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 |
|---|---|---|---|---|---|---|---|---|
12491
|
People Powered Vehicle were manufactured by EVI of Sterling Heights, Michigan and it had limited weather protection.
|
{
"evidence": [
"People Powered Vehicle_sentence_1",
"People Powered Vehicle_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:\nPeople Powered Vehicle were manufactured by EVI of Sterling Heights, Michigan and it had limited weather protection.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"People Powered Vehicle_sentence_1",
"People Powered Vehicle_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4284,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.063",
"value": "?search="
},
{
"operation": "search",
"time": "10.2",
"value": "People Powered Vehicle"
},
{
"operation": "Now on",
"time": "11.261",
"value": "People Powered Vehicle"
},
{
"operation": "Highlighting",
"time": "13.702",
"value": "People Powered Vehicle_sentence_1"
},
{
"operation": "Highlighting",
"time": "21.169",
"value": "People Powered Vehicle_sentence_2"
},
{
"operation": "finish",
"time": "33.273",
"value": "finish"
}
]
}
|
exfever_6743
|
Injustice 2 was initially released for the game consoles that include the home video game console developed by Ubisoft.
|
{
"evidence": [
"Injustice 2",
"Xbox One"
],
"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:\nInjustice 2 was initially released for the game consoles that include the home video game console developed by Ubisoft.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Injustice 2",
"Xbox One"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4285,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8088
|
Donald McNichol Sutherland is a Canadian dancer who has been nominated for nine accolades bestowed by the 105 members of the nonprofit organization of journalists and photographers.
|
{
"evidence": [
"Donald Sutherland",
"Golden Globe Award",
"Hollywood Foreign Press Association"
],
"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:\nDonald McNichol Sutherland is a Canadian dancer who has been nominated for nine accolades bestowed by the 105 members of the nonprofit organization of journalists and photographers.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Donald Sutherland",
"Golden Globe Award",
"Hollywood Foreign Press Association"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4286,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1809
|
Danny Boyle won a Golden Globe Award for Best Director for the film The Beach.
|
{
"evidence": [
"The Beach (film)",
"Leonardo DiCaprio"
],
"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:\nDanny Boyle won a Golden Globe Award for Best Director for the film The Beach.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Beach (film)",
"Leonardo DiCaprio"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4287,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
51663
|
After the Ministry of Food Control was abolished in April 1921, Charles McCurdy was appointed Coalition Liberal Chief Whip in succession to Frederick Guest (born on June 1875), who had held the position during the 1918 seat negotiations with the Unionists.
|
{
"evidence": [
"Charles McCurdy_sentence_9",
"Freddie Guest_sentence_0",
"Charles McCurdy_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:\nAfter the Ministry of Food Control was abolished in April 1921, Charles McCurdy was appointed Coalition Liberal Chief Whip in succession to Frederick Guest (born on June 1875), who had held the position during the 1918 seat negotiations with the Unionists.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Charles McCurdy_sentence_9",
"Freddie Guest_sentence_0",
"Charles McCurdy_sentence_10"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4288,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.567",
"value": "undefined"
},
{
"operation": "search",
"time": "39.201",
"value": "Ministry of Food Control"
},
{
"operation": "Now on",
"time": "41.3",
"value": "Ministry of Food Control"
},
{
"operation": "Highlighting",
"time": "69.676",
"value": "Minister of Food_sentence_0"
},
{
"operation": "Highlighting",
"time": "69.677",
"value": "Minister of Food_title"
},
{
"operation": "Highlighting deleted",
"time": "76.593",
"value": "Minister of Food_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "76.594",
"value": "Minister of Food_title"
},
{
"operation": "Page search",
"time": "83.436",
"value": "abol"
},
{
"operation": "Highlighting",
"time": "94.766",
"value": "Minister of Food_sentence_5"
},
{
"operation": "Highlighting",
"time": "94.767",
"value": "Minister of Food_title"
},
{
"operation": "Highlighting deleted",
"time": "99.671",
"value": "Minister of Food_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "99.672",
"value": "Minister of Food_title"
},
{
"operation": "Page search",
"time": "110.403",
"value": "Charles McCurdy"
},
{
"operation": "search",
"time": "120.911",
"value": "Charles McCurdy"
},
{
"operation": "Now on",
"time": "122.46",
"value": "Charles McCurdy"
},
{
"operation": "Page search",
"time": "155.727",
"value": "ministry"
},
{
"operation": "Highlighting",
"time": "163.991",
"value": "Charles McCurdy_sentence_9"
},
{
"operation": "hyperlink",
"time": "178.279",
"value": "Frederick Guest"
},
{
"operation": "Now on",
"time": "178.913",
"value": "Freddie Guest"
},
{
"operation": "Highlighting",
"time": "182.558",
"value": "Freddie Guest_sentence_0"
},
{
"operation": "back-button-clicked",
"time": "191.171",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "191.366",
"value": "Charles McCurdy"
},
{
"operation": "Highlighting",
"time": "196.304",
"value": "Charles McCurdy_sentence_10"
},
{
"operation": "finish",
"time": "241.107",
"value": "finish"
}
]
}
|
exfever_4042
|
The Lamniformes include ten families with 22 species, with the sum of seven living families and 17 living species.
|
{
"evidence": [
"Lamniformes",
"Goblin shark"
],
"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 Lamniformes include ten families with 22 species, with the sum of seven living families and 17 living species.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Lamniformes",
"Goblin shark"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4289,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7208
|
This Is Us is an American family drama television series that was piloted on an American English-language commercial radio network.?
|
{
"evidence": [
"This Is Us (TV series)",
"NBC"
],
"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:\nThis Is Us is an American family drama television series that was piloted on an American English-language commercial radio network.?\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"This Is Us (TV series)",
"NBC"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4290,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1232
|
Aeneas was a Trojan hero, the son of the Greek goddess Aphrodite, who was equivalent to?a Roman goddess whose functions encompassed love, beauty, desire, sex, fertility, prosperity, and victory.
|
{
"evidence": [
"Aeneas",
"Venus (mythology)"
],
"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:\nAeneas was a Trojan hero, the son of the Greek goddess Aphrodite, who was equivalent to?a Roman goddess whose functions encompassed love, beauty, desire, sex, fertility, prosperity, and victory.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Aeneas",
"Venus (mythology)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4291,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1708
|
The Sony Group Corporation is Japan's most profitable company.
