capitol Records in 1967.
|
{
"evidence": [
"Glen Campbell",
"By the Time I Get to Phoenix"
],
"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:\nGlen Travis Campbell was a guitarist and singer who had several hit songs, including a song written by Jimmy Webb and released on Capitol Records in 1967.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Glen Campbell",
"By the Time I Get to Phoenix"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3088,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
65883
|
Glenn Gruenhagen was raised on a dairy farm near Glencoe, he is a veteran of the United States Marine Corps and was a small business owner.
|
{
"evidence": [
"Glenn Gruenhagen_sentence_3",
"Glenn Gruenhagen_sentence_4",
"Glenn Gruenhagen_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:\nGlenn Gruenhagen was raised on a dairy farm near Glencoe, he is a veteran of the United States Marine Corps and was a small business owner.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Glenn Gruenhagen_sentence_3",
"Glenn Gruenhagen_sentence_4",
"Glenn Gruenhagen_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3089,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "3.947",
"value": "?search="
},
{
"operation": "search",
"time": "17.424",
"value": "Glenn Gruenhagen"
},
{
"operation": "Now on",
"time": "18.609",
"value": "Glenn Gruenhagen"
},
{
"operation": "Highlighting",
"time": "24.503",
"value": "Glenn Gruenhagen_sentence_3"
},
{
"operation": "Highlighting",
"time": "28.007",
"value": "Glenn Gruenhagen_sentence_4"
},
{
"operation": "Highlighting",
"time": "32.903",
"value": "Glenn Gruenhagen_sentence_2"
},
{
"operation": "finish",
"time": "107.658",
"value": "finish"
}
]
}
|
exfever_6576
|
Juilliard is one of the best drama schools to earn an acting degree.
|
{
"evidence": [
"Drama school",
"Academic department"
],
"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:\nJuilliard is one of the best drama schools to earn an acting degree.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Drama school",
"Academic department"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3090,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5891
|
Gimli, the son of Glóin, is a fictional character in Middle-earth by an English writer, poet, philologist, and academic, best known as the author of The Hobbit.
|
{
"evidence": [
"Gimli (Middle-earth)",
"J. R. R. Tolkien"
],
"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:\nGimli, the son of Glóin, is a fictional character in Middle-earth by an English writer, poet, philologist, and academic, best known as the author of The Hobbit.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Gimli (Middle-earth)",
"J. R. R. Tolkien"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3091,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1570
|
Hugh Michael Jackman is an Australian actor best known for his films X-Men and the 2004 action gothic horror film written and directed by Stephen Sommers.
|
{
"evidence": [
"Hugh Jackman",
"Van Helsing (film)"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nHugh Michael Jackman is an Australian actor best known for his films X-Men and the 2004 action gothic horror film written and directed by Stephen Sommers.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Hugh Jackman",
"Van Helsing (film)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3092,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_173
|
Melisandre of Asshai is a fictional character in the A Song of Ice and Fire series of fantasy novels by the American novelist, screenwriter, television producer, and short-story writer.
|
{
"evidence": [
"Melisandre",
"George R. R. Martin"
],
"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:\nMelisandre of Asshai is a fictional character in the A Song of Ice and Fire series of fantasy novels by the American novelist, screenwriter, television producer, and short-story writer.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Melisandre",
"George R. R. Martin"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3093,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2900
|
Sully is a 2016 American film directed by Clint Eastwood which is a biographical category of narrative fiction intended to be more serious than humorous in tone.
|
{
"evidence": [
"Sully (film)",
"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:\nSully is a 2016 American film directed by Clint Eastwood which is a biographical category of narrative fiction intended to be more serious than humorous in tone.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Sully (film)",
"Drama (film and television)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3094,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5773
|
Elementary is an American procedural drama television series that presented a contemporary update of Sir Arthur Conan Doyle's character who refers to himself as the "consulting detective" in the stories.
|
{
"evidence": [
"Elementary (TV series)",
"Sherlock Holmes"
],
"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:\nElementary is an American procedural drama television series that presented a contemporary update of Sir Arthur Conan Doyle's character who refers to himself as the \"consulting detective\" in the stories.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Elementary (TV series)",
"Sherlock Holmes"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3095,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
72658
|
Double Bedroom Housing scheme (a.k.a. 2BHK) is a housing project created by the Government of Telangana that follows a certain standard of measurements.
|
{
"evidence": [
"Double Bedroom Housing scheme_sentence_0",
"Double Bedroom Housing scheme_sentence_13",
"Double Bedroom Housing scheme_sentence_14",
"Double Bedroom Housing scheme_sentence_15",
"Double Bedroom Housing scheme_sentence_16"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nDouble Bedroom Housing scheme (a.k.a. 2BHK) is a housing project created by the Government of Telangana that follows a certain standard of measurements.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Double Bedroom Housing scheme_sentence_0",
"Double Bedroom Housing scheme_sentence_13",
"Double Bedroom Housing scheme_sentence_14",
"Double Bedroom Housing scheme_sentence_15",
"Double Bedroom Housing scheme_sentence_16"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3096,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.91",
"value": "?search="
},
{
"operation": "search",
"time": "14.03",
"value": "Double Bedroom Housing scheme"
},
{
"operation": "Now on",
"time": "14.943",
"value": "Double Bedroom Housing scheme"
},
{
"operation": "Highlighting",
"time": "17.25",
"value": "Double Bedroom Housing scheme_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "18.312",
"value": "Double Bedroom Housing scheme_sentence_0"
},
{
"operation": "Highlighting",
"time": "20.337",
"value": "Double Bedroom Housing scheme_sentence_0"
},
{
"operation": "Highlighting",
"time": "74.984",
"value": "Double Bedroom Housing scheme_sentence_13"
},
{
"operation": "Highlighting",
"time": "76.36",
"value": "Double Bedroom Housing scheme_sentence_14"
},
{
"operation": "Highlighting",
"time": "80.742",
"value": "Double Bedroom Housing scheme_sentence_15"
},
{
"operation": "Highlighting",
"time": "85.22",
"value": "Double Bedroom Housing scheme_sentence_16"
},
{
"operation": "finish",
"time": "99.388",
"value": "finish"
}
]
}
|
10282
|
In 1959, former Chilean boxer Alfredo Cornejo Cuevas (born June 6, 1933) won the gold medal in the welterweight division at the Pan American Games (held in Chicago, United States, from August 27 to September 7) in Chicago, United States, and the world amateur welterweight title in Mexico City.
|
{
"evidence": [
"Alfredo Cornejo_sentence_2",
"Boxing at the 1959 Pan American Games_sentence_0",
"Alfredo Cornejo_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:\nIn 1959, former Chilean boxer Alfredo Cornejo Cuevas (born June 6, 1933) won the gold medal in the welterweight division at the Pan American Games (held in Chicago, United States, from August 27 to September 7) in Chicago, United States, and the world amateur welterweight title in Mexico City.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Alfredo Cornejo_sentence_2",
"Boxing at the 1959 Pan American Games_sentence_0",
"Alfredo Cornejo_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3097,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.484",
"value": "?search="
},
{
"operation": "search",
"time": "160.173",
"value": "Chilean boxer Alfredo Cornejo Cuevas"
},
{
"operation": "Now on",
"time": "161.225",
"value": "undefined"
},
{
"operation": "search",
"time": "174.972",
"value": "welterweight division at the Pan American Games"
},
{
"operation": "Now on",
"time": "176.427",
"value": "undefined"
},
{
"operation": "search",
"time": "188.812",
"value": "Pan American Games"
},
{
"operation": "Now on",
"time": "189.882",
"value": "Pan American Games"
},
{
"operation": "search",
"time": "217.371",
"value": "Alfredo Cornejo Cuevas"
},
{
"operation": "Now on",
"time": "217.995",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "223.065",
"value": "Alfredo Cornejo"
},
{
"operation": "Now on",
"time": "223.57",
"value": "Alfredo Cornejo"
},
{
"operation": "Highlighting",
"time": "233.845",
"value": "Alfredo Cornejo_sentence_2"
},
{
"operation": "hyperlink",
"time": "268.258",
"value": "1959 Pan American Games"
},
{
"operation": "Now on",
"time": "269.071",
"value": "Boxing at the 1959 Pan American Games"
},
{
"operation": "Highlighting",
"time": "273.214",
"value": "Boxing at the 1959 Pan American Games_sentence_0"
},
{
"operation": "back-button-clicked",
"time": "277.191",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "277.241",
"value": "Alfredo Cornejo"
},
{
"operation": "Highlighting",
"time": "278.935",
"value": "Alfredo Cornejo_sentence_3"
},
{
"operation": "finish",
"time": "289.221",
"value": "finish"
}
]
}
|
exfever_7021
|
Roddick was the youngest champion at the 2003 US Open.
|
{
"evidence": [
"Andy Roddick",
"2003 US Open – Men's Singles",
"David Nalbandian"
],
"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:\nRoddick was the youngest champion at the 2003 US Open.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Andy Roddick",
"2003 US Open – Men's Singles",
"David Nalbandian"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3098,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1645
|
Honest is the second studio album by American rapper Future that features guest appearances from a Canadian rapper who gained recognition by starring as Jimmy Brooks in the CTV teen drama series Degrassi.
|
{
"evidence": [
"Honest (Future album)",
"Drake (musician)"
],
"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:\nHonest is the second studio album by American rapper Future that features guest appearances from a Canadian rapper who gained recognition by starring as Jimmy Brooks in the CTV teen drama series Degrassi.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Honest (Future album)",
"Drake (musician)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3099,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5294
|
In Dubious Battle is a 2016 American drama film starring an American actor and filmmaker whose career spans more than nine decades.
|
{
"evidence": [
"In Dubious Battle (film)",
"Robert Duvall"
],
"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:\nIn Dubious Battle is a 2016 American drama film starring an American actor and filmmaker whose career spans more than nine decades.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"In Dubious Battle (film)",
"Robert Duvall"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3100,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
2620
|
Francesca Neri is an actress that has been in many films.
|
{
"evidence": [
"Francesca Neri_sentence_0",
"Francesca Neri_sentence_2",
"Francesca Neri_sentence_3",
"Francesca Neri_sentence_4",
"Francesca Neri_sentence_5",
"Francesca Neri_sentence_6",
"Francesca Neri_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:\nFrancesca Neri is an actress that has been in many films.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Francesca Neri_sentence_0",
"Francesca Neri_sentence_2",
"Francesca Neri_sentence_3",
"Francesca Neri_sentence_4",
"Francesca Neri_sentence_5",
"Francesca Neri_sentence_6",
"Francesca Neri_sentence_7"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3101,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "33.224",
"value": "Francesca Neri"
},
{
"operation": "Highlighting",
"time": "45.084",
"value": "Francesca Neri_sentence_0"
},
{
"operation": "Highlighting",
"time": "69.727",
"value": "Francesca Neri_sentence_2"
},
{
"operation": "Highlighting",
"time": "71.73",
"value": "Francesca Neri_sentence_3"
},
{
"operation": "Highlighting",
"time": "73.46",
"value": "Francesca Neri_sentence_4"
},
{
"operation": "Highlighting",
"time": "74.727",
"value": "Francesca Neri_sentence_5"
},
{
"operation": "Highlighting",
"time": "79.568",
"value": "Francesca Neri_sentence_6"
},
{
"operation": "Highlighting",
"time": "84.708",
"value": "Francesca Neri_sentence_7"
},
{
"operation": "finish",
"time": "97.124",
"value": "finish"
}
]
}
|
93465
|
The song immediately fell to number 97 on the U.S. Billboard Hot Dance Club Play on the second day of its album release.
|
{
"evidence": [
"Dance Club Songs_sentence_2",
"Dance Club Songs_sentence_10"
],
"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 song immediately fell to number 97 on the U.S. Billboard Hot Dance Club Play on the second day of its album release.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Dance Club Songs_sentence_2",
"Dance Club Songs_sentence_10"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3102,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.434",
"value": "?search="
},
{
"operation": "search",
"time": "72.658",
"value": "Billboard Hot Dance Club Play"
},
{
"operation": "Now on",
"time": "74.268",
"value": "Dance Club Songs"
},
{
"operation": "hyperlink",
"time": "161.904",
"value": "Love Hangover 2020"
},
{
"operation": "Now on",
"time": "162.565",
"value": "Love Hangover 2020"
},
{
"operation": "back-button-clicked",
"time": "187.727",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "189.473",
"value": "Dance Club Songs"
},
{
"operation": "Highlighting",
"time": "201.178",
"value": "Dance Club Songs_sentence_2"
},
{
"operation": "Highlighting",
"time": "205.739",
"value": "Dance Club Songs_sentence_10"
},
{
"operation": "finish",
"time": "227.678",
"value": "finish"
}
]
}
|
13843
|
Kilians toured Germany in 2006 and played several big gigs, they changed their name when they released their first merch.
|
{
"evidence": [
"Kilians_sentence_9",
"Kilians_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:\nKilians toured Germany in 2006 and played several big gigs, they changed their name when they released their first merch.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Kilians_sentence_9",
"Kilians_sentence_10"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3103,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.602",
"value": "undefined"
},
{
"operation": "search",
"time": "12.083",
"value": "Kilians"
},
{
"operation": "Now on",
"time": "13.853",
"value": "Kilians"
},
{
"operation": "Highlighting",
"time": "26.987",
"value": "Kilians_sentence_11"
},
{
"operation": "Highlighting",
"time": "36.558",
"value": "Kilians_sentence_9"
},
{
"operation": "Highlighting",
"time": "40.876",
"value": "Kilians_sentence_10"
},
{
"operation": "Highlighting deleted",
"time": "45.682",
"value": "Kilians_sentence_11"
},
{
"operation": "finish",
"time": "63.556",
"value": "finish"
}
]
}
|
23091
|
The Bay Super V had 17 different versions but only 15 of them ever flew.