|
{
"evidence": [
"Sony",
"Minato, Tokyo"
],
"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 Sony Group Corporation is Japan's most profitable company.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Sony",
"Minato, Tokyo"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4292,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8397
|
Caitlyn Marie Jenner was the captain of the Graceland Yellowjackets.
|
{
"evidence": [
"Caitlyn Jenner",
"Olympic Games"
],
"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:\nCaitlyn Marie Jenner was the captain of the Graceland Yellowjackets.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Caitlyn Jenner",
"Olympic Games"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4293,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
56523
|
Alla Davydova is a retired female hammer thrower from Russia whose personal best throw was 69.17 metres.
|
{
"evidence": [
"Alla Davydova_sentence_0",
"Alla Davydova_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:\nAlla Davydova is a retired female hammer thrower from Russia whose personal best throw was 69.17 metres.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Alla Davydova_sentence_0",
"Alla Davydova_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4294,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.309",
"value": "?search="
},
{
"operation": "search",
"time": "30.166",
"value": "Alla Davydova"
},
{
"operation": "Now on",
"time": "31.904",
"value": "Alla Davydova"
},
{
"operation": "Highlighting",
"time": "49.529",
"value": "Alla Davydova_sentence_0"
},
{
"operation": "Highlighting",
"time": "53.381",
"value": "Alla Davydova_sentence_1"
},
{
"operation": "finish",
"time": "63.802",
"value": "finish"
}
]
}
|
exfever_7178
|
A Song of Ice and Fire is the first written novel by the American author George R. R. Martin.
|
{
"evidence": [
"Gregor Clegane",
"Game of Thrones"
],
"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:\nA Song of Ice and Fire is the first written novel by the American author George R. R. Martin.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Gregor Clegane",
"Game of Thrones"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4295,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
16511
|
Fish River Station, near the Daly River, Wingate Mountains, and Florina Station, was sold to the Indigenous Land Corporation, now the Indigenous Land and Sea Corporation, by Alan Myers in 2011.
|
{
"evidence": [
"Fish River Station_sentence_1",
"Fish River Station_sentence_2",
"Fish River Station_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:\nFish River Station, near the Daly River, Wingate Mountains, and Florina Station, was sold to the Indigenous Land Corporation, now the Indigenous Land and Sea Corporation, by Alan Myers in 2011.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Fish River Station_sentence_1",
"Fish River Station_sentence_2",
"Fish River Station_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4296,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.026",
"value": "?search="
},
{
"operation": "search",
"time": "15.321",
"value": "Fish River Station"
},
{
"operation": "Now on",
"time": "16.002",
"value": "Fish River Station"
},
{
"operation": "Highlighting",
"time": "21.853",
"value": "Fish River Station_header_cell_0_1_0"
},
{
"operation": "Highlighting deleted",
"time": "28.529",
"value": "Fish River Station_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "38.862",
"value": "Fish River Station_sentence_1"
},
{
"operation": "Highlighting",
"time": "58.255",
"value": "Fish River Station_sentence_2"
},
{
"operation": "Highlighting",
"time": "92.782",
"value": "Fish River Station_sentence_3"
},
{
"operation": "finish",
"time": "126.926",
"value": "finish"
}
]
}
|
exfever_1845
|
Joanne Rowling wrote a seven-volume children's fantasy series that chronicles the life of a young wizard, with the main story arc concerns Harry's struggle against main antagonist in the novels.
|
{
"evidence": [
"J. K. Rowling",
"Harry Potter",
"Lord Voldemort"
],
"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:\nJoanne Rowling wrote a seven-volume children's fantasy series that chronicles the life of a young wizard, with the main story arc concerns Harry's struggle against main antagonist in the novels.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"J. K. Rowling",
"Harry Potter",
"Lord Voldemort"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4297,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5554
|
David Thewlis's other film roles include a 1995 erotic historic drama film based on a 1967 play by a Portuguese-born American playwright, screenwriter, translator, and film director.
|
{
"evidence": [
"David Thewlis",
"Total Eclipse (film)",
"Christopher Hampton"
],
"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:\nDavid Thewlis's other film roles include a 1995 erotic historic drama film based on a 1967 play by a Portuguese-born American playwright, screenwriter, translator, and film director.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"David Thewlis",
"Total Eclipse (film)",
"Christopher Hampton"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4298,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4093
|
Ryan O'Neal landed the role of Rodney Harrington on a prime-time soap opera in which a number of guest stars have appeared; among them was an American actress, television director, and aviator.
|
{
"evidence": [
"Ryan O'Neal",
"Peyton Place (TV series)",
"Susan Oliver"
],
"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:\nRyan O'Neal landed the role of Rodney Harrington on a prime-time soap opera in which a number of guest stars have appeared; among them was an American actress, television director, and aviator.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Ryan O'Neal",
"Peyton Place (TV series)",
"Susan Oliver"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4299,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
68762
|
Lars Hedegaard Andersen toured Namibia in 1998 before touring Zimbabwe with Denmark the following year.
|
{
"evidence": [
"Lars Hedegaard Andersen_sentence_6",
"Lars Hedegaard Andersen_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:\nLars Hedegaard Andersen toured Namibia in 1998 before touring Zimbabwe with Denmark the following year.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Lars Hedegaard Andersen_sentence_6",
"Lars Hedegaard Andersen_sentence_7"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4300,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.237",
"value": "?search="
},
{
"operation": "search",
"time": "10.998",
"value": "Lars Hedegaard"
},
{
"operation": "Now on",
"time": "14.449",
"value": "Lars Hedegaard"
},
{
"operation": "hyperlink",
"time": "32.418",
"value": "Lars Hedegaard Andersen"
},
{
"operation": "Now on",
"time": "34.773",
"value": "Lars Hedegaard Andersen"
},
{
"operation": "Highlighting",
"time": "52.916",
"value": "Lars Hedegaard Andersen_sentence_6"
},
{
"operation": "Highlighting",
"time": "55.053",
"value": "Lars Hedegaard Andersen_sentence_7"
},
{
"operation": "finish",
"time": "75.258",
"value": "finish"
}
]
}
|
51450
|
Earth Island Institute is a non-profit environmental group founded in 1982 by David Brower who was a prominent environmentalist and the founder of many environmental organizations, including the John Muir Institute..
|
{
"evidence": [
"Earth Island Institute_sentence_2",
"David Brower_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:\nEarth Island Institute is a non-profit environmental group founded in 1982 by David Brower who was a prominent environmentalist and the founder of many environmental organizations, including the John Muir Institute..\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Earth Island Institute_sentence_2",
"David Brower_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4301,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.025",
"value": "?search="
},
{
"operation": "search",
"time": "8.505",
"value": "Earth Island Institute"
},
{
"operation": "Now on",
"time": "9.562",
"value": "Earth Island Institute"
},
{
"operation": "Highlighting",
"time": "11.806",
"value": "Earth Island Institute_sentence_2"
},
{
"operation": "hyperlink",
"time": "17.747",
"value": "David Brower"
},
{
"operation": "Now on",
"time": "18.621",
"value": "David Brower"
},
{
"operation": "Highlighting",
"time": "22.809",
"value": "David Brower_sentence_1"
},
{
"operation": "finish",
"time": "41.499",
"value": "finish"
}
]
}
|
26361
|
Photographer Roger Minick created a famous series called "Sightseer" that shows tourists in U.S. National Parks.
|
{
"evidence": [
"Roger Minick_sentence_0",
"Roger Minick_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:\nPhotographer Roger Minick created a famous series called \"Sightseer\" that shows tourists in U.S. National Parks.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Roger Minick_sentence_0",
"Roger Minick_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4302,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.64",
"value": "?search="
},
{
"operation": "search",
"time": "8.25",
"value": "Roger Minick"
},
{
"operation": "Now on",
"time": "9.09",
"value": "Roger Minick"
},
{
"operation": "Page search",
"time": "12.985",
"value": "Sightseer"
},
{
"operation": "Highlighting",
"time": "24.8",
"value": "Roger Minick_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "25.651",
"value": "Roger Minick_sentence_0"
},
{
"operation": "Highlighting",
"time": "26.066",
"value": "Roger Minick_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "27.222",
"value": "Roger Minick_sentence_0"
},
{
"operation": "Highlighting",
"time": "27.722",
"value": "Roger Minick_sentence_0"
},
{
"operation": "Highlighting",
"time": "32.745",
"value": "Roger Minick_sentence_1"
},
{
"operation": "Page search",
"time": "51.621",
"value": "tourists"
},
{
"operation": "Highlighting deleted",
"time": "54.178",
"value": "Roger Minick_sentence_1"
},
{
"operation": "Highlighting",
"time": "55.301",
"value": "Roger Minick_sentence_1"
},
{
"operation": "finish",
"time": "260.164",
"value": "finish"
}
]
}
|
46246
|
After Rossbach, Madame de Pompadour is alleged to have comforted the king with the now-famous: "au reste, après nous, le Déluge" ("Besides, after us, the Deluge") and Italy emerged from the war diminished and virtually bankrupt.
|
{
"evidence": [
"Madame de Pompadour_sentence_56"
],
"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:\nAfter Rossbach, Madame de Pompadour is alleged to have comforted the king with the now-famous: \"au reste, après nous, le Déluge\" (\"Besides, after us, the Deluge\") and Italy emerged from the war diminished and virtually bankrupt.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Madame de Pompadour_sentence_56"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4303,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.64",
"value": "?search="
},
{
"operation": "search",
"time": "21.264",
"value": "Madame de Pompadour"
},
{
"operation": "Now on",
"time": "22.186",
"value": "Madame de Pompadour"
},
{
"operation": "Page search",
"time": "28.741",
"value": "rossbach"
},
{
"operation": "Highlighting",
"time": "35.881",
"value": "Madame de Pompadour_sentence_54"
},
{
"operation": "Highlighting",
"time": "40.588",
"value": "Madame de Pompadour_sentence_55"
},
{
"operation": "Highlighting",
"time": "46.319",
"value": "Madame de Pompadour_sentence_56"
},
{
"operation": "Highlighting deleted",
"time": "55.28",
"value": "Madame de Pompadour_sentence_54"
},
{
"operation": "Highlighting deleted",
"time": "55.653",
"value": "Madame de Pompadour_sentence_55"
},
{
"operation": "Highlighting",
"time": "61.052",
"value": "Madame de Pompadour_sentence_54"
},
{
"operation": "Highlighting",
"time": "61.475",
"value": "Madame de Pompadour_sentence_55"
},
{
"operation": "Highlighting deleted",
"time": "62.947",
"value": "Madame de Pompadour_sentence_54"
},
{
"operation": "Highlighting deleted",
"time": "63.899",
"value": "Madame de Pompadour_sentence_55"
},
{
"operation": "finish",
"time": "67.246",
"value": "finish"
}
]
}
|
45396
|
Jaylen Brown, who would eventually go on to play for the Cleveland Cavaliers in the NBA, averaged 14.6 points, 5.4 rebounds, and 2.0 assists in 27.6 minutes per game over 34 games in his college basketball career at Berkley and had his best scoring games against Richmond and Utah, scoring 27 points in each game.
|
{
"evidence": [
"Jaylen Brown_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:\nJaylen Brown, who would eventually go on to play for the Cleveland Cavaliers in the NBA, averaged 14.6 points, 5.4 rebounds, and 2.0 assists in 27.6 minutes per game over 34 games in his college basketball career at Berkley and had his best scoring games against Richmond and Utah, scoring 27 points in each game.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jaylen Brown_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4304,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.756",
"value": "undefined"
},
{
"operation": "search",
"time": "8.657",
"value": "Jaylen Brown"
},
{
"operation": "Now on",
"time": "9.696",
"value": "Jaylen Brown"
},
{
"operation": "Page search",
"time": "37.127",
"value": "Cleveland Cavaliers"
},
{
"operation": "Highlighting",
"time": "135.14",
"value": "Jaylen Brown_sentence_1"
},
{
"operation": "finish",
"time": "149.387",
"value": "finish"
}
]
}
|
26435
|
Rucheng County (simplified Chinese: 汝城县; traditional Chinese: 汝城縣; pinyin: Rǔchéng Xiàn is a county in Hunan Province, China, it is under the administration of the prefecture-level city of Chenzhou.