|
{
"evidence": [
"Bay Super V_sentence_0",
"Bay Super V_sentence_1",
"Bay Super V_sentence_36"
],
"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 Bay Super V had 17 different versions but only 15 of them ever flew.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Bay Super V_sentence_0",
"Bay Super V_sentence_1",
"Bay Super V_sentence_36"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3104,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.291",
"value": "?search="
},
{
"operation": "search",
"time": "14.812",
"value": "Bay Super V"
},
{
"operation": "Now on",
"time": "16.377",
"value": "Bay Super V"
},
{
"operation": "Highlighting",
"time": "26.732",
"value": "Bay Super V_sentence_0"
},
{
"operation": "Highlighting",
"time": "93.563",
"value": "Bay Super V_sentence_1"
},
{
"operation": "Highlighting",
"time": "187.809",
"value": "Bay Super V_sentence_36"
},
{
"operation": "finish",
"time": "223.825",
"value": "finish"
}
]
}
|
82548
|
Bombay to Bangkok, a 2008 Comedy, is about a chef who steals money escapes with doctors leaving the country.
|
{
"evidence": [
"Bombay to Bangkok_sentence_0",
"Bombay to Bangkok_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:\nBombay to Bangkok, a 2008 Comedy, is about a chef who steals money escapes with doctors leaving the country.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Bombay to Bangkok_sentence_0",
"Bombay to Bangkok_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3105,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.998",
"value": "?search="
},
{
"operation": "search",
"time": "9.756",
"value": "Bombay to Bangkok"
},
{
"operation": "Now on",
"time": "10.6",
"value": "Bombay to Bangkok"
},
{
"operation": "Highlighting",
"time": "21.723",
"value": "Bombay to Bangkok_sentence_0"
},
{
"operation": "Highlighting",
"time": "26.152",
"value": "Bombay to Bangkok_sentence_2"
},
{
"operation": "finish",
"time": "112.691",
"value": "finish"
}
]
}
|
37458
|
All solid waste policy around the world is aimed at developing and implementing proper mechanisms to effectively manage solid waste, which, generally, refers to non-hazardous waste and does not include solid or dissolved materials in domestic sewage, solid or dissolved materials in irrigation return flows, or industrial discharges.
|
{
"evidence": [
"Solid waste policy in the United States_sentence_0",
"Solid waste policy in the United States_sentence_9",
"Solid waste policy in the United States_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:\nAll solid waste policy around the world is aimed at developing and implementing proper mechanisms to effectively manage solid waste, which, generally, refers to non-hazardous waste and does not include solid or dissolved materials in domestic sewage, solid or dissolved materials in irrigation return flows, or industrial discharges.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Solid waste policy in the United States_sentence_0",
"Solid waste policy in the United States_sentence_9",
"Solid waste policy in the United States_sentence_7"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3106,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.169",
"value": "?search="
},
{
"operation": "search",
"time": "25.542",
"value": "olid waste policy around the world is aimed at developing and implementing proper mechanisms to effectively manage solid waste"
},
{
"operation": "Now on",
"time": "27.464",
"value": "undefined"
},
{
"operation": "search",
"time": "41.433",
"value": "solid waste policy around the world is aimed at developing and implementing proper mechanisms to effectively manage solid waste"
},
{
"operation": "Now on",
"time": "42.924",
"value": "undefined"
},
{
"operation": "search",
"time": "86.768",
"value": "solid waste"
},
{
"operation": "Now on",
"time": "87.981",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "101.226",
"value": "List of solid waste treatment technologies"
},
{
"operation": "Now on",
"time": "101.923",
"value": "List of solid waste treatment technologies"
},
{
"operation": "search",
"time": "138.534",
"value": "refers to non-hazardous waste and does not include solid or dissolved materials"
},
{
"operation": "Now on",
"time": "141.348",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "166.815",
"value": "Solid waste policy in the United States"
},
{
"operation": "Now on",
"time": "168.118",
"value": "Solid waste policy in the United States"
},
{
"operation": "Highlighting",
"time": "177.725",
"value": "Solid waste policy in the United States_sentence_0"
},
{
"operation": "Page search",
"time": "201.82",
"value": "hazar"
},
{
"operation": "Highlighting",
"time": "216.746",
"value": "Solid waste policy in the United States_sentence_9"
},
{
"operation": "Page search",
"time": "249.532",
"value": "disso"
},
{
"operation": "Highlighting",
"time": "256.115",
"value": "Solid waste policy in the United States_sentence_7"
},
{
"operation": "Page search",
"time": "292.17",
"value": "world"
},
{
"operation": "search",
"time": "323.43",
"value": "\"solid\" \"waste\" \"policy\" \"world\""
},
{
"operation": "Now on",
"time": "324.341",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "367.912",
"value": "Environmental law"
},
{
"operation": "Now on",
"time": "369.569",
"value": "Environmental law"
},
{
"operation": "Page search",
"time": "375.582",
"value": "world"
},
{
"operation": "hyperlink",
"time": "533.059",
"value": "List of international environmental agreements"
},
{
"operation": "Now on",
"time": "534.621",
"value": "List of international environmental agreements"
},
{
"operation": "search",
"time": "566.613",
"value": "solid waste policy around the world"
},
{
"operation": "Now on",
"time": "568.946",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "587.635",
"value": "Around the world Environmental law_section_24"
},
{
"operation": "Now on",
"time": "588.346",
"value": "Environmental law#Around the world Environmental law section 24"
},
{
"operation": "back-button-clicked",
"time": "610.059",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "610.959",
"value": "undefined"
},
{
"operation": "finish",
"time": "700.519",
"value": "finish"
}
]
}
|
exfever_5078
|
Evans also starred in several fringe shows in London and the Edinburgh Festival.
|
{
"evidence": [
"Luke Evans (actor)",
"Miss Saigon"
],
"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:\nEvans also starred in several fringe shows in London and the Edinburgh Festival.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Luke Evans (actor)",
"Miss Saigon"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3107,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8696
|
Bonnie Lynn Hunt is an American actress that has a film role in an American family film directed by Rod Daniel also starring a Canadian actress known for playing sharp-tongued women.
|
{
"evidence": [
"Bonnie Hunt",
"Beethoven's 2nd (film)",
"Debi Mazar"
],
"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:\nBonnie Lynn Hunt is an American actress that has a film role in an American family film directed by Rod Daniel also starring a Canadian actress known for playing sharp-tongued women.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Bonnie Hunt",
"Beethoven's 2nd (film)",
"Debi Mazar"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3108,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3454
|
Vacation is a 2015 American road comedy film that stars a Canadian actor who starred as Stuart Price in The Hangover trilogy.
|
{
"evidence": [
"Vacation (2015 film)",
"Ed Helms"
],
"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:\nVacation is a 2015 American road comedy film that stars a Canadian actor who starred as Stuart Price in The Hangover trilogy.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Vacation (2015 film)",
"Ed Helms"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3109,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
11900
|
Rick Peckham provided play-by-play commentary for NHL games on SportsChannel America over three years, but he was never placed beside Dave Maloney during broadcast.
|
{
"evidence": [
"Dave Maloney_sentence_7"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nRick Peckham provided play-by-play commentary for NHL games on SportsChannel America over three years, but he was never placed beside Dave Maloney during broadcast.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Dave Maloney_sentence_7"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3110,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.626",
"value": "?search="
},
{
"operation": "search",
"time": "10.346",
"value": "Rick Peckham"
},
{
"operation": "Now on",
"time": "11.377",
"value": "Rick Peckham"
},
{
"operation": "Highlighting",
"time": "21.286",
"value": "Rick Peckham_sentence_0"
},
{
"operation": "Highlighting",
"time": "21.286",
"value": "Rick Peckham_title"
},
{
"operation": "Highlighting deleted",
"time": "32.249",
"value": "Rick Peckham_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "32.251",
"value": "Rick Peckham_title"
},
{
"operation": "Highlighting",
"time": "33.949",
"value": "Rick Peckham_sentence_2"
},
{
"operation": "Highlighting",
"time": "33.95",
"value": "Rick Peckham_title"
},
{
"operation": "Highlighting",
"time": "77.832",
"value": "Rick Peckham_sentence_0"
},
{
"operation": "search",
"time": "96.292",
"value": "dave maloney"
},
{
"operation": "Now on",
"time": "97.407",
"value": "Dave Maloney"
},
{
"operation": "Page search",
"time": "107.077",
"value": "peckham"
},
{
"operation": "hyperlink",
"time": "120.804",
"value": "Rick Peckham"
},
{
"operation": "Now on",
"time": "121.283",
"value": "Rick Peckham"
},
{
"operation": "back-button-clicked",
"time": "131.182",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "131.299",
"value": "Dave Maloney"
},
{
"operation": "Highlighting",
"time": "133.378",
"value": "Dave Maloney_sentence_7"
},
{
"operation": "finish",
"time": "150.228",
"value": "finish"
}
]
}
|
exfever_8257
|
Alice is a 1990 American fantasy romantic comedy film starring an American actor who played a leading role in the neo-noir Body Heat with an American actress known for her distinctive voice.
|
{
"evidence": [
"Alice (1990 film)",
"William Hurt",
"Kathleen Turner"
],
"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:\nAlice is a 1990 American fantasy romantic comedy film starring an American actor who played a leading role in the neo-noir Body Heat with an American actress known for her distinctive voice.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Alice (1990 film)",
"William Hurt",
"Kathleen Turner"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3111,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
19054
|
John Boyd Bentley was an ordained deacon in 1922 and would later become an ordained priest in 1929.
|
{
"evidence": [
"John Boyd Bentley_sentence_6",
"John Boyd Bentley_sentence_9"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJohn Boyd Bentley was an ordained deacon in 1922 and would later become an ordained priest in 1929.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"John Boyd Bentley_sentence_6",
"John Boyd Bentley_sentence_9"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3112,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.186",
"value": "?search="
},
{
"operation": "search",
"time": "11.948",
"value": "John Boyd Bentley"
},
{
"operation": "Now on",
"time": "12.908",
"value": "John Boyd Bentley"
},
{
"operation": "Highlighting",
"time": "100.015",
"value": "John Boyd Bentley_sentence_6"
},
{
"operation": "Highlighting",
"time": "103.397",
"value": "John Boyd Bentley_sentence_9"
},
{
"operation": "finish",
"time": "110.219",
"value": "finish"
}
]
}
|
37980
|
During the 2009 CD Universidad San Martin season, Luis Álvarez and Pedro Gallese both transferred to Atlético Minero.
|
{
"evidence": [
"Pedro Gallese_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:\nDuring the 2009 CD Universidad San Martin season, Luis Álvarez and Pedro Gallese both transferred to Atlético Minero.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Pedro Gallese_sentence_5"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3113,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.797",
"value": "?search="
},
{
"operation": "search",
"time": "17.302",
"value": "2009 CD Universidad San Martín season"
},
{
"operation": "Now on",
"time": "19.051",
"value": "2009 CD Universidad San Martín season"
},
{
"operation": "Page search",
"time": "28.978",
"value": "alvarez"
},
{
"operation": "Page search",
"time": "52.07",
"value": "atletico"
},
{
"operation": "Page search",
"time": "67.333",
"value": "atletico"
},
{
"operation": "Page search",
"time": "128.95",
"value": "pedro"
},
{
"operation": "Highlighting",
"time": "148.593",
"value": "2009 CD Universidad San Martín season_cell_1_35_2"
},
{
"operation": "Highlighting",
"time": "148.594",
"value": "2009 CD Universidad San Martín season_title"
},
{
"operation": "Highlighting",
"time": "148.594",
"value": "2009 CD Universidad San Martín season_section_0"
},
{
"operation": "Highlighting",
"time": "148.595",
"value": "2009 CD Universidad San Martín season_section_1"
},
{
"operation": "Highlighting",
"time": "148.608",
"value": "2009 CD Universidad San Martín season_header_cell_1_0_2"
},
{
"operation": "hyperlink",
"time": "150.92",
"value": "Pedro Gallese"
},
{
"operation": "Now on",
"time": "151.855",
"value": "Pedro Gallese"
},
{
"operation": "Page search",
"time": "160.871",
"value": "atletico"
},
{
"operation": "Highlighting",
"time": "190.109",
"value": "Pedro Gallese_sentence_5"
},
{
"operation": "back-button-clicked",
"time": "198.692",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "199.041",
"value": "2009 CD Universidad San Martín season"
},
{
"operation": "Highlighting",
"time": "208.15",
"value": "2009 CD Universidad San Martín season_cell_1_33_2"
},
{
"operation": "Highlighting",
"time": "208.151",
"value": "2009 CD Universidad San Martín season_title"
},
{
"operation": "Highlighting",
"time": "208.151",
"value": "2009 CD Universidad San Martín season_section_0"
},
{
"operation": "Highlighting",
"time": "208.152",
"value": "2009 CD Universidad San Martín season_section_1"
},
{
"operation": "Highlighting",
"time": "208.162",
"value": "2009 CD Universidad San Martín season_header_cell_1_0_2"
},
{
"operation": "hyperlink",
"time": "212.914",
"value": "Peru"
},
{
"operation": "Now on",
"time": "214.591",
"value": "Peru"
},
{
"operation": "back-button-clicked",
"time": "218.297",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "218.666",
"value": "2009 CD Universidad San Martín season"
},
{
"operation": "search",
"time": "230.805",
"value": "luiz alvarez"
},
{
"operation": "Now on",
"time": "232.17",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "258.299",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "258.665",
"value": "2009 CD Universidad San Martín season"
},
{
"operation": "search",
"time": "277.437",
"value": "Atlético Minero"
},
{
"operation": "Now on",
"time": "278.104",
"value": "Atlético Minero"
},
{
"operation": "search",
"time": "297.648",
"value": "2009 atletico minero"
},
{
"operation": "Now on",
"time": "298.607",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "307.267",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "307.441",
"value": "Atlético Minero"
},
{
"operation": "search",
"time": "340.2",
"value": "atletico minero 2009 season"
},
{
"operation": "Now on",
"time": "341.347",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "373.169",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "373.363",
"value": "Atlético Minero"
},
{
"operation": "Highlighting",
"time": "390.943",
"value": "Atlético Minero_sentence_16"
},
{
"operation": "Highlighting",
"time": "390.944",
"value": "Atlético Minero_title"
},
{
"operation": "Highlighting",
"time": "390.945",
"value": "Atlético Minero_section_2"
},
{
"operation": "Highlighting deleted",
"time": "394.317",
"value": "Atlético Minero_sentence_16"
},
{
"operation": "Highlighting deleted",
"time": "394.319",
"value": "Atlético Minero_title"
},
{
"operation": "Highlighting deleted",
"time": "394.32",
"value": "Atlético Minero_section_2"
},
{
"operation": "search",
"time": "400.574",
"value": "Atlético Minero footballer"
},
{
"operation": "Now on",
"time": "401.487",
"value": "undefined"
},
{
"operation": "finish",
"time": "483.608",
"value": "finish"
}
]
}
|
36332
|
The rear cover of the album shows "Portrait U.S.A.", a satellite image of the United States produced by their Beltsville Photo Engineering Lab with the assistance of the National Geographic Society and NASA, and created in 1976 by the General Electric Co.