|
{
"evidence": [
"Rucheng County_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:\nRucheng County (simplified Chinese: 汝城县; traditional Chinese: 汝城縣; pinyin: Rǔchéng Xiàn is a county in Hunan Province, China, it is under the administration of the prefecture-level city of Chenzhou.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Rucheng County_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4305,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.498",
"value": "?search="
},
{
"operation": "search",
"time": "20.493",
"value": "Rucheng County"
},
{
"operation": "Now on",
"time": "21.838",
"value": "Rucheng County"
},
{
"operation": "Highlighting",
"time": "34.555",
"value": "Rucheng County_sentence_0"
},
{
"operation": "Highlighting",
"time": "75.973",
"value": "Rucheng County_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "82.859",
"value": "Rucheng County_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "83.998",
"value": "Rucheng County_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "84.008",
"value": "Rucheng County_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "84.01",
"value": "Rucheng County_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "86.063",
"value": "Rucheng County_header_cell_0_2_0"
},
{
"operation": "Highlighting",
"time": "87.191",
"value": "Rucheng County_cell_0_2_1"
},
{
"operation": "Highlighting",
"time": "87.195",
"value": "Rucheng County_header_cell_0_2_0"
},
{
"operation": "Highlighting",
"time": "88.899",
"value": "Rucheng County_header_cell_0_3_0"
},
{
"operation": "Highlighting",
"time": "90.064",
"value": "Rucheng County_cell_0_3_1"
},
{
"operation": "Highlighting",
"time": "90.07",
"value": "Rucheng County_header_cell_0_3_0"
},
{
"operation": "finish",
"time": "134.133",
"value": "finish"
}
]
}
|
30685
|
Neshota River is a 17.22-mile-long river near Neshota County Park, manure spill made the quality of the river poor but no landmark was named after it.
|
{
"evidence": [
"Neshota River_sentence_0",
"Neshota River_sentence_3",
"Neshota River_sentence_4"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nNeshota River is a 17.22-mile-long river near Neshota County Park, manure spill made the quality of the river poor but no landmark was named after it.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Neshota River_sentence_0",
"Neshota River_sentence_3",
"Neshota River_sentence_4"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4306,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.828",
"value": "?search="
},
{
"operation": "search",
"time": "12.623",
"value": "Neshota River"
},
{
"operation": "Now on",
"time": "13.567",
"value": "Neshota River"
},
{
"operation": "Highlighting",
"time": "16.907",
"value": "Neshota River_sentence_0"
},
{
"operation": "Highlighting",
"time": "51.572",
"value": "Neshota River_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "57.394",
"value": "Neshota River_sentence_3"
},
{
"operation": "Highlighting",
"time": "61.368",
"value": "Neshota River_sentence_3"
},
{
"operation": "Highlighting",
"time": "92.431",
"value": "Neshota River_sentence_4"
},
{
"operation": "finish",
"time": "167.807",
"value": "finish"
}
]
}
|
2858
|
McSherry's career, as a midfielder, started with Kilmarnock in 1970 where he had 118 appearances for the club and scored 8 goals.
|
{
"evidence": [
"John McSherry_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:\nMcSherry's career, as a midfielder, started with Kilmarnock in 1970 where he had 118 appearances for the club and scored 8 goals.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"John McSherry_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4307,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "11.875",
"value": "McSherry"
},
{
"operation": "hyperlink",
"time": "30.781",
"value": "John McSherry"
},
{
"operation": "search",
"time": "51.438",
"value": "kilmarnock"
},
{
"operation": "hyperlink",
"time": "66.201",
"value": "Kilmarnock F.C."
},
{
"operation": "hyperlink",
"time": "83.482",
"value": "7 Players Kilmarnock F.C._section_9"
},
{
"operation": "hyperlink",
"time": "109.038",
"value": "List of Kilmarnock F.C. seasons"
},
{
"operation": "search",
"time": "166.931",
"value": "kilmarnock F.C. season 1970"
},
{
"operation": "hyperlink",
"time": "173.988",
"value": "Stirling Albion F.C."
},
{
"operation": "hyperlink",
"time": "192.32",
"value": "1.3 The 1970–1980s Stirling Albion F.C._section_3"
},
{
"operation": "Page search",
"time": "205.699",
"value": "mcsherry"
},
{
"operation": "search",
"time": "219.196",
"value": "mcsherry"
},
{
"operation": "search",
"time": "232.555",
"value": "david mcsherry"
},
{
"operation": "back-button-clicked",
"time": "238.985",
"value": "back-button-clicked"
},
{
"operation": "hyperlink",
"time": "275.347",
"value": "John McSherry"
},
{
"operation": "Highlighting",
"time": "277.658",
"value": "John McSherry_sentence_0"
},
{
"operation": "finish",
"time": "291.469",
"value": "finish"
}
]
}
|
40747
|
Krastyo Lazarov was recruited by the pro-Bulgarian Internal Macedonian Revolutionary Organization, and was initially part of the ceta of general Ivan Tsonchev.
|
{
"evidence": [
"Krsta Kovačević_sentence_5",
"Krsta Kovačević_sentence_6"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nKrastyo Lazarov was recruited by the pro-Bulgarian Internal Macedonian Revolutionary Organization, and was initially part of the ceta of general Ivan Tsonchev.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Krsta Kovačević_sentence_5",
"Krsta Kovačević_sentence_6"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4308,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.722",
"value": "?search="
},
{
"operation": "search",
"time": "19.136",
"value": "Krastyo Lazarov"
},
{
"operation": "Now on",
"time": "19.878",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "24.715",
"value": "Krsta Kovačević"
},
{
"operation": "Now on",
"time": "25.423",
"value": "Krsta Kovačević"
},
{
"operation": "back-button-clicked",
"time": "32.518",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "33.113",
"value": "undefined"
},
{
"operation": "search",
"time": "46.546",
"value": "Krastyo Lazarov"
},
{
"operation": "Now on",
"time": "47.222",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "61.663",
"value": "Krsta Kovačević"
},
{
"operation": "Now on",
"time": "62.085",
"value": "Krsta Kovačević"
},
{
"operation": "Page search",
"time": "65.22",
"value": "Krastyo Lazarov"
},
{
"operation": "Page search",
"time": "65.787",
"value": "Krastyo Lazarov"
},
{
"operation": "Page search",
"time": "66.255",
"value": "Krastyo Lazarov"
},
{
"operation": "Page search",
"time": "76.113",
"value": "Krastyo Lazaro"
},
{
"operation": "search",
"time": "114.082",
"value": "pro-Bulgarian Internal Macedonian Revolutionary Organization"
},
{
"operation": "Now on",
"time": "115.932",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "139.283",
"value": "Krsta Kovačević"
},
{
"operation": "Now on",
"time": "139.682",
"value": "Krsta Kovačević"
},
{
"operation": "Page search",
"time": "143.815",
"value": "pro-Bulgarian Internal Macedonian Revolutionary Organization"
},
{
"operation": "Page search",
"time": "162.912",
"value": "recruit"
},
{
"operation": "Highlighting",
"time": "182.255",
"value": "Krsta Kovačević_sentence_5"
},
{
"operation": "Highlighting",
"time": "189.872",
"value": "Krsta Kovačević_sentence_6"
},
{
"operation": "finish",
"time": "224.122",
"value": "finish"
}
]
}
|
exfever_8106
|
Heinrich Luitpold Himmler was Reichsführer of the major paramilitary organization under Adolf Hitler and the Nazi Party in Nazi Germany.
|
{
"evidence": [
"Heinrich Himmler",
"Schutzstaffel"
],
"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:\nHeinrich Luitpold Himmler was Reichsführer of the major paramilitary organization under Adolf Hitler and the Nazi Party in Nazi Germany.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Heinrich Himmler",
"Schutzstaffel"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4309,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
64392
|
Cleveland Pioneer Cemetery is a heritage-listed cemetery which is a burial ground or graveyard is a place where the remains of dead people are buried or otherwise interred.
|
{
"evidence": [
"Cleveland Pioneer Cemetery_sentence_0",
"Cemetery_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:\nCleveland Pioneer Cemetery is a heritage-listed cemetery which is a burial ground or graveyard is a place where the remains of dead people are buried or otherwise interred.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Cleveland Pioneer Cemetery_sentence_0",
"Cemetery_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4310,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.324",
"value": "?search="
},
{
"operation": "search",
"time": "10.671",
"value": "Cleveland Pioneer Cemetery"
},
{
"operation": "Now on",
"time": "13.036",
"value": "Cleveland Pioneer Cemetery"
},
{
"operation": "Highlighting",
"time": "15.094",
"value": "Cleveland Pioneer Cemetery_sentence_0"
},
{
"operation": "hyperlink",
"time": "17.98",
"value": "cemetery"
},
{
"operation": "Now on",
"time": "20.674",
"value": "Cemetery"
},
{
"operation": "Highlighting",
"time": "22.061",
"value": "Cemetery_sentence_1"
},
{
"operation": "finish",
"time": "44.69",
"value": "finish"
}
]
}
|
30172
|
Moore obtained a sponsorship from S&W Foods that brought notoriety to the otherwise sleepy Central Valley town; and yet when S&W dropped its sponsorship, Moore found a new sponsor in another company.
|
{
"evidence": [
"Modesto Relays_sentence_13",
"Modesto Relays_sentence_14"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMoore obtained a sponsorship from S&W Foods that brought notoriety to the otherwise sleepy Central Valley town; and yet when S&W dropped its sponsorship, Moore found a new sponsor in another company.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Modesto Relays_sentence_13",
"Modesto Relays_sentence_14"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4311,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.172",
"value": "?search="
},
{
"operation": "search",
"time": "7.924",
"value": "Moore"
},
{
"operation": "Now on",
"time": "8.522",
"value": "Moore"
},
{
"operation": "Page search",
"time": "100.773",
"value": "sponsorship"
},
{
"operation": "search",
"time": "118.823",
"value": "Moore obtained a sponsorship from S&W Foods"
},
{
"operation": "Now on",
"time": "121.11",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "137.047",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "137.128",
"value": "Moore"
},
{
"operation": "hyperlink",
"time": "161.529",
"value": "List of people with surname Moore"
},
{
"operation": "Now on",
"time": "162.254",
"value": "List of people with surname Moore"
},
{
"operation": "search",
"time": "181.384",
"value": "Contains...Moore obtained a sponsorship from S&W Foods that brought notoriety to the otherwise sleepy Central Valley town"
},
{
"operation": "Now on",
"time": "182.9",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "186.178",
"value": "Modesto Relays"
},
{
"operation": "Now on",
"time": "186.768",
"value": "Modesto Relays"
},
{
"operation": "Page search",
"time": "193.277",
"value": "sponsorship"
},
{
"operation": "Highlighting",
"time": "199.749",
"value": "Modesto Relays_sentence_13"
},
{
"operation": "Highlighting",
"time": "207.553",
"value": "Modesto Relays_sentence_14"
},
{
"operation": "finish",
"time": "256.386",
"value": "finish"
}
]
}
|
70440
|
There are at least 100 species of Jovellana that are cultivated as ornamental garden plants, and they are frost-hardy down to −100 °C, but in cultivation, they require constant running water.
|
{
"evidence": [
"Jovellana_sentence_14",
"Jovellana_sentence_15"
],
"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:\nThere are at least 100 species of Jovellana that are cultivated as ornamental garden plants, and they are frost-hardy down to −100 °C, but in cultivation, they require constant running water.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jovellana_sentence_14",
"Jovellana_sentence_15"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4312,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.766",
"value": "?search="
},
{
"operation": "search",
"time": "9.506",
"value": "Jovellana"
},
{
"operation": "Now on",
"time": "10.247",
"value": "Jovellana"
},
{
"operation": "Highlighting",
"time": "27.252",
"value": "Jovellana_sentence_14"
},
{
"operation": "Highlighting",
"time": "37.323",
"value": "Jovellana_sentence_15"
},
{
"operation": "finish",
"time": "53.531",
"value": "finish"
}
]
}
|
36366
|
Sonny Gallant has worked in the Legislative Assembly of Prince Edward Island, Executive Council of Prince Edward Island, which is usually made up of members of the Legislative Assembly, and as interim leader of the Republican Party.
|
{
"evidence": [
"Sonny Gallant_sentence_4"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSonny Gallant has worked in the Legislative Assembly of Prince Edward Island, Executive Council of Prince Edward Island, which is usually made up of members of the Legislative Assembly, and as interim leader of the Republican Party.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Sonny Gallant_sentence_4"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4313,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.904",
"value": "undefined"
},
{
"operation": "search",
"time": "15.008",
"value": "Sonny Gallant"
},
{
"operation": "Now on",
"time": "16.26",
"value": "Sonny Gallant"
},
{
"operation": "Highlighting",
"time": "53.394",
"value": "Sonny Gallant_sentence_1"
},
{
"operation": "Highlighting",
"time": "59.88",
"value": "Sonny Gallant_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "60.936",
"value": "Sonny Gallant_sentence_1"
},
{
"operation": "finish",
"time": "72.617",
"value": "finish"
}
]
}
|
80325
|
SR-20, a state highway in southern Utah, begins at I-15, Exit 95, 14 miles (23 km) north of Paragonah, heads east and southeast through a pass between the Markagunt Plateau and the Tushar Mountains, and ends at an intersection with US-89 at Bear Valley Junction.