|
{
"evidence": [
"More Songs About Buildings and Food_sentence_5",
"More Songs About Buildings and Food_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 rear cover of the album shows \"Portrait U.S.A.\", a satellite image of the United States produced by their Beltsville Photo Engineering Lab with the assistance of the National Geographic Society and NASA, and created in 1976 by the General Electric Co.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"More Songs About Buildings and Food_sentence_5",
"More Songs About Buildings and Food_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3114,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.475",
"value": "undefined"
},
{
"operation": "search",
"time": "55.375",
"value": "The rear cover of the album shows \"Portrait U.S.A.\","
},
{
"operation": "Now on",
"time": "56.681",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "60.533",
"value": "The Girls Want to Be With the Girls"
},
{
"operation": "Now on",
"time": "61.388",
"value": "The Girls Want to Be With the Girls"
},
{
"operation": "Page search",
"time": "65.754",
"value": "Portrait"
},
{
"operation": "Highlighting",
"time": "69.991",
"value": "More Songs About Buildings and Food_sentence_5"
},
{
"operation": "Highlighting",
"time": "86.772",
"value": "More Songs About Buildings and Food_sentence_6"
},
{
"operation": "finish",
"time": "132.139",
"value": "finish"
}
]
}
|
49415
|
The 1964 Tower Hamlets London Borough Council election was the first to the newly formed borough, where 115 candidates stood in the election for 60 seats being contested.
|
{
"evidence": [
"1964 Tower Hamlets London Borough Council election_sentence_2",
"1964 Tower Hamlets London Borough Council election_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:\nThe 1964 Tower Hamlets London Borough Council election was the first to the newly formed borough, where 115 candidates stood in the election for 60 seats being contested.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"1964 Tower Hamlets London Borough Council election_sentence_2",
"1964 Tower Hamlets London Borough Council election_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3115,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.662",
"value": "?search="
},
{
"operation": "search",
"time": "15.707",
"value": "1964 Tower Hamlets London Borough Council election"
},
{
"operation": "Now on",
"time": "18.893",
"value": "1964 Tower Hamlets London Borough Council election"
},
{
"operation": "Highlighting",
"time": "27.821",
"value": "1964 Tower Hamlets London Borough Council election_sentence_2"
},
{
"operation": "Highlighting",
"time": "36.784",
"value": "1964 Tower Hamlets London Borough Council election_sentence_5"
},
{
"operation": "finish",
"time": "57.177",
"value": "finish"
}
]
}
|
54513
|
Dartmouth House is located at 37 Charles Street (first owned by Henry Herbert, 2nd Earl of Carnarvon from 1757-1776), and is used by more than 40,000 people every year.
|
{
"evidence": [
"Dartmouth House_sentence_2",
"Dartmouth House_sentence_5",
"Dartmouth House_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:\nDartmouth House is located at 37 Charles Street (first owned by Henry Herbert, 2nd Earl of Carnarvon from 1757-1776), and is used by more than 40,000 people every year.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Dartmouth House_sentence_2",
"Dartmouth House_sentence_5",
"Dartmouth House_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3116,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.352",
"value": "?search="
},
{
"operation": "search",
"time": "9.846",
"value": "Dartmouth House"
},
{
"operation": "Now on",
"time": "10.388",
"value": "Dartmouth House"
},
{
"operation": "Highlighting",
"time": "21.101",
"value": "Dartmouth House_sentence_2"
},
{
"operation": "Highlighting",
"time": "46.38",
"value": "Dartmouth House_sentence_5"
},
{
"operation": "Highlighting",
"time": "56.629",
"value": "Dartmouth House_sentence_3"
},
{
"operation": "Now on",
"time": "85.879",
"value": "Dartmouth House"
},
{
"operation": "finish",
"time": "109.693",
"value": "finish"
}
]
}
|
exfever_5809
|
Gorgeous Ladies of Wrestling is organized by wrestling federations called promotions that began in 1986 and have continued in various forms after it left television.
|
{
"evidence": [
"Gorgeous Ladies of Wrestling",
"Women's professional wrestling"
],
"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:\nGorgeous Ladies of Wrestling is organized by wrestling federations called promotions that began in 1986 and have continued in various forms after it left television.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Gorgeous Ladies of Wrestling",
"Women's professional wrestling"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3117,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3755
|
Chadwick Aaron Boseman was the first American actor to win a Golden Globe Award for Best Actor.
|
{
"evidence": [
"Chadwick Boseman",
"42 (film)",
"Sports 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:\nChadwick Aaron Boseman was the first American actor to win a Golden Globe Award for Best Actor.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Chadwick Boseman",
"42 (film)",
"Sports film"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3118,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6197
|
Amanda Leigh Moore is an Australian singer, songwriter, and actress whose self-titled second studio album was released on June 19, 2001, by an American record label owned by Sony Music Entertainment.
|
{
"evidence": [
"Mandy Moore",
"Mandy Moore (album)",
"Epic Records"
],
"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:\nAmanda Leigh Moore is an Australian singer, songwriter, and actress whose self-titled second studio album was released on June 19, 2001, by an American record label owned by Sony Music Entertainment.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Mandy Moore",
"Mandy Moore (album)",
"Epic Records"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3119,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
67904
|
Central Europe is home to churches known for their architecture, stonework, and historical significance.
|
{
"evidence": [
"Central Europe_sentence_192",
"List of central European countries by development indexes_sentence_21",
"List of central European countries by development indexes_sentence_22"
],
"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:\nCentral Europe is home to churches known for their architecture, stonework, and historical significance.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Central Europe_sentence_192",
"List of central European countries by development indexes_sentence_21",
"List of central European countries by development indexes_sentence_22"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3120,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.793",
"value": "?search="
},
{
"operation": "search",
"time": "11.018",
"value": "Central Europe"
},
{
"operation": "Now on",
"time": "12.764",
"value": "Central Europe"
},
{
"operation": "search",
"time": "49.985",
"value": "home to churches known for their architecture, stonework, and historical significance"
},
{
"operation": "Now on",
"time": "54.173",
"value": "undefined"
},
{
"operation": "search",
"time": "78.764",
"value": "Central Europe churches"
},
{
"operation": "Now on",
"time": "80.585",
"value": "undefined"
},
{
"operation": "search",
"time": "96.333",
"value": "Central Europe"
},
{
"operation": "Now on",
"time": "96.984",
"value": "Central Europe"
},
{
"operation": "hyperlink",
"time": "141.447",
"value": "8.1 Architecture Central Europe_section_39"
},
{
"operation": "hyperlink",
"time": "166.671",
"value": "List of central European countries by development indexes § Architecture"
},
{
"operation": "Now on",
"time": "167.728",
"value": "List of central European countries by development indexes#Architecture"
},
{
"operation": "search",
"time": "200.192",
"value": "central Europe"
},
{
"operation": "Now on",
"time": "200.815",
"value": "Central Europe"
},
{
"operation": "search",
"time": "238.124",
"value": "architecture, stonework, and historical significance"
},
{
"operation": "Now on",
"time": "239.244",
"value": "undefined"
},
{
"operation": "search",
"time": "255.263",
"value": "Churches Central Europe"
},
{
"operation": "Now on",
"time": "256.399",
"value": "undefined"
},
{
"operation": "search",
"time": "281.074",
"value": "Central Europe"
},
{
"operation": "Now on",
"time": "282.03",
"value": "Central Europe"
},
{
"operation": "Highlighting",
"time": "299.236",
"value": "Central Europe_sentence_192"
},
{
"operation": "hyperlink",
"time": "300.952",
"value": "List of central European countries by development indexes § Architecture"
},
{
"operation": "Now on",
"time": "301.393",
"value": "List of central European countries by development indexes#Architecture"
},
{
"operation": "Highlighting",
"time": "309.064",
"value": "List of central European countries by development indexes_sentence_21"
},
{
"operation": "Highlighting",
"time": "310.889",
"value": "List of central European countries by development indexes_sentence_22"
},
{
"operation": "finish",
"time": "323.958",
"value": "finish"
}
]
}
|
27654
|
Glaros started her career in Parkersburg, West Virginia; then moved to South Florida in September 2004 and became the Local 10 morning news meteorologist and host of SportsJam Live.
|
{
"evidence": [
"Megan Glaros_sentence_8",
"Megan Glaros_sentence_10"
],
"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:\nGlaros started her career in Parkersburg, West Virginia; then moved to South Florida in September 2004 and became the Local 10 morning news meteorologist and host of SportsJam Live.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Megan Glaros_sentence_8",
"Megan Glaros_sentence_10"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3121,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.188",
"value": "?search="
},
{
"operation": "search",
"time": "50.623",
"value": "megan glaros"
},
{
"operation": "Now on",
"time": "52.216",
"value": "Megan Glaros"
},
{
"operation": "Highlighting",
"time": "133.907",
"value": "Megan Glaros_sentence_8"
},
{
"operation": "Highlighting",
"time": "142.298",
"value": "Megan Glaros_sentence_10"
},
{
"operation": "Highlighting",
"time": "518.293",
"value": "Megan Glaros_sentence_11"
},
{
"operation": "Highlighting deleted",
"time": "518.865",
"value": "Megan Glaros_sentence_11"
},
{
"operation": "finish",
"time": "526.496",
"value": "finish"
}
]
}
|
18975
|
Before becoming president of the Liberal Party and serving in the Skien city council, Jennie Johnsen first served the Young Liberals of Norway.
|
{
"evidence": [
"Jennie Johnsen_sentence_3",
"Jennie Johnsen_sentence_1"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nBefore becoming president of the Liberal Party and serving in the Skien city council, Jennie Johnsen first served the Young Liberals of Norway.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Jennie Johnsen_sentence_3",
"Jennie Johnsen_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3122,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.219",
"value": "?search="
},
{
"operation": "search",
"time": "20.102",
"value": "Contains...Young Liberals of Norway"
},
{
"operation": "Now on",
"time": "21.183",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "33.164",
"value": "Olav Gullvåg"
},
{
"operation": "Now on",
"time": "34.01",
"value": "Olav Gullvåg"
},
{
"operation": "search",
"time": "47.655",
"value": "Jennie Johnsen"
},
{
"operation": "Now on",
"time": "48.497",
"value": "Jennie Johnsen"
},
{
"operation": "Highlighting",
"time": "59.727",
"value": "Jennie Johnsen_sentence_1"
},
{
"operation": "hyperlink",
"time": "107.166",
"value": "Liberal Party"
},
{
"operation": "Now on",
"time": "108.373",
"value": "Liberal Party (Norway)"
},
{
"operation": "hyperlink",
"time": "143.071",
"value": "4 Party leaders Liberal Party (Norway)_section_3"
},
{
"operation": "hyperlink",
"time": "197.992",
"value": "Lars Sponheim"
},
{
"operation": "Now on",
"time": "198.738",
"value": "Lars Sponheim"
},
{
"operation": "Highlighting",
"time": "205.08",
"value": "Lars Sponheim_sentence_1"
},
{
"operation": "Highlighting",
"time": "205.081",
"value": "Lars Sponheim_title"
},
{
"operation": "Highlighting deleted",
"time": "223.392",
"value": "Lars Sponheim_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "223.396",
"value": "Lars Sponheim_title"
},
{
"operation": "Highlighting",
"time": "227.833",
"value": "Lars Sponheim_sentence_1"
},
{
"operation": "Highlighting",
"time": "227.834",
"value": "Lars Sponheim_title"
},
{
"operation": "search",
"time": "274.639",
"value": "Jennie Johnsen"
},
{
"operation": "Now on",
"time": "275.559",
"value": "Jennie Johnsen"
},
{
"operation": "Highlighting",
"time": "317.332",
"value": "Jennie Johnsen_sentence_3"
},
{
"operation": "Highlighting",
"time": "346.173",
"value": "Jennie Johnsen_sentence_3"
},
{
"operation": "Highlighting",
"time": "368.325",
"value": "Jennie Johnsen_sentence_1"
},
{
"operation": "finish",
"time": "382.982",
"value": "finish"
}
]
}
|
exfever_382
|
James Arness was an American actor, best known for portraying Marshal Matt Dillon for 20 years in the CBS television American radio and television Western drama series created by director Norman Macdonnell.