|
{
"evidence": [
"Utah State Route 20_sentence_0",
"Utah State Route 20_sentence_4",
"Utah State Route 20_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:\nSR-20, a state highway in southern Utah, begins at I-15, Exit 95, 14 miles (23 km) north of Paragonah, heads east and southeast through a pass between the Markagunt Plateau and the Tushar Mountains, and ends at an intersection with US-89 at Bear Valley Junction.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Utah State Route 20_sentence_0",
"Utah State Route 20_sentence_4",
"Utah State Route 20_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4314,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.841",
"value": "?search="
},
{
"operation": "search",
"time": "10.614",
"value": "SR-20"
},
{
"operation": "Now on",
"time": "12.606",
"value": "SR-20"
},
{
"operation": "hyperlink",
"time": "21.835",
"value": "List of highways numbered 20"
},
{
"operation": "Now on",
"time": "22.652",
"value": "List of highways numbered 20"
},
{
"operation": "hyperlink",
"time": "29.129",
"value": "15 United States List of highways numbered 20_section_14"
},
{
"operation": "hyperlink",
"time": "35.424",
"value": "Utah State Route 20"
},
{
"operation": "Now on",
"time": "35.746",
"value": "Utah State Route 20"
},
{
"operation": "Highlighting",
"time": "39.573",
"value": "Utah State Route 20_sentence_0"
},
{
"operation": "Highlighting",
"time": "61.536",
"value": "Utah State Route 20_sentence_4"
},
{
"operation": "Highlighting",
"time": "66.851",
"value": "Utah State Route 20_sentence_5"
},
{
"operation": "finish",
"time": "94.348",
"value": "finish"
}
]
}
|
65102
|
The Album How to Stop Your Brain in an Accident is by Future of the Left, a Welsh alternative rock band based in Cardiff.
|
{
"evidence": [
"How to Stop Your Brain in an Accident_sentence_0",
"Future of the Left_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 Album How to Stop Your Brain in an Accident is by Future of the Left, a Welsh alternative rock band based in Cardiff.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"How to Stop Your Brain in an Accident_sentence_0",
"Future of the Left_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4315,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.011",
"value": "?search="
},
{
"operation": "search",
"time": "13.639",
"value": "How to Stop Your Brain in an Accident"
},
{
"operation": "Now on",
"time": "14.654",
"value": "How to Stop Your Brain in an Accident"
},
{
"operation": "Highlighting",
"time": "20.818",
"value": "How to Stop Your Brain in an Accident_sentence_0"
},
{
"operation": "hyperlink",
"time": "25.01",
"value": "Future of the Left"
},
{
"operation": "Now on",
"time": "30.358",
"value": "Future of the Left"
},
{
"operation": "Highlighting",
"time": "31.834",
"value": "Future of the Left_sentence_0"
},
{
"operation": "finish",
"time": "63.364",
"value": "finish"
}
]
}
|
exfever_7722
|
Gone with the Wind is a 1939 American epic historical romance film produced by David O. Selznick and directed by the American film director, cinematographer, and producer best known for his movie The Wizard of Oz.
|
{
"evidence": [
"Gone with the Wind (film)",
"Victor Fleming"
],
"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:\nGone with the Wind is a 1939 American epic historical romance film produced by David O. Selznick and directed by the American film director, cinematographer, and producer best known for his movie The Wizard of Oz.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Gone with the Wind (film)",
"Victor Fleming"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4316,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
40157
|
Jake Thompson pitched for the Lehigh Valley IronPigs in 2016 and won the International League Most Valuable Pitcher Award, an annual award given to the best pitcher in Minor League Baseball's International League.
|
{
"evidence": [
"Jake Thompson_sentence_22",
"Jake Thompson_sentence_24",
"International League Most Valuable Pitcher Award_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:\nJake Thompson pitched for the Lehigh Valley IronPigs in 2016 and won the International League Most Valuable Pitcher Award, an annual award given to the best pitcher in Minor League Baseball's International League.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Jake Thompson_sentence_22",
"Jake Thompson_sentence_24",
"International League Most Valuable Pitcher Award_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4317,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.78",
"value": "?search="
},
{
"operation": "search",
"time": "54.187",
"value": "Jake Thompson"
},
{
"operation": "Now on",
"time": "54.963",
"value": "Jake Thompson"
},
{
"operation": "Page search",
"time": "66.686",
"value": "Lehigh Valley IronPigs"
},
{
"operation": "Highlighting",
"time": "71.726",
"value": "Jake Thompson_sentence_22"
},
{
"operation": "Highlighting",
"time": "90.917",
"value": "Jake Thompson_sentence_24"
},
{
"operation": "hyperlink",
"time": "95.965",
"value": "International League Most Valuable Pitcher Award"
},
{
"operation": "Now on",
"time": "96.786",
"value": "International League Most Valuable Pitcher Award"
},
{
"operation": "Highlighting",
"time": "100.216",
"value": "International League Most Valuable Pitcher Award_sentence_0"
},
{
"operation": "finish",
"time": "113.547",
"value": "finish"
}
]
}
|
35825
|
Utah State Route 158 has four exits in mile 0, 3.778, 4.337, and 21.691 all of which are in the entire Weber County, Utah's fourth-most populous county.