|
{
"evidence": [
"James Arness",
"Gunsmoke"
],
"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:\nJames Arness was an American actor, best known for portraying Marshal Matt Dillon for 20 years in the CBS television American radio and television Western drama series created by director Norman Macdonnell.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"James Arness",
"Gunsmoke"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3123,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
26995
|
Jo Eleanor Elliott (5 October 1923 – 1 May 2011) was a nurse and head of the American Nurses Association who received the Living Legend Award from the American Nurses Association.
|
{
"evidence": [
"Jo Eleanor Elliott_sentence_0",
"Jo Eleanor Elliott_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:\nJo Eleanor Elliott (5 October 1923 – 1 May 2011) was a nurse and head of the American Nurses Association who received the Living Legend Award from the American Nurses Association.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jo Eleanor Elliott_sentence_0",
"Jo Eleanor Elliott_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3124,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.009",
"value": "?search="
},
{
"operation": "search",
"time": "12.218",
"value": "Jo Eleanor Elliott"
},
{
"operation": "Now on",
"time": "12.912",
"value": "Jo Eleanor Elliott"
},
{
"operation": "Highlighting",
"time": "69.583",
"value": "Jo Eleanor Elliott_sentence_0"
},
{
"operation": "Highlighting",
"time": "72.744",
"value": "Jo Eleanor Elliott_sentence_1"
},
{
"operation": "Page search",
"time": "98.078",
"value": "living legend"
},
{
"operation": "page-search-reset",
"time": "105.589",
"value": "page-search-reset"
},
{
"operation": "Highlighting",
"time": "107.154",
"value": "Jo Eleanor Elliott_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "107.363",
"value": "Jo Eleanor Elliott_sentence_2"
},
{
"operation": "finish",
"time": "187.039",
"value": "finish"
}
]
}
|
8907
|
Liam Keoghan is an Irish retired sportsperson who played hurling, an outdoor team game of ancient Gaelic Irish origin, with his local club Tullaroan.
|
{
"evidence": [
"Liam Keoghan_sentence_0",
"Liam Keoghan_sentence_1",
"Hurling_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:\nLiam Keoghan is an Irish retired sportsperson who played hurling, an outdoor team game of ancient Gaelic Irish origin, with his local club Tullaroan.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Liam Keoghan_sentence_0",
"Liam Keoghan_sentence_1",
"Hurling_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3125,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.446",
"value": "?search="
},
{
"operation": "search",
"time": "21.798",
"value": "Liam Keoghan"
},
{
"operation": "Now on",
"time": "22.907",
"value": "Liam Keoghan"
},
{
"operation": "Highlighting",
"time": "24.907",
"value": "Liam Keoghan_sentence_0"
},
{
"operation": "Highlighting",
"time": "27.748",
"value": "Liam Keoghan_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "30.278",
"value": "Liam Keoghan_sentence_1"
},
{
"operation": "Highlighting",
"time": "31.343",
"value": "Liam Keoghan_sentence_1"
},
{
"operation": "hyperlink",
"time": "31.961",
"value": "hurling"
},
{
"operation": "Now on",
"time": "32.711",
"value": "Hurling"
},
{
"operation": "hyperlink",
"time": "35.009",
"value": "Irish"
},
{
"operation": "Now on",
"time": "36.247",
"value": "Irish language"
},
{
"operation": "back-button-clicked",
"time": "37.636",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "37.738",
"value": "Hurling"
},
{
"operation": "Highlighting",
"time": "42.563",
"value": "Hurling_sentence_3"
},
{
"operation": "back-button-clicked",
"time": "52.833",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "52.837",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "52.9",
"value": "Liam Keoghan"
},
{
"operation": "Highlighting",
"time": "65.801",
"value": "Liam Keoghan_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "78.5",
"value": "Liam Keoghan_sentence_2"
},
{
"operation": "Highlighting",
"time": "80.343",
"value": "Liam Keoghan_header_cell_0_5_0"
},
{
"operation": "Highlighting",
"time": "82.664",
"value": "Liam Keoghan_cell_0_7_1"
},
{
"operation": "Highlighting",
"time": "82.672",
"value": "Liam Keoghan_header_cell_0_7_0"
},
{
"operation": "Highlighting",
"time": "82.674",
"value": "Liam Keoghan_header_cell_0_5_0"
},
{
"operation": "Highlighting deleted",
"time": "114.122",
"value": "Liam Keoghan_cell_0_7_1"
},
{
"operation": "Highlighting deleted",
"time": "114.13",
"value": "Liam Keoghan_header_cell_0_7_0"
},
{
"operation": "Highlighting deleted",
"time": "114.131",
"value": "Liam Keoghan_header_cell_0_5_0"
},
{
"operation": "finish",
"time": "128.775",
"value": "finish"
}
]
}
|
10444
|
Henri Eyebe Ayissi was born in Mbellé and worked at the Inspection Générale before moving to the ministry of public service.
|
{
"evidence": [
"Henri Eyebe Ayissi_sentence_2",
"Henri Eyebe Ayissi_sentence_3",
"Henri Eyebe Ayissi_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:\nHenri Eyebe Ayissi was born in Mbellé and worked at the Inspection Générale before moving to the ministry of public service.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Henri Eyebe Ayissi_sentence_2",
"Henri Eyebe Ayissi_sentence_3",
"Henri Eyebe Ayissi_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3126,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.638",
"value": "?search="
},
{
"operation": "search",
"time": "9.119",
"value": "Henri Eyebe Ayissi"
},
{
"operation": "Now on",
"time": "10.402",
"value": "Henri Eyebe Ayissi"
},
{
"operation": "Highlighting",
"time": "19.674",
"value": "Henri Eyebe Ayissi_sentence_2"
},
{
"operation": "Highlighting",
"time": "22.423",
"value": "Henri Eyebe Ayissi_sentence_3"
},
{
"operation": "Highlighting",
"time": "31.697",
"value": "Henri Eyebe Ayissi_sentence_4"
},
{
"operation": "finish",
"time": "56.474",
"value": "finish"
}
]
}
|
exfever_2611
|
Hungarians are a nation and a group native to Hungary, which is a grouping of people who identify with each other on the basis of shared attributes that distinguish them from other groups, which defined by a shared heritage of tangible and intangible heritage assets of a group.
|
{
"evidence": [
"Hungarians",
"Ethnic group",
"Cultural heritage"
],
"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:\nHungarians are a nation and a group native to Hungary, which is a grouping of people who identify with each other on the basis of shared attributes that distinguish them from other groups, which defined by a shared heritage of tangible and intangible heritage assets of a group.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Hungarians",
"Ethnic group",
"Cultural heritage"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3127,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
88550
|
The population of Schluein, a municipality in the Surselva Region in the Finnish canton of Graubünden, steadily increases as time passes; in 1850, it had 366 residents, increasing to 424 residents in 1900.
|
{
"evidence": [
"Schluein_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 population of Schluein, a municipality in the Surselva Region in the Finnish canton of Graubünden, steadily increases as time passes; in 1850, it had 366 residents, increasing to 424 residents in 1900.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Schluein_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3128,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.119",
"value": "?search="
},
{
"operation": "search",
"time": "9.947",
"value": "Schluein"
},
{
"operation": "Now on",
"time": "10.723",
"value": "Schluein"
},
{
"operation": "Highlighting",
"time": "17.568",
"value": "Schluein_sentence_0"
},
{
"operation": "finish",
"time": "97.989",
"value": "finish"
}
]
}
|
41718
|
Good Kisser was released in more than 21 countries on May 5, 2014.
|
{
"evidence": [
"Good Kisser_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:\nGood Kisser was released in more than 21 countries on May 5, 2014.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Good Kisser_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3129,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "4.622",
"value": "undefined"
},
{
"operation": "search",
"time": "38.196",
"value": "Good Kisser"
},
{
"operation": "Now on",
"time": "42.45",
"value": "Good Kisser"
},
{
"operation": "Highlighting",
"time": "51.668",
"value": "Good Kisser_sentence_2"
},
{
"operation": "hyperlink",
"time": "73.756",
"value": "Usher"
},
{
"operation": "Now on",
"time": "79.678",
"value": "Usher (musician)"
},
{
"operation": "finish",
"time": "95.417",
"value": "finish"
}
]
}
|
exfever_5766
|
The Shape of Water is a 2017 American romantic fantasy film directed by a Canadian film director best known for his Academy Award-winning fantasy films.
|
{
"evidence": [
"The Shape of Water (film)",
"Guillermo del Toro"
],
"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 Shape of Water is a 2017 American romantic fantasy film directed by a Canadian film director best known for his Academy Award-winning fantasy films.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Shape of Water (film)",
"Guillermo del Toro"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3130,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1162
|
30 Rock is an American satirical television series that originally aired on an American English-language commercial broadcast television and radio network that is owned by Comcast through NBCUniversal.
|
{
"evidence": [
"30 Rock",
"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:\n30 Rock is an American satirical television series that originally aired on an American English-language commercial broadcast television and radio network that is owned by Comcast through NBCUniversal.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"30 Rock",
"NBC"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3131,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
67708
|
10 Days in a Madhouse is a 2015 American biographical film about undercover journalist Nellie Bly who was an American journalist, industrialist, inventor, and charity worker who was widely known for her record-breaking trip around the world.
|
{
"evidence": [
"10 Days in a Madhouse_sentence_0",
"Nellie Bly_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:\n10 Days in a Madhouse is a 2015 American biographical film about undercover journalist Nellie Bly who was an American journalist, industrialist, inventor, and charity worker who was widely known for her record-breaking trip around the world.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"10 Days in a Madhouse_sentence_0",
"Nellie Bly_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3132,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.149",
"value": "?search="
},
{
"operation": "search",
"time": "342.916",
"value": "10 Days in a Madhouse"
},
{
"operation": "Now on",
"time": "346.026",
"value": "10 Days in a Madhouse"
},
{
"operation": "Highlighting",
"time": "349.944",
"value": "10 Days in a Madhouse_sentence_0"
},
{
"operation": "hyperlink",
"time": "378.644",
"value": "Nellie Bly"
},
{
"operation": "Now on",
"time": "379.627",
"value": "Nellie Bly"
},
{
"operation": "Highlighting",
"time": "390.685",
"value": "Nellie Bly_sentence_0"
},
{
"operation": "finish",
"time": "413.365",
"value": "finish"
}
]
}
|
66772
|
Pellegrino Aretusi, an Italian painter whose early instruction was from his father Giovanni Munari, died in his sleep in 1523.
|
{
"evidence": [
"Pellegrino Aretusi_sentence_5"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nPellegrino Aretusi, an Italian painter whose early instruction was from his father Giovanni Munari, died in his sleep in 1523.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Pellegrino Aretusi_sentence_5"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3133,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.324",
"value": "undefined"
},
{
"operation": "search",
"time": "172.834",
"value": "Pellegrino Aretusi"
},
{
"operation": "Now on",
"time": "177.059",
"value": "Pellegrino Aretusi"
},
{
"operation": "Page search",
"time": "190.099",
"value": "Italian"
},
{
"operation": "Highlighting",
"time": "193.343",
"value": "Pellegrino Aretusi_sentence_1"
},
{
"operation": "Highlighting",
"time": "208.527",
"value": "Pellegrino Aretusi_sentence_2"
},
{
"operation": "Highlighting",
"time": "244.995",
"value": "Pellegrino Aretusi_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "247.546",
"value": "Pellegrino Aretusi_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "248.74",
"value": "Pellegrino Aretusi_sentence_1"
},
{
"operation": "finish",
"time": "282.041",
"value": "finish"
}
]
}
|
59079
|
The area with a total population of 2,014 in the Baden District in the Aargau Canton is Turgi.
|
{
"evidence": [
"Turgi_sentence_0",
"Turgi_sentence_7"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe area with a total population of 2,014 in the Baden District in the Aargau Canton is Turgi.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Turgi_sentence_0",
"Turgi_sentence_7"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3134,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.71",
"value": "?search="
},
{
"operation": "search",
"time": "19.011",
"value": "Turgi"
},
{
"operation": "Now on",
"time": "20.658",
"value": "Turgi"
},
{
"operation": "Highlighting",
"time": "33.016",
"value": "Turgi_sentence_0"
},
{
"operation": "Highlighting",
"time": "108.241",
"value": "Turgi_sentence_7"
},
{
"operation": "finish",
"time": "163.286",
"value": "finish"
}
]
}
|
75633
|
Ivaylovgrad hydroelectric power plant (HPP) is the last stage of the Arda cascade but the initial plans for the construction of a dam on the Arda date to as early as 1948.
|
{
"evidence": [
"Ivaylovgrad Dam_sentence_7",
"Ivaylovgrad Dam_sentence_8"
],
"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:\nIvaylovgrad hydroelectric power plant (HPP) is the last stage of the Arda cascade but the initial plans for the construction of a dam on the Arda date to as early as 1948.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Ivaylovgrad Dam_sentence_7",
"Ivaylovgrad Dam_sentence_8"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3135,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.801",
"value": "?search="
},
{
"operation": "search",
"time": "50.9",
"value": "Contains...Arda cascade"
},
{
"operation": "Now on",
"time": "52.067",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "58.595",
"value": "Ivaylovgrad Dam"
},
{
"operation": "Now on",
"time": "59.514",
"value": "Ivaylovgrad Dam"
},
{
"operation": "Highlighting",
"time": "82.067",
"value": "Ivaylovgrad Dam_sentence_7"
},
{
"operation": "Highlighting",
"time": "90.611",
"value": "Ivaylovgrad Dam_sentence_8"
},
{
"operation": "finish",
"time": "116.437",
"value": "finish"
}
]
}
|
exfever_5656
|
Lymelife is a 2001 American comedy-drama film starring an American actor.
|
{
"evidence": [
"Lymelife",
"Rory Culkin"
],
"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:\nLymelife is a 2001 American comedy-drama film starring an American actor.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Lymelife",
"Rory Culkin"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3136,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
67094
|
Heydekrug often sought city rights, but was opposed by Memel and Tilsit in 1721 and 1725.