|
{
"evidence": [
"Weber County, Utah_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:\nUtah State Route 158 has four exits in mile 0, 3.778, 4.337, and 21.691 all of which are in the entire Weber County, Utah's fourth-most populous county.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Weber County, Utah_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4318,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.743",
"value": "?search="
},
{
"operation": "search",
"time": "38.706",
"value": "Utah State Route 158"
},
{
"operation": "Now on",
"time": "39.711",
"value": "Utah State Route 158"
},
{
"operation": "Page search",
"time": "56.957",
"value": "0, 3.778, 4.337"
},
{
"operation": "Page search",
"time": "81.577",
"value": "exit"
},
{
"operation": "Page search",
"time": "82.764",
"value": "exit"
},
{
"operation": "search",
"time": "146.964",
"value": "\"Utah State Route 158\" \"0, 3.778, 4.337\" \""
},
{
"operation": "Now on",
"time": "148.44",
"value": "undefined"
},
{
"operation": "search",
"time": "197.131",
"value": "\"21.691\" \"Utah State Route 158\" \"0, 3.778, 4.337\" \"Weber County\""
},
{
"operation": "Now on",
"time": "198.148",
"value": "undefined"
},
{
"operation": "search",
"time": "202.395",
"value": "Weber County"
},
{
"operation": "Now on",
"time": "203.71",
"value": "Weber County"
},
{
"operation": "hyperlink",
"time": "207.664",
"value": "Weber County, Utah"
},
{
"operation": "Now on",
"time": "208.729",
"value": "Weber County, Utah"
},
{
"operation": "Highlighting",
"time": "217.71",
"value": "Weber County, Utah_sentence_2"
},
{
"operation": "Page search",
"time": "242.8",
"value": "158"
},
{
"operation": "search",
"time": "307.796",
"value": "\"Utah State Route 158\" \"0, 3.778, 4.337\""
},
{
"operation": "Now on",
"time": "309.197",
"value": "undefined"
},
{
"operation": "search",
"time": "322.671",
"value": "mile 0, 3.778, 4.337"
},
{
"operation": "Now on",
"time": "327.21",
"value": "undefined"
},
{
"operation": "search",
"time": "386.365",
"value": "\"utah\" \"21.691\""
},
{
"operation": "Now on",
"time": "387.299",
"value": "undefined"
},
{
"operation": "search",
"time": "412.202",
"value": "Utah State Route 158"
},
{
"operation": "Now on",
"time": "413.186",
"value": "Utah State Route 158"
},
{
"operation": "Page search",
"time": "422.571",
"value": "exit"
},
{
"operation": "hyperlink",
"time": "514.991",
"value": "Utah State Route 158 (1933-1969)"
},
{
"operation": "Now on",
"time": "517.817",
"value": "List of Utah State Routes deleted in 1969"
},
{
"operation": "Page search",
"time": "522.203",
"value": "exit"
},
{
"operation": "Page search",
"time": "545.796",
"value": "0, 3.778, 4.337"
},
{
"operation": "Page search",
"time": "632.776",
"value": "21.691"
},
{
"operation": "Page search",
"time": "699.572",
"value": "exit"
},
{
"operation": "search",
"time": "759.737",
"value": "mile 0, 3.778, 4.337"
},
{
"operation": "Now on",
"time": "761.198",
"value": "undefined"
},
{
"operation": "finish",
"time": "817.316",
"value": "finish"
}
]
}
|
exfever_8742
|
The atom is the basic structural and functional unit of life forms that consists of all material within a eukaryotic cell except the cell nucleus.
|
{
"evidence": [
"Cell (biology)",
"Cytoplasm"
],
"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 atom is the basic structural and functional unit of life forms that consists of all material within a eukaryotic cell except the cell nucleus.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Cell (biology)",
"Cytoplasm"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4319,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2921
|
Steven George Gerrard is an English professional football manager and former player, who manages an English professional football club that played since 1897 at their home ground in a football stadium in Aston, Birmingham, California.
|
{
"evidence": [
"Steven Gerrard",
"Aston Villa F.C.",
"Villa Park"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSteven George Gerrard is an English professional football manager and former player, who manages an English professional football club that played since 1897 at their home ground in a football stadium in Aston, Birmingham, California.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Steven Gerrard",
"Aston Villa F.C.",
"Villa Park"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4320,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3266
|
Life After Death is The Notorious B.I.G.'s second and final studio album, released as an audio album that spans two units of the primary medium in which it is sold sixteen days after his death.
|
{
"evidence": [
"Life After Death",
"Double 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:\nLife After Death is The Notorious B.I.G.'s second and final studio album, released as an audio album that spans two units of the primary medium in which it is sold sixteen days after his death.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Life After Death",
"Double album"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4321,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1966
|
Marvel's Iron Fist is an American television series set in the shared universe centered on a series of superhero films in an American collection of related media in which several derivative works have been produced from an original creative work of fiction.
|
{
"evidence": [
"Iron Fist (TV series)",
"Marvel Cinematic Universe",
"Media franchise"
],
"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:\nMarvel's Iron Fist is an American television series set in the shared universe centered on a series of superhero films in an American collection of related media in which several derivative works have been produced from an original creative work of fiction.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Iron Fist (TV series)",
"Marvel Cinematic Universe",
"Media franchise"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4322,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
29422
|
Taxation in the Republic of Ireland has a standard rate of 0.5% for those with an income of up to Up to €19,372.00.
|
{
"evidence": [
"Taxation in the Republic of Ireland_sentence_57"
],
"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:\nTaxation in the Republic of Ireland has a standard rate of 0.5% for those with an income of up to Up to €19,372.00.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Taxation in the Republic of Ireland_sentence_57"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4323,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.975",
"value": "?search="
},
{
"operation": "search",
"time": "20.998",
"value": "Taxation in the Republic of Ireland"
},
{
"operation": "Now on",
"time": "23.663",
"value": "Taxation in the Republic of Ireland"
},
{
"operation": "Highlighting",
"time": "714.604",
"value": "Taxation in the Republic of Ireland_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "717.28",
"value": "Taxation in the Republic of Ireland_sentence_1"
},
{
"operation": "Page search",
"time": "724.479",
"value": "standard rate"
},
{
"operation": "Highlighting",
"time": "747.073",
"value": "Taxation in the Republic of Ireland_sentence_57"
},
{
"operation": "finish",
"time": "752.858",
"value": "finish"
}
]
}
|
30238
|
Jérémy Perbet moved to Belgian Pro League side Tubize in 2008 before moving with Lokeren in 2010.
|
{
"evidence": [
"Jérémy Perbet_sentence_17",
"Jérémy Perbet_sentence_19"
],
"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:\nJérémy Perbet moved to Belgian Pro League side Tubize in 2008 before moving with Lokeren in 2010.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jérémy Perbet_sentence_17",
"Jérémy Perbet_sentence_19"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4324,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.898",
"value": "?search="
},
{
"operation": "search",
"time": "17.106",
"value": "Jérémy Perbet"
},
{
"operation": "Now on",
"time": "18.955",
"value": "Jérémy Perbet"
},
{
"operation": "Highlighting",
"time": "28.021",
"value": "Jérémy Perbet_table_caption_0"
},
{
"operation": "Highlighting deleted",
"time": "36.059",
"value": "Jérémy Perbet_table_caption_0"
},
{
"operation": "Page search",
"time": "41.109",
"value": "belgian pro"
},
{
"operation": "Highlighting",
"time": "47.424",
"value": "Jérémy Perbet_sentence_17"
},
{
"operation": "Highlighting",
"time": "65.962",
"value": "Jérémy Perbet_sentence_19"
},
{
"operation": "finish",
"time": "72.866",
"value": "finish"
}
]
}
|
29737
|
Three years after defeating Horrace Herring in the 1938 election, Arthur Grigg was killed in the midst of World War II.