|
{
"evidence": [
"Šilutė_sentence_9"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nHeydekrug often sought city rights, but was opposed by Memel and Tilsit in 1721 and 1725.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Šilutė_sentence_9"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3137,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "3.038",
"value": "?search="
},
{
"operation": "search",
"time": "206.626",
"value": "Šilutė"
},
{
"operation": "Now on",
"time": "208.312",
"value": "Šilutė"
},
{
"operation": "Highlighting",
"time": "346.568",
"value": "Šilutė_sentence_9"
},
{
"operation": "finish",
"time": "374.56",
"value": "finish"
}
]
}
|
exfever_751
|
Harold Ramis directed the 1980 Italian film, which was written by an American comedy writer who co-founded the magazine National Lampoon.
|
{
"evidence": [
"Harold Ramis",
"Caddyshack",
"Douglas Kenney"
],
"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:\nHarold Ramis directed the 1980 Italian film, which was written by an American comedy writer who co-founded the magazine National Lampoon.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Harold Ramis",
"Caddyshack",
"Douglas Kenney"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3138,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4057
|
The film BASEketball is Lewis Friedman's first work as a writer.
|
{
"evidence": [
"Lewis Friedman",
"Shorewood High School (Wisconsin)"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe film BASEketball is Lewis Friedman's first work as a writer.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Lewis Friedman",
"Shorewood High School (Wisconsin)"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3139,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4089
|
Dwight D. Eisenhower was an American military officer and statesman who achieved the highest military rank of general officer in the United States.
|
{
"evidence": [
"Dwight D. Eisenhower",
"General of the Army (United States)",
"Five-star rank"
],
"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:\nDwight D. Eisenhower was an American military officer and statesman who achieved the highest military rank of general officer in the United States.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Dwight D. Eisenhower",
"General of the Army (United States)",
"Five-star rank"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3140,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4953
|
Lion is a 2016 Australian biographical drama film starring an Australian actor who was known in Hollywood for his roles as Faramir in The Lord of the Rings film trilogy.
|
{
"evidence": [
"Lion (2016 film)",
"David Wenham"
],
"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:\nLion is a 2016 Australian biographical drama film starring an Australian actor who was known in Hollywood for his roles as Faramir in The Lord of the Rings film trilogy.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Lion (2016 film)",
"David Wenham"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3141,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
62267
|
Alan Rafkin, who attended Syracuse University (a private research university founded in 1831 in Syracuse, NY), was an actor, director, producer and father of two.
|
{
"evidence": [
"Syracuse University_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:\nAlan Rafkin, who attended Syracuse University (a private research university founded in 1831 in Syracuse, NY), was an actor, director, producer and father of two.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Syracuse University_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3142,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.207",
"value": "?search="
},
{
"operation": "search",
"time": "12.54",
"value": "Alan Rafkin"
},
{
"operation": "Now on",
"time": "13.448",
"value": "Alan Rafkin"
},
{
"operation": "Highlighting",
"time": "16.552",
"value": "Alan Rafkin_cell_0_3_1"
},
{
"operation": "Highlighting",
"time": "16.552",
"value": "Alan Rafkin_title"
},
{
"operation": "Highlighting",
"time": "16.554",
"value": "Alan Rafkin_header_cell_0_3_0"
},
{
"operation": "Highlighting",
"time": "16.555",
"value": "Alan Rafkin_header_cell_0_0_0"
},
{
"operation": "hyperlink",
"time": "17.54",
"value": "Syracuse University"
},
{
"operation": "Now on",
"time": "18.592",
"value": "Syracuse University"
},
{
"operation": "Highlighting",
"time": "25.499",
"value": "Syracuse University_sentence_0"
},
{
"operation": "Highlighting",
"time": "72.968",
"value": "Syracuse University_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "81.996",
"value": "Syracuse University_sentence_0"
},
{
"operation": "finish",
"time": "92.285",
"value": "finish"
}
]
}
|
52955
|
Samuel Rhoads (1711 – April 7, 1784) was an architect from US who first worked as a carpenter and builder before becoming a merchant and later served as the 59th mayor of Philadelphia, Pennsylvania and master of the Carpenters' Company of Philadelphia.
|
{
"evidence": [
"Samuel Rhoads_sentence_6",
"Samuel Rhoads_sentence_13",
"Samuel Rhoads_sentence_16",
"Samuel Rhoads_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:\nSamuel Rhoads (1711 – April 7, 1784) was an architect from US who first worked as a carpenter and builder before becoming a merchant and later served as the 59th mayor of Philadelphia, Pennsylvania and master of the Carpenters' Company of Philadelphia.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Samuel Rhoads_sentence_6",
"Samuel Rhoads_sentence_13",
"Samuel Rhoads_sentence_16",
"Samuel Rhoads_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3143,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.375",
"value": "?search="
},
{
"operation": "search",
"time": "14.827",
"value": "Samuel Rhoads"
},
{
"operation": "Now on",
"time": "15.874",
"value": "Samuel Rhoads"
},
{
"operation": "Highlighting",
"time": "20.865",
"value": "Samuel Rhoads_cell_0_3_1"
},
{
"operation": "Highlighting",
"time": "20.869",
"value": "Samuel Rhoads_header_cell_0_3_0"
},
{
"operation": "Highlighting",
"time": "20.869",
"value": "Samuel Rhoads_header_cell_0_2_0"
},
{
"operation": "Highlighting",
"time": "20.869",
"value": "Samuel Rhoads_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "20.869",
"value": "Samuel Rhoads_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "21.556",
"value": "Samuel Rhoads_cell_0_4_1"
},
{
"operation": "Highlighting",
"time": "21.559",
"value": "Samuel Rhoads_header_cell_0_4_0"
},
{
"operation": "Highlighting",
"time": "45.554",
"value": "Samuel Rhoads_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "54.389",
"value": "Samuel Rhoads_sentence_0"
},
{
"operation": "Highlighting",
"time": "66.594",
"value": "Samuel Rhoads_sentence_6"
},
{
"operation": "Highlighting",
"time": "86.611",
"value": "Samuel Rhoads_sentence_13"
},
{
"operation": "Highlighting",
"time": "120.126",
"value": "Samuel Rhoads_sentence_16"
},
{
"operation": "Highlighting",
"time": "155.606",
"value": "Samuel Rhoads_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "157.946",
"value": "Samuel Rhoads_cell_0_3_1"
},
{
"operation": "Highlighting deleted",
"time": "157.95",
"value": "Samuel Rhoads_header_cell_0_3_0"
},
{
"operation": "Highlighting deleted",
"time": "158.784",
"value": "Samuel Rhoads_cell_0_4_1"
},
{
"operation": "Highlighting deleted",
"time": "158.788",
"value": "Samuel Rhoads_header_cell_0_4_0"
},
{
"operation": "Highlighting deleted",
"time": "158.789",
"value": "Samuel Rhoads_header_cell_0_2_0"
},
{
"operation": "Highlighting deleted",
"time": "158.79",
"value": "Samuel Rhoads_header_cell_0_1_0"
},
{
"operation": "Highlighting deleted",
"time": "158.791",
"value": "Samuel Rhoads_header_cell_0_0_0"
},
{
"operation": "finish",
"time": "218.917",
"value": "finish"
}
]
}
|
55137
|
Naula is a town in Sri Lanka (an island country in South Asia) with an intermediate climate
|
{
"evidence": [
"Naula_sentence_0",
"Sri Lanka_sentence_3",
"Naula_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:\nNaula is a town in Sri Lanka (an island country in South Asia) with an intermediate climate\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Naula_sentence_0",
"Sri Lanka_sentence_3",
"Naula_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3144,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.742",
"value": "?search="
},
{
"operation": "search",
"time": "20.549",
"value": "Naula"
},
{
"operation": "Now on",
"time": "22.004",
"value": "Naula"
},
{
"operation": "Highlighting",
"time": "24.241",
"value": "Naula_sentence_0"
},
{
"operation": "hyperlink",
"time": "25.113",
"value": "Sri Lanka"
},
{
"operation": "Now on",
"time": "26.988",
"value": "Sri Lanka"
},
{
"operation": "Highlighting",
"time": "38.206",
"value": "Sri Lanka_sentence_3"
},
{
"operation": "back-button-clicked",
"time": "44.924",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "44.976",
"value": "Naula"
},
{
"operation": "Highlighting",
"time": "49.261",
"value": "Naula_sentence_3"
},
{
"operation": "finish",
"time": "56.869",
"value": "finish"
}
]
}
|
exfever_7577
|
Kamala Harris is a member of the world's oldest active political party who became the first female vice president of the United Kingdom.
|
{
"evidence": [
"Kamala Harris",
"Democratic Party (United States)"
],
"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:\nKamala Harris is a member of the world's oldest active political party who became the first female vice president of the United Kingdom.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Kamala Harris",
"Democratic Party (United States)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3145,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
63407
|
Norrie Martin played for the Rangers, a Scottish professional football club in Edinburgh.
|
{
"evidence": [
"Rangers F.C._sentence_1"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nNorrie Martin played for the Rangers, a Scottish professional football club in Edinburgh.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Rangers F.C._sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3146,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.953",
"value": "?search="
},
{
"operation": "search",
"time": "12.784",
"value": "Norrie Martin"
},
{
"operation": "Now on",
"time": "13.655",
"value": "Norrie Martin"
},
{
"operation": "Highlighting",
"time": "141.832",
"value": "Norrie Martin_sentence_0"
},
{
"operation": "Highlighting",
"time": "141.832",
"value": "Norrie Martin_title"
},
{
"operation": "hyperlink",
"time": "161.752",
"value": "Rangers"
},
{
"operation": "Now on",
"time": "163.622",
"value": "Rangers F.C."
},
{
"operation": "Highlighting",
"time": "166.023",
"value": "Rangers F.C._sentence_1"
},
{
"operation": "finish",
"time": "186.815",
"value": "finish"
}
]
}
|
exfever_6039
|
Steel is a 1997 American superhero film loosely based on the American comic book publisher that recently relocated its headquarters to a city in the southeastern end of the Conejo Valley in Los Angeles County.
|
{
"evidence": [
"Steel (1997 film)",
"DC Comics",
"Burbank, California"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSteel is a 1997 American superhero film loosely based on the American comic book publisher that recently relocated its headquarters to a city in the southeastern end of the Conejo Valley in Los Angeles County.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Steel (1997 film)",
"DC Comics",
"Burbank, California"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3147,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
57646
|
The 2008 VMI Keydets football team never represented any college and played an unknown number of games in the 2008 season.
|
{
"evidence": [
"Virginia Military Institute_sentence_0",
"2008 VMI Keydets football team_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 2008 VMI Keydets football team never represented any college and played an unknown number of games in the 2008 season.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Virginia Military Institute_sentence_0",
"2008 VMI Keydets football team_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3148,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.723",
"value": "?search="
},
{
"operation": "search",
"time": "8.433",
"value": "2008 VMI Keydets football team"
},
{
"operation": "Now on",
"time": "9.397",
"value": "2008 VMI Keydets football team"
},
{
"operation": "hyperlink",
"time": "33.573",
"value": "Virginia Military Institute"
},
{
"operation": "Now on",
"time": "37.422",
"value": "Virginia Military Institute"
},
{
"operation": "Highlighting",
"time": "38.439",
"value": "Virginia Military Institute_sentence_0"
},
{
"operation": "search",
"time": "46.929",
"value": "2008 VMI Keydets football team"
},
{
"operation": "Now on",
"time": "47.824",
"value": "2008 VMI Keydets football team"
},
{
"operation": "Highlighting",
"time": "54.822",
"value": "2008 VMI Keydets football team_sentence_0"
},
{
"operation": "finish",
"time": "68.47",
"value": "finish"
}
]
}
|
78018
|
With a total area of 246.31 km, Cayma District is one of the twenty-nine districts of Peru's Arequipa Province, which is known as the birthplace of Adobo, the cites official dish, and known to have no churches in the area.
|
{
"evidence": [
"Cayma District_sentence_0",
"Cayma District_sentence_1",
"Cayma District_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:\nWith a total area of 246.31 km, Cayma District is one of the twenty-nine districts of Peru's Arequipa Province, which is known as the birthplace of Adobo, the cites official dish, and known to have no churches in the area.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Cayma District_sentence_0",
"Cayma District_sentence_1",
"Cayma District_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3149,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.483",
"value": "?search="
},
{
"operation": "search",
"time": "15.069",
"value": "Cayma District"
},
{
"operation": "Now on",
"time": "16.012",
"value": "Cayma District"
},
{
"operation": "Highlighting",
"time": "32.753",
"value": "Cayma District_sentence_0"
},
{
"operation": "Highlighting",
"time": "42.044",
"value": "Cayma District_sentence_1"
},
{
"operation": "Highlighting",
"time": "48.067",
"value": "Cayma District_sentence_2"
},
{
"operation": "finish",
"time": "57.56",
"value": "finish"
}
]
}
|
exfever_8768
|
Julius Caesar subsequently became dictator of Rome from 49 BC until being assassinated by a group of senators on the Ides of March in 44 BC.
|
{
"evidence": [
"Julius Caesar",
"Assassination of Julius Caesar"
],
"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:\nJulius Caesar subsequently became dictator of Rome from 49 BC until being assassinated by a group of senators on the Ides of March in 44 BC.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Julius Caesar",
"Assassination of Julius Caesar"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3150,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8519
|
Apocalypse Now is a 1979 American epic psychological war film starring an American actor.
|
{
"evidence": [
"Apocalypse Now",
"Albert Hall (actor)"
],
"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:\nApocalypse Now is a 1979 American epic psychological war film starring an American actor.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Apocalypse Now",
"Albert Hall (actor)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3151,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
70272
|
The 2011–12 UCI Africa Tour began on September 29, 2011, with the Grand Prix Chantal Biya (a professional road bicycle racing stage race held in Cameroon and sponsored by the Fédération Camerounaise de Cyclisme/Ateba Koungou), and in 2015 UCI Africa Tour, ten races had a UCI rating of 1.2 while four races had a UCI rating of 2.2.
|
{
"evidence": [
"2011–12 UCI Africa Tour_sentence_1",
"Grand Prix Chantal Biya_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 2011–12 UCI Africa Tour began on September 29, 2011, with the Grand Prix Chantal Biya (a professional road bicycle racing stage race held in Cameroon and sponsored by the Fédération Camerounaise de Cyclisme/Ateba Koungou), and in 2015 UCI Africa Tour, ten races had a UCI rating of 1.2 while four races had a UCI rating of 2.2.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"2011–12 UCI Africa Tour_sentence_1",
"Grand Prix Chantal Biya_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3152,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.808",
"value": "?search="
},
{
"operation": "search",
"time": "21.473",
"value": "2011–12 UCI Africa Tour"
},
{
"operation": "Now on",
"time": "22.592",
"value": "2011–12 UCI Africa Tour"
},
{
"operation": "Highlighting",
"time": "29.602",
"value": "2011–12 UCI Africa Tour_sentence_1"
},
{
"operation": "hyperlink",
"time": "48",
"value": "Grand Prix Chantal Biya"
},
{
"operation": "Now on",
"time": "48.658",
"value": "Grand Prix Chantal Biya"
},
{
"operation": "Highlighting",
"time": "54.812",
"value": "Grand Prix Chantal Biya_sentence_0"
},
{
"operation": "back-button-clicked",
"time": "56.333",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "56.381",
"value": "2011–12 UCI Africa Tour"
},
{
"operation": "search",
"time": "103.368",
"value": "Contains... 2015 UCI Africa Tour"
},
{
"operation": "Now on",
"time": "105.087",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "122.873",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "122.92",
"value": "2011–12 UCI Africa Tour"
},
{
"operation": "hyperlink",
"time": "128.834",
"value": "UCI Africa Tour"
},
{
"operation": "Now on",
"time": "130.301",
"value": "UCI Continental Circuits"
},
{
"operation": "search",
"time": "181.369",
"value": "UCI ratings"
},
{
"operation": "Now on",
"time": "182.82",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "196.743",
"value": "2015 UCI America Tour"
},
{
"operation": "Now on",
"time": "197.538",
"value": "2015 UCI America Tour"
},
{
"operation": "search",
"time": "218.082",
"value": "2015 UCI Africa Tour"
},
{
"operation": "Now on",
"time": "219.478",
"value": "undefined"
},
{
"operation": "search",
"time": "253.849",
"value": "Contains...ten races had a UCI rating of 1.2 while four races had a UCI rating of 2.2"
},
{
"operation": "Now on",
"time": "255.863",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "296.757",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "297.757",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "301.042",
"value": "2015 KZN Autumn Series"
},
{
"operation": "Now on",
"time": "301.779",
"value": "2015 KZN Autumn Series"
},
{
"operation": "back-button-clicked",
"time": "317.935",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "318.974",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "318.983",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "318.987",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "318.99",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "319.032",
"value": "2015 UCI America Tour"
},
{
"operation": "back-button-clicked",
"time": "319.953",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "319.955",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "320.892",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "322.634",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "322.637",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "323.818",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "323.861",
"value": "2011–12 UCI Africa Tour"
},
{
"operation": "search",
"time": "451.001",
"value": "UCI Africa Tour"
},
{
"operation": "Now on",
"time": "452.379",
"value": "UCI Continental Circuits"
},
{
"operation": "Highlighting",
"time": "481.678",
"value": "UCI Continental Circuits_cell_0_11_0"
},
{
"operation": "Highlighting",
"time": "481.68",
"value": "UCI Continental Circuits_title"
},
{
"operation": "Highlighting",
"time": "481.68",
"value": "UCI Continental Circuits_section_0"
},
{
"operation": "Highlighting",
"time": "481.68",
"value": "UCI Continental Circuits_section_1"
},
{
"operation": "Highlighting",
"time": "481.682",
"value": "UCI Continental Circuits_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "484.116",
"value": "UCI Continental Circuits_cell_0_11_0"
},
{
"operation": "Highlighting deleted",
"time": "484.116",
"value": "UCI Continental Circuits_title"
},
{
"operation": "Highlighting deleted",
"time": "484.117",
"value": "UCI Continental Circuits_section_0"
},
{
"operation": "Highlighting deleted",
"time": "484.118",
"value": "UCI Continental Circuits_section_1"
},
{
"operation": "Highlighting deleted",
"time": "484.12",
"value": "UCI Continental Circuits_header_cell_0_0_0"
},
{
"operation": "hyperlink",
"time": "493.389",
"value": "Skydive Dubai Pro Cycling Team–Al Ahli Club"
},
{
"operation": "Now on",
"time": "494.116",
"value": "Skydive Dubai–Al Ahli Pro Cycling Team"
},
{
"operation": "back-button-clicked",
"time": "501.922",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "507.613",
"value": "UCI Continental Circuits"
},
{
"operation": "hyperlink",
"time": "527.835",
"value": "Salah Eddine Mraouni"
},
{
"operation": "Now on",
"time": "528.331",
"value": "Salah Eddine Mraouni"
},
{
"operation": "finish",
"time": "550.635",
"value": "finish"
}
]
}
|
30484
|
The Revolution Is Never Coming received a positive rating from Tone Deaf, while Rolling Stone (an American monthly magazine that never focuses on popular culture), Zoo Weekly, and Sputnikmusic failed to give it a review score.
|
{
"evidence": [
"Rolling Stone_sentence_3"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Revolution Is Never Coming received a positive rating from Tone Deaf, while Rolling Stone (an American monthly magazine that never focuses on popular culture), Zoo Weekly, and Sputnikmusic failed to give it a review score.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Rolling Stone_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3153,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.867",
"value": "?search="
},
{
"operation": "search",
"time": "11.174",
"value": "The Revolution Is Never Coming"
},
{
"operation": "Now on",
"time": "13.152",
"value": "The Revolution Is Never Coming"
},
{
"operation": "Highlighting",
"time": "15.583",
"value": "The Revolution Is Never Coming_cell_0_2_1"
},
{
"operation": "Highlighting",
"time": "15.585",
"value": "The Revolution Is Never Coming_title"
},
{
"operation": "Highlighting",
"time": "15.591",
"value": "The Revolution Is Never Coming_header_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "15.592",
"value": "The Revolution Is Never Coming_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "16.274",
"value": "The Revolution Is Never Coming_cell_0_2_0"
},
{
"operation": "Highlighting",
"time": "16.277",
"value": "The Revolution Is Never Coming_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "20.619",
"value": "The Revolution Is Never Coming_cell_0_3_0"
},
{
"operation": "Highlighting",
"time": "21.083",
"value": "The Revolution Is Never Coming_cell_0_3_1"
},
{
"operation": "Highlighting",
"time": "22.52",
"value": "The Revolution Is Never Coming_cell_0_4_0"
},
{
"operation": "Highlighting",
"time": "23.097",
"value": "The Revolution Is Never Coming_cell_0_4_1"
},
{
"operation": "Highlighting",
"time": "23.671",
"value": "The Revolution Is Never Coming_cell_0_5_0"
},
{
"operation": "Highlighting",
"time": "24.231",
"value": "The Revolution Is Never Coming_cell_0_5_1"
},
{
"operation": "hyperlink",
"time": "26.763",
"value": "Rolling Stone"
},
{
"operation": "Now on",
"time": "27.606",
"value": "Rolling Stone"
},
{
"operation": "Highlighting",
"time": "29.751",
"value": "Rolling Stone_sentence_3"
},
{
"operation": "back-button-clicked",
"time": "34.608",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "34.701",
"value": "The Revolution Is Never Coming"
},
{
"operation": "Highlighting deleted",
"time": "35.669",
"value": "The Revolution Is Never Coming_cell_0_2_1"
},
{
"operation": "Highlighting deleted",
"time": "36.181",
"value": "The Revolution Is Never Coming_cell_0_2_0"
},
{
"operation": "Highlighting deleted",
"time": "36.551",
"value": "The Revolution Is Never Coming_cell_0_3_1"
},
{
"operation": "Highlighting deleted",
"time": "37.061",
"value": "The Revolution Is Never Coming_cell_0_3_0"
},
{
"operation": "Highlighting deleted",
"time": "37.458",
"value": "The Revolution Is Never Coming_cell_0_5_1"
},
{
"operation": "Highlighting deleted",
"time": "38.086",
"value": "The Revolution Is Never Coming_cell_0_4_0"
},
{
"operation": "Highlighting deleted",
"time": "38.51",
"value": "The Revolution Is Never Coming_cell_0_5_0"
},
{
"operation": "Highlighting deleted",
"time": "38.517",
"value": "The Revolution Is Never Coming_header_cell_0_1_0"
},
{
"operation": "Highlighting deleted",
"time": "38.943",
"value": "The Revolution Is Never Coming_cell_0_4_1"
},
{
"operation": "Highlighting deleted",
"time": "38.945",
"value": "The Revolution Is Never Coming_title"
},
{
"operation": "Highlighting deleted",
"time": "38.948",
"value": "The Revolution Is Never Coming_header_cell_0_1_1"
},
{
"operation": "Highlighting deleted",
"time": "38.949",
"value": "The Revolution Is Never Coming_header_cell_0_0_0"
},
{
"operation": "finish",
"time": "50.598",
"value": "finish"
}
]
}
|
exfever_1735
|
Winter Passing is a 2005 American action film starring an American actress who is known for her deadpan roles in comedy films, including a 2008 romantic comedy film directed by Peyton Reed.
|
{
"evidence": [
"Winter Passing",
"Zooey Deschanel",
"Yes Man (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:\nWinter Passing is a 2005 American action film starring an American actress who is known for her deadpan roles in comedy films, including a 2008 romantic comedy film directed by Peyton Reed.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Winter Passing",
"Zooey Deschanel",
"Yes Man (film)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3154,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8531
|
The Star Wars sequel trilogy is the third trilogy of the primary Star Wars franchise, produced by Lucasfilm Ltd. and distributed by the Chinese film distribution studio within the Disney Media and Entertainment Distribution division.
|
{
"evidence": [
"Star Wars sequel trilogy",
"Walt Disney Studios Motion 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:\nThe Star Wars sequel trilogy is the third trilogy of the primary Star Wars franchise, produced by Lucasfilm Ltd. and distributed by the Chinese film distribution studio within the Disney Media and Entertainment Distribution division.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Star Wars sequel trilogy",
"Walt Disney Studios Motion Pictures"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3155,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6754
|
John Paul Cusack is a film score composer.
|
{
"evidence": [
"John Cusack",
"Tapeheads",
"Tim Robbins"
],
"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:\nJohn Paul Cusack is a film score composer.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"John Cusack",
"Tapeheads",
"Tim Robbins"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3156,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1812
|
Jeffrey Preston Bezos Is an American entrepreneur who graduated from a public Ivy League research university in Princeton, New Jersey.
|
{
"evidence": [
"Jeff Bezos",
"Princeton University"
],
"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:\nJeffrey Preston Bezos Is an American entrepreneur who graduated from a public Ivy League research university in Princeton, New Jersey.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jeff Bezos",
"Princeton University"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3157,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
11065
|
Sengalese football team Diambars FC was founded in 2003 and elevated to international status in 2009; they won their only League Cup in 2016.
|
{
"evidence": [
"Diambars FC_sentence_3"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSengalese football team Diambars FC was founded in 2003 and elevated to international status in 2009; they won their only League Cup in 2016.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Diambars FC_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3158,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.704",
"value": "?search="
},
{
"operation": "search",
"time": "10.775",
"value": "Diambars FC"
},
{
"operation": "Now on",
"time": "12.28",
"value": "Diambars FC"
},
{
"operation": "Highlighting",
"time": "14.979",
"value": "Diambars FC_sentence_0"
},
{
"operation": "Highlighting",
"time": "18.312",
"value": "Diambars FC_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "18.315",
"value": "Diambars FC_header_cell_0_1_0"
},
{
"operation": "Page search",
"time": "41.419",
"value": "2009"
},
{
"operation": "Highlighting",
"time": "56.336",
"value": "Diambars FC_sentence_3"
},
{
"operation": "hyperlink",
"time": "90.149",
"value": "CAF Champions League"
},
{
"operation": "Now on",
"time": "92.335",
"value": "CAF Champions League"
},
{
"operation": "back-button-clicked",
"time": "97.979",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "98.153",
"value": "Diambars FC"
},
{
"operation": "Highlighting deleted",
"time": "104.506",
"value": "Diambars FC_sentence_0"
},
{
"operation": "Page search",
"time": "120.409",
"value": "league cup"
},
{
"operation": "Highlighting",
"time": "125.81",
"value": "Diambars FC_sentence_9"
},
{
"operation": "Highlighting deleted",
"time": "159.375",
"value": "Diambars FC_sentence_9"
},
{
"operation": "Highlighting deleted",
"time": "164.091",
"value": "Diambars FC_cell_0_1_1"
},
{
"operation": "Highlighting deleted",
"time": "164.096",
"value": "Diambars FC_header_cell_0_1_0"
},
{
"operation": "finish",
"time": "173.375",
"value": "finish"
}
]
}
|
62440
|
Ireland competed at the 2011 World Championships in Athletics from August 27 to September 4 in Daegu, South Korea, and during this event, only two men out of the six men from Ireland finished the finals, and they were Ciaran O'Lionaird (1500 meters) and Alistair Ian Cragg (5000 meters).
|
{
"evidence": [
"2011 World Championships in Athletics_sentence_1",
"2011 World Championships in Athletics_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:\nIreland competed at the 2011 World Championships in Athletics from August 27 to September 4 in Daegu, South Korea, and during this event, only two men out of the six men from Ireland finished the finals, and they were Ciaran O'Lionaird (1500 meters) and Alistair Ian Cragg (5000 meters).\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"2011 World Championships in Athletics_sentence_1",
"2011 World Championships in Athletics_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3159,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.493",
"value": "?search="
},
{
"operation": "Now on",
"time": "2398.039",
"value": "?search="
},
{
"operation": "search",
"time": "2457.412",
"value": "he 2011 World Championships in Athletics"
},
{
"operation": "Now on",
"time": "2461.567",
"value": "undefined"
},
{
"operation": "search",
"time": "2501.063",
"value": "2011 World Championships in Athletics"
},
{
"operation": "Now on",
"time": "2507.485",
"value": "2011 World Championships in Athletics"
},
{
"operation": "Highlighting",
"time": "2522.935",
"value": "2011 World Championships in Athletics_sentence_1"
},
{
"operation": "Highlighting",
"time": "2525.044",
"value": "2011 World Championships in Athletics_sentence_0"
},
{
"operation": "search",
"time": "2620.536",
"value": "Ciaran O'Lionaird"
},
{
"operation": "Now on",
"time": "2622.451",
"value": "Ciarán Ó Lionáird"
},
{
"operation": "hyperlink",
"time": "2634.968",
"value": "2011 IAAF World Championships"
},
{
"operation": "Now on",
"time": "2640.679",
"value": "2011 World Championships in Athletics"
},
{
"operation": "hyperlink",
"time": "2704.655",
"value": "2011 World Championships in Athletics qualification standards"
},
{
"operation": "Now on",
"time": "2706.245",
"value": "2011 World Championships in Athletics qualification standards"
},
{
"operation": "back-button-clicked",
"time": "2710.722",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "2711.045",
"value": "2011 World Championships in Athletics"
},
{
"operation": "search",
"time": "2782.562",
"value": "Alistair Ian Cragg"
},
{
"operation": "Now on",
"time": "2785.081",
"value": "Alistair Cragg"
},
{
"operation": "hyperlink",
"time": "2809.041",
"value": "2011 World Championships in Athletics"
},
{
"operation": "Now on",
"time": "2810.388",
"value": "2011 World Championships in Athletics"
},
{
"operation": "finish",
"time": "2881.233",
"value": "finish"
}
]
}
|
50611
|
The list of Date A Live episodes, an anime series adapted from the light novels of the same title written by Kōshi Tachibana, include those from the second season which was produced by Production IMS while the third season was produced by J.C.Staff.
|
{
"evidence": [
"List of Date A Live episodes_sentence_0",
"Date A Live (season 2)_sentence_2",
"Date A Live (season 3)_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 list of Date A Live episodes, an anime series adapted from the light novels of the same title written by Kōshi Tachibana, include those from the second season which was produced by Production IMS while the third season was produced by J.C.Staff.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"List of Date A Live episodes_sentence_0",
"Date A Live (season 2)_sentence_2",
"Date A Live (season 3)_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3160,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.852",
"value": "?search="
},
{
"operation": "search",
"time": "85.451",
"value": "list of Date A Live episodes"
},
{
"operation": "Now on",
"time": "86.918",
"value": "List of Date A Live episodes"
},
{
"operation": "Highlighting",
"time": "93.899",
"value": "List of Date A Live episodes_sentence_0"
},
{
"operation": "hyperlink",
"time": "125.362",
"value": "Date A Live (season 2)"
},
{
"operation": "Now on",
"time": "126.183",
"value": "Date A Live (season 2)"
},
{
"operation": "Highlighting",
"time": "130.327",
"value": "Date A Live (season 2)_sentence_2"
},
{
"operation": "back-button-clicked",
"time": "133.489",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "133.611",
"value": "List of Date A Live episodes"
},
{
"operation": "hyperlink",
"time": "136.707",
"value": "Date A Live (season 3)"
},
{
"operation": "Now on",
"time": "138.361",
"value": "Date A Live (season 3)"
},
{
"operation": "Highlighting",
"time": "144.401",
"value": "Date A Live (season 3)_sentence_0"
},
{
"operation": "finish",
"time": "149.768",
"value": "finish"
}
]
}
|
15561
|
Setsuko Hara was a Japanese singer who was active from 1935-1963.
|
{
"evidence": [
"Setsuko Hara_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:\nSetsuko Hara was a Japanese singer who was active from 1935-1963.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Setsuko Hara_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3161,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.576",
"value": "?search="
},
{
"operation": "search",
"time": "5.388",
"value": "Setsuko Hara"
},
{
"operation": "Now on",
"time": "6.1",
"value": "Setsuko Hara"
},
{
"operation": "Highlighting",
"time": "8.005",
"value": "Setsuko Hara_sentence_0"
},
{
"operation": "Page search",
"time": "13.854",
"value": "singer"
},
{
"operation": "finish",
"time": "23.791",
"value": "finish"
}
]
}
|
exfever_8595
|
George Clooney was born on May 6, 1961, in Lexington, Kentucky.
|
{
"evidence": [
"George Clooney",
"NBC",
"30 Rockefeller Plaza"
],
"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:\nGeorge Clooney was born on May 6, 1961, in Lexington, Kentucky.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"George Clooney",
"NBC",
"30 Rockefeller Plaza"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3162,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3093
|
Katharine Houghton Hepburn was an American actress who was raised in the southernmost state in New England, bordered to the south by a marine sound, also known as the tidal estuary of the Atlantic Ocean.
|
{
"evidence": [
"Katharine Hepburn",
"Connecticut",
"Long Island Sound"
],
"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:\nKatharine Houghton Hepburn was an American actress who was raised in the southernmost state in New England, bordered to the south by a marine sound, also known as the tidal estuary of the Atlantic Ocean.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Katharine Hepburn",
"Connecticut",
"Long Island Sound"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3163,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5755
|
Radiohead is an English rock band that worked with an English record producer, recording engineer, and musician.
|
{
"evidence": [
"Radiohead",
"Nigel Godrich"
],
"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:\nRadiohead is an English rock band that worked with an English record producer, recording engineer, and musician.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Radiohead",
"Nigel Godrich"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3164,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8816
|
John Anthony Frusciante is a musician and songwriter who rejoined the Red Chili Peppers, taking them to major success with their seventh studio album was released on June 8, 1999, on Warner Bros.
|
{
"evidence": [
"John Frusciante",
"Californication (album)"
],
"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:\nJohn Anthony Frusciante is a musician and songwriter who rejoined the Red Chili Peppers, taking them to major success with their seventh studio album was released on June 8, 1999, on Warner Bros.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"John Frusciante",
"Californication (album)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3165,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
40150
|
The Colour of My Love was released in Canada on 9 November 1993 by Columbia Records (owned by Sony Music Entertainment), and contained 15 tracks.
|
{
"evidence": [
"The Colour of My Love_sentence_1",
"Columbia Records_sentence_3"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Colour of My Love was released in Canada on 9 November 1993 by Columbia Records (owned by Sony Music Entertainment), and contained 15 tracks.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"The Colour of My Love_sentence_1",
"Columbia Records_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3166,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.713",
"value": "?search="
},
{
"operation": "search",
"time": "14.649",
"value": "The Color of my Love"
},
{
"operation": "Now on",
"time": "15.416",
"value": "The Colour of My Love"
},
{
"operation": "Highlighting",
"time": "24.095",
"value": "The Colour of My Love_sentence_1"
},
{
"operation": "Page search",
"time": "47.349",
"value": "Canada"
},
{
"operation": "hyperlink",
"time": "100.92",
"value": "Columbia Records"
},
{
"operation": "Now on",
"time": "101.705",
"value": "Columbia Records"
},
{
"operation": "Highlighting",
"time": "107.771",
"value": "Columbia Records_sentence_3"
},
{
"operation": "back-button-clicked",
"time": "147.79",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "148.359",
"value": "The Colour of My Love"
},
{
"operation": "finish",
"time": "155.273",
"value": "finish"
}
]
}
|
exfever_5669
|
The Formula is a 1980 movie directed by John G. Avildsen, whose genre revolves around the solution of a problem or a crime.
|
{
"evidence": [
"The Formula (1980 film)",
"Mystery film"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Formula is a 1980 movie directed by John G. Avildsen, whose genre revolves around the solution of a problem or a crime.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Formula (1980 film)",
"Mystery film"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3167,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2720
|
Jennifer Grey is an American actress who subsequently earned worldwide fame for starring as Frances "Baby" Houseman in a 1987 American dance film written by Eleanor Bergstein that involves intimate love stories recorded in visual media for broadcast in theatres or on television.
|
{
"evidence": [
"Jennifer Grey",
"Dirty Dancing",
"Romance film"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJennifer Grey is an American actress who subsequently earned worldwide fame for starring as Frances \"Baby\" Houseman in a 1987 American dance film written by Eleanor Bergstein that involves intimate love stories recorded in visual media for broadcast in theatres or on television.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jennifer Grey",
"Dirty Dancing",
"Romance film"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3168,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
89340
|
In the 2016 Longford Senior Football Championships, there were 14 teams, where Group A and B consisted of 4 teams with 3 progressing to the Quarter-Finals, and Group C consisting of the 4 teams involved in the 2015 S.F.C.
|
{
"evidence": [
"2016 Longford Senior Football Championship_sentence_8",
"2016 Longford Senior Football Championship_sentence_1"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nIn the 2016 Longford Senior Football Championships, there were 14 teams, where Group A and B consisted of 4 teams with 3 progressing to the Quarter-Finals, and Group C consisting of the 4 teams involved in the 2015 S.F.C.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"2016 Longford Senior Football Championship_sentence_8",
"2016 Longford Senior Football Championship_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3169,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.969",
"value": "?search="
},
{
"operation": "search",
"time": "8.528",
"value": "Contains...2016 Longford Senior Football Championships"
},
{
"operation": "Now on",
"time": "10.845",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "12.494",
"value": "2016 Longford Senior Football Championship"
},
{
"operation": "Now on",
"time": "13.239",
"value": "2016 Longford Senior Football Championship"
},
{
"operation": "Highlighting",
"time": "17.936",
"value": "2016 Longford Senior Football Championship_sentence_1"
},
{
"operation": "Highlighting",
"time": "22.518",
"value": "2016 Longford Senior Football Championship_sentence_8"
},
{
"operation": "Highlighting deleted",
"time": "28.014",
"value": "2016 Longford Senior Football Championship_sentence_1"
},
{
"operation": "Highlighting",
"time": "30.323",
"value": "2016 Longford Senior Football Championship_sentence_1"
},
{
"operation": "finish",
"time": "34.111",
"value": "finish"
}
]
}
|
exfever_3003
|
Jeb Bush is an American politician and businessman which is the second son of the American politician, diplomat, and businessman who served as the 42nd president of the United States from 1989 to 1993.
|
{
"evidence": [
"Jeb Bush",
"George H. W. Bush"
],
"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:\nJeb Bush is an American politician and businessman which is the second son of the American politician, diplomat, and businessman who served as the 42nd president of the United States from 1989 to 1993.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jeb Bush",
"George H. W. Bush"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3170,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5467
|
Faheem Rasheed Najm is an Italian rapper, singer, songwriter, and record producer who was signed to Konvict Muzik by a Senegalese American singer who rose to prominence in 2004 following the release of "Locked Up" the first single from his debut album Trouble.
|
{
"evidence": [
"T-Pain",
"Akon"
],
"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:\nFaheem Rasheed Najm is an Italian rapper, singer, songwriter, and record producer who was signed to Konvict Muzik by a Senegalese American singer who rose to prominence in 2004 following the release of \"Locked Up\" the first single from his debut album Trouble.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"T-Pain",
"Akon"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3171,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
61683
|
Out of the 14 participants of Big Brother Europe 4, 11 of which are in their 20's and only three are in their 30's.
|
{
"evidence": [
"Big Brother (franchise)_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:\nOut of the 14 participants of Big Brother Europe 4, 11 of which are in their 20's and only three are in their 30's.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Big Brother (franchise)_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3172,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.388",
"value": "undefined"
},
{
"operation": "search",
"time": "27.033",
"value": "Big Brother Europe 4"
},
{
"operation": "Now on",
"time": "31.435",
"value": "undefined"
},
{
"operation": "search",
"time": "54.361",
"value": "Big Brother Europe"
},
{
"operation": "Now on",
"time": "55.341",
"value": "undefined"
},
{
"operation": "search",
"time": "69.024",
"value": "Big Brother"
},
{
"operation": "Now on",
"time": "70.672",
"value": "Big Brother"
},
{
"operation": "hyperlink",
"time": "144.141",
"value": "Brother (disambiguation)"
},
{
"operation": "Now on",
"time": "145.053",
"value": "Brother (disambiguation)"
},
{
"operation": "back-button-clicked",
"time": "149.727",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "150.231",
"value": "Big Brother"
},
{
"operation": "hyperlink",
"time": "191.397",
"value": "\"Big Brother\" (Glee)"
},
{
"operation": "Now on",
"time": "192.405",
"value": "Big Brother (Glee)"
},
{
"operation": "back-button-clicked",
"time": "196.837",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "197.288",
"value": "Big Brother"
},
{
"operation": "hyperlink",
"time": "200.664",
"value": "Big Brother (franchise)"
},
{
"operation": "Now on",
"time": "204.37",
"value": "Big Brother (franchise)"
},
{
"operation": "Page search",
"time": "248.32",
"value": "europe"
},
{
"operation": "Page search",
"time": "248.54",
"value": "europe"
},
{
"operation": "Page search",
"time": "248.785",
"value": "europe"
},
{
"operation": "Page search",
"time": "248.997",
"value": "europe"
},
{
"operation": "Highlighting",
"time": "334.569",
"value": "Big Brother (franchise)_sentence_2"
},
{
"operation": "finish",
"time": "358.173",
"value": "finish"
}
]
}
|
27537
|
Barnes was a left-handed batsman, born in Grantham but never represented his county.
|
{
"evidence": [
"Terry Barnes_sentence_3",
"Terry Barnes_sentence_5"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nBarnes was a left-handed batsman, born in Grantham but never represented his county.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Terry Barnes_sentence_3",
"Terry Barnes_sentence_5"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3173,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.039",
"value": "?search="
},
{
"operation": "search",
"time": "17.901",
"value": "barnes batsman"
},
{
"operation": "Now on",
"time": "18.776",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "45.597",
"value": "Ross Barnes"
},
{
"operation": "Now on",
"time": "46.387",
"value": "Ross Barnes"
},
{
"operation": "back-button-clicked",
"time": "108.201",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "108.909",
"value": "undefined"
},
{
"operation": "search",
"time": "131.198",
"value": "sid barnes"
},
{
"operation": "Now on",
"time": "132.133",
"value": "Sid Barnes"
},
{
"operation": "Highlighting",
"time": "144.121",
"value": "Sid Barnes_sentence_3"
},
{
"operation": "Highlighting",
"time": "144.123",
"value": "Sid Barnes_title"
},
{
"operation": "search",
"time": "188.604",
"value": "Contains...barnes grantham"
},
{
"operation": "Now on",
"time": "189.276",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "205.28",
"value": "Terry Barnes"
},
{
"operation": "Now on",
"time": "206.025",
"value": "Terry Barnes"
},
{
"operation": "Highlighting",
"time": "226.706",
"value": "Terry Barnes_sentence_2"
},
{
"operation": "Highlighting",
"time": "230.312",
"value": "Terry Barnes_header_cell_0_2_0"
},
{
"operation": "Highlighting",
"time": "231.371",
"value": "Terry Barnes_cell_0_2_1"
},
{
"operation": "Highlighting",
"time": "231.388",
"value": "Terry Barnes_header_cell_0_2_0"
},
{
"operation": "Highlighting",
"time": "231.388",
"value": "Terry Barnes_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "262.08",
"value": "Terry Barnes_sentence_3"
},
{
"operation": "Highlighting",
"time": "269.697",
"value": "Terry Barnes_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "274.406",
"value": "Terry Barnes_cell_0_2_1"
},
{
"operation": "Highlighting deleted",
"time": "274.419",
"value": "Terry Barnes_header_cell_0_2_0"
},
{
"operation": "Highlighting deleted",
"time": "274.42",
"value": "Terry Barnes_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "281.32",
"value": "Terry Barnes_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "283.538",
"value": "Terry Barnes_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "292.527",
"value": "Terry Barnes_sentence_2"
},
{
"operation": "finish",
"time": "334.611",
"value": "finish"
}
]
}
|
52723
|
The state of Victoria in Australia, the second-smallest state with a land area of 91,761 square miles, experienced the wettest January in 2011 which caused flash flooding, resulting in damage to businesses and homes and swelling in the waterways.
|
{
"evidence": [
"Victoria (Australia)_sentence_2",
"Victoria (Australia)_sentence_3",
"Victoria (Australia)_sentence_123",
"Wilsons Promontory_sentence_31"
],
"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 state of Victoria in Australia, the second-smallest state with a land area of 91,761 square miles, experienced the wettest January in 2011 which caused flash flooding, resulting in damage to businesses and homes and swelling in the waterways.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Victoria (Australia)_sentence_2",
"Victoria (Australia)_sentence_3",
"Victoria (Australia)_sentence_123",
"Wilsons Promontory_sentence_31"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3174,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.067",
"value": "?search="
},
{
"operation": "search",
"time": "18.978",
"value": "Victoria, Australia"
},
{
"operation": "Now on",
"time": "28.768",
"value": "Victoria (Australia)"
},
{
"operation": "Highlighting",
"time": "33.421",
"value": "Victoria (Australia)_sentence_2"
},
{
"operation": "Highlighting",
"time": "37.9",
"value": "Victoria (Australia)_sentence_3"
},
{
"operation": "Page search",
"time": "52.994",
"value": "2011"
},
{
"operation": "Highlighting",
"time": "77.069",
"value": "Victoria (Australia)_sentence_123"
},
{
"operation": "hyperlink",
"time": "141.451",
"value": "Tidal River"
},
{
"operation": "Now on",
"time": "142.091",
"value": "Tidal River, Victoria"
},
{
"operation": "Page search",
"time": "149.232",
"value": "2011"
},
{
"operation": "hyperlink",
"time": "160.521",
"value": "Tidal River (Victoria)"
},
{
"operation": "Now on",
"time": "161.437",
"value": "Tidal River (Victoria)"
},
{
"operation": "Page search",
"time": "164.689",
"value": "2011"
},
{
"operation": "search",
"time": "186.577",
"value": "victoria, australia flooding"
},
{
"operation": "Now on",
"time": "187.823",
"value": "undefined"
},
{
"operation": "search",
"time": "202.442",
"value": "2011 flood victoria australia"
},
{
"operation": "Now on",
"time": "203.163",
"value": "undefined"
},
{
"operation": "search",
"time": "214.531",
"value": "Victoria, Australia"
},
{
"operation": "Now on",
"time": "215.108",
"value": "Victoria, Australia"
},
{
"operation": "hyperlink",
"time": "227.094",
"value": "2.2.1 Rainfall Victoria (Australia)_section_8"
},
{
"operation": "hyperlink",
"time": "231.068",
"value": "Wilsons Promontory National Park"
},
{
"operation": "Now on",
"time": "231.605",
"value": "Wilsons Promontory National Park"
},
{
"operation": "hyperlink",
"time": "254.56",
"value": "Wilsons Promontory"
},
{
"operation": "Now on",
"time": "256.544",
"value": "Wilsons Promontory"
},
{
"operation": "Highlighting",
"time": "260.659",
"value": "Wilsons Promontory_sentence_31"
},
{
"operation": "hyperlink",
"time": "346.257",
"value": "Victoria"
},
{
"operation": "Now on",
"time": "347.808",
"value": "Victoria (Australia)"
},
{
"operation": "finish",
"time": "392.464",
"value": "finish"
}
]
}
|
43428
|
Kurt Gottfried is a professor of Physics, he was born in Milan, his family emigrated to Montreal and studied at Massachusetts Institute of Technology.
|
{
"evidence": [
"Kurt Gottfried_sentence_3"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nKurt Gottfried is a professor of Physics, he was born in Milan, his family emigrated to Montreal and studied at Massachusetts Institute of Technology.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Kurt Gottfried_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3175,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.17",
"value": "?search="
},
{
"operation": "search",
"time": "12.677",
"value": "Kurt Gottfried"
},
{
"operation": "Now on",
"time": "13.45",
"value": "Kurt Gottfried"
},
{
"operation": "Highlighting",
"time": "40.11",
"value": "Kurt Gottfried_sentence_9"
},
{
"operation": "Highlighting",
"time": "40.113",
"value": "Kurt Gottfried_section_1"
},
{
"operation": "Highlighting",
"time": "45.621",
"value": "Kurt Gottfried_sentence_10"
},
{
"operation": "Highlighting",
"time": "54.058",
"value": "Kurt Gottfried_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "55.857",
"value": "Kurt Gottfried_sentence_9"
},
{
"operation": "Highlighting deleted",
"time": "56.499",
"value": "Kurt Gottfried_sentence_10"
},
{
"operation": "Highlighting deleted",
"time": "56.502",
"value": "Kurt Gottfried_section_1"
},
{
"operation": "finish",
"time": "64.759",
"value": "finish"
}
]
}
|
exfever_5205
|
DC Comics' first published book was Superman.
|
{
"evidence": [
"Superman",
"Superhero",
"Stock character"
],
"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:\nDC Comics' first published book was Superman.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Superman",
"Superhero",
"Stock character"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3176,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
35784
|
Mary Beth Peil is an American actress and singer and recipient of an Obie Award which is given by The Village Voice newspaper to theater artist s and groups in New York City.
|
{
"evidence": [
"Obie Award_sentence_2",
"Mary Beth Peil_sentence_0",
"Mary Beth Peil_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:\nMary Beth Peil is an American actress and singer and recipient of an Obie Award which is given by The Village Voice newspaper to theater artist s and groups in New York City.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Obie Award_sentence_2",
"Mary Beth Peil_sentence_0",
"Mary Beth Peil_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3177,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.28",
"value": "?search="
},
{
"operation": "search",
"time": "13.584",
"value": "Obie Award"
},
{
"operation": "Now on",
"time": "16.085",
"value": "Obie Award"
},
{
"operation": "Highlighting",
"time": "20.284",
"value": "Obie Award_sentence_2"
},
{
"operation": "search",
"time": "31.279",
"value": "Mary Beth Peil"
},
{
"operation": "Now on",
"time": "33.609",
"value": "Mary Beth Peil"
},
{
"operation": "Highlighting",
"time": "36.338",
"value": "Mary Beth Peil_sentence_0"
},
{
"operation": "Highlighting",
"time": "39.31",
"value": "Mary Beth Peil_sentence_1"
},
{
"operation": "finish",
"time": "63.099",
"value": "finish"
}
]
}
|
exfever_7772
|
The Odyssey is one of two major ancient Greek short narrative poem typically about the extraordinary deeds of extraordinary characters, attributed to Homer.
|
{
"evidence": [
"Odyssey",
"Epic poetry"
],
"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 Odyssey is one of two major ancient Greek short narrative poem typically about the extraordinary deeds of extraordinary characters, attributed to Homer.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Odyssey",
"Epic poetry"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3178,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6190
|
The Fall's collaborators include Paul Simonon, of an English band that covers a broad genre of popular music that originated in the United States.
|
{
"evidence": [
"The Fall (Gorillaz album)",
"The Clash",
"Rock music"
],
"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 Fall's collaborators include Paul Simonon, of an English band that covers a broad genre of popular music that originated in the United States.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Fall (Gorillaz album)",
"The Clash",
"Rock music"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3179,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
79975
|
Christian Frederik von Schalburg defended himself as a victim of Jewish slander and headed the youth branch of the National Socialist Workers' Party of Denmark from 1939.
|
{
"evidence": [
"Christian Frederik von Schalburg_sentence_17",
"Christian Frederik von Schalburg_sentence_18"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nChristian Frederik von Schalburg defended himself as a victim of Jewish slander and headed the youth branch of the National Socialist Workers' Party of Denmark from 1939.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Christian Frederik von Schalburg_sentence_17",
"Christian Frederik von Schalburg_sentence_18"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3180,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.846",
"value": "?search="
},
{
"operation": "search",
"time": "10.183",
"value": "Christian Frederik von Schalburg"
},
{
"operation": "Now on",
"time": "10.9",
"value": "Christian Frederik von Schalburg"
},
{
"operation": "Highlighting",
"time": "48.222",
"value": "Christian Frederik von Schalburg_sentence_17"
},
{
"operation": "Highlighting",
"time": "53.835",
"value": "Christian Frederik von Schalburg_sentence_18"
},
{
"operation": "finish",
"time": "145.273",
"value": "finish"
}
]
}
|
61537
|
Located within McDowell County and Tazewell County, West Virginia Route 161 enters Virginia for approximately 700 feet (213 m), and has clear signs or visual indications between state lines.
|
{
"evidence": [
"West Virginia Route 161_sentence_0",
"West Virginia Route 161_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:\nLocated within McDowell County and Tazewell County, West Virginia Route 161 enters Virginia for approximately 700 feet (213 m), and has clear signs or visual indications between state lines.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"West Virginia Route 161_sentence_0",
"West Virginia Route 161_sentence_8"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3181,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.73",
"value": "?search="
},
{
"operation": "search",
"time": "15.902",
"value": "West Virginia Route 161"
},
{
"operation": "Now on",
"time": "16.617",
"value": "West Virginia Route 161"
},
{
"operation": "Highlighting",
"time": "54.132",
"value": "West Virginia Route 161_sentence_0"
},
{
"operation": "Highlighting",
"time": "67.704",
"value": "West Virginia Route 161_sentence_8"
},
{
"operation": "finish",
"time": "73.416",
"value": "finish"
}
]
}
|
exfever_8205
|
Sense8 is an American science fiction drama streaming television series created by an American filmmaker, comic book writer, and founder of a studio initially run by Patricia Tallman.
|
{
"evidence": [
"Sense8",
"J. Michael Straczynski",
"Studio JMS"
],
"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:\nSense8 is an American science fiction drama streaming television series created by an American filmmaker, comic book writer, and founder of a studio initially run by Patricia Tallman.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Sense8",
"J. Michael Straczynski",
"Studio JMS"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3182,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
43442
|
Marshall Altman, who once worked in sales, formed a band called Desert in 1995, and as a record producer has worked for a variety of artists, including Audrey Assad, an American singer-songwriter and contemporary Christian music artist.
|
{
"evidence": [
"Marshall Altman_sentence_17"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMarshall Altman, who once worked in sales, formed a band called Desert in 1995, and as a record producer has worked for a variety of artists, including Audrey Assad, an American singer-songwriter and contemporary Christian music artist.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Marshall Altman_sentence_17"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3183,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.044",
"value": "?search="
},
{
"operation": "search",
"time": "8.918",
"value": "Marshall Altman"
},
{
"operation": "Now on",
"time": "9.716",
"value": "Marshall Altman"
},
{
"operation": "Highlighting",
"time": "26.587",
"value": "Marshall Altman_sentence_16"
},
{
"operation": "Highlighting",
"time": "60.659",
"value": "Marshall Altman_sentence_17"
},
{
"operation": "Highlighting deleted",
"time": "61.505",
"value": "Marshall Altman_sentence_16"
},
{
"operation": "finish",
"time": "69.838",
"value": "finish"
}
]
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.