|
{
"evidence": [
"Arthur Grigg_sentence_5",
"Arthur Grigg_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:\nThree years after defeating Horrace Herring in the 1938 election, Arthur Grigg was killed in the midst of World War II.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Arthur Grigg_sentence_5",
"Arthur Grigg_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4325,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.072",
"value": "?search="
},
{
"operation": "search",
"time": "13.483",
"value": "Arthur Grigg"
},
{
"operation": "Now on",
"time": "14.153",
"value": "Arthur Grigg"
},
{
"operation": "Page search",
"time": "25.203",
"value": "horrace herring"
},
{
"operation": "Page search",
"time": "36.062",
"value": "1938"
},
{
"operation": "Highlighting",
"time": "41.915",
"value": "Arthur Grigg_sentence_5"
},
{
"operation": "Highlighting",
"time": "59.272",
"value": "Arthur Grigg_sentence_0"
},
{
"operation": "Highlighting",
"time": "69.095",
"value": "Arthur Grigg_sentence_6"
},
{
"operation": "Highlighting deleted",
"time": "71.581",
"value": "Arthur Grigg_sentence_0"
},
{
"operation": "finish",
"time": "90.77",
"value": "finish"
}
]
}
|
45611
|
Paulo Wanchope is a Costa Rican former footballer and former Head Coach of the Costa Rica national football team which represents Costa Rica in men's international football.
|
{
"evidence": [
"Paulo Wanchope_sentence_1",
"Costa Rica national football team_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:\nPaulo Wanchope is a Costa Rican former footballer and former Head Coach of the Costa Rica national football team which represents Costa Rica in men's international football.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Paulo Wanchope_sentence_1",
"Costa Rica national football team_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4326,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.108",
"value": "?search="
},
{
"operation": "search",
"time": "20.894",
"value": "Paulo Wanchope"
},
{
"operation": "Now on",
"time": "22.816",
"value": "Paulo Wanchope"
},
{
"operation": "Highlighting",
"time": "47.612",
"value": "Paulo Wanchope_sentence_1"
},
{
"operation": "hyperlink",
"time": "57.481",
"value": "Costa Rica national football team"
},
{
"operation": "Now on",
"time": "61.653",
"value": "Costa Rica national football team"
},
{
"operation": "Highlighting",
"time": "63.252",
"value": "Costa Rica national football team_sentence_2"
},
{
"operation": "finish",
"time": "87.79",
"value": "finish"
}
]
}
|
50541
|
Josephine Uwineza managed a Chinese restaurant for 10 years before becoming a member of the Peace Through Business program
|
{
"evidence": [
"Josephine Uwineza_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:\nJosephine Uwineza managed a Chinese restaurant for 10 years before becoming a member of the Peace Through Business program\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Josephine Uwineza_sentence_7"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4327,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.783",
"value": "?search="
},
{
"operation": "search",
"time": "72.353",
"value": "Josephine Uwineza"
},
{
"operation": "Now on",
"time": "73.283",
"value": "Josephine Uwineza"
},
{
"operation": "Highlighting",
"time": "122.514",
"value": "Josephine Uwineza_sentence_7"
},
{
"operation": "finish",
"time": "137.729",
"value": "finish"
}
]
}
|
57676
|
CD99 is expressed on all leukocytes but highest on thymocytes and is believed to augment T-cell adhesion and apoptosis of double positive T cells, and has been found in endothelial cells and in the periodontium, including gingival fibroblasts and gingival epithelial cells, as well as participates in migration and activation.
|
{
"evidence": [
"CD99_sentence_3",
"CD99_sentence_4",
"CD99_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:\nCD99 is expressed on all leukocytes but highest on thymocytes and is believed to augment T-cell adhesion and apoptosis of double positive T cells, and has been found in endothelial cells and in the periodontium, including gingival fibroblasts and gingival epithelial cells, as well as participates in migration and activation.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"CD99_sentence_3",
"CD99_sentence_4",
"CD99_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4328,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.053",
"value": "?search="
},
{
"operation": "search",
"time": "16.558",
"value": "CD99"
},
{
"operation": "Now on",
"time": "17.339",
"value": "CD99"
},
{
"operation": "Highlighting",
"time": "114.546",
"value": "CD99_sentence_3"
},
{
"operation": "Highlighting",
"time": "118.308",
"value": "CD99_sentence_4"
},
{
"operation": "Highlighting",
"time": "119.411",
"value": "CD99_sentence_5"
},
{
"operation": "finish",
"time": "269.101",
"value": "finish"
}
]
}
|
3980
|
Dekker, who wrote his first pamphlet in 1603, was not the only one to view the outbreak of plague as a divine consequence of Elizabeth's death and recalls the widespread lamentation at her death and includes in his work some of the epigrams written for her funeral at Whitehall.
|
{
"evidence": [
"The Wonderfull Yeare_sentence_0",
"The Wonderfull Yeare_sentence_10",
"The Wonderfull Yeare_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:\nDekker, who wrote his first pamphlet in 1603, was not the only one to view the outbreak of plague as a divine consequence of Elizabeth's death and recalls the widespread lamentation at her death and includes in his work some of the epigrams written for her funeral at Whitehall.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"The Wonderfull Yeare_sentence_0",
"The Wonderfull Yeare_sentence_10",
"The Wonderfull Yeare_sentence_9"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4329,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "21.238",
"value": "Dekker"
},
{
"operation": "Highlighting",
"time": "70.803",
"value": "Dekker_item_0_52"
},
{
"operation": "Highlighting",
"time": "70.811",
"value": "Dekker_title"
},
{
"operation": "hyperlink",
"time": "75.313",
"value": "Thomas Dekker (writer)"
},
{
"operation": "Highlighting",
"time": "185.647",
"value": "Thomas Dekker (writer)_sentence_68"
},
{
"operation": "Highlighting",
"time": "185.652",
"value": "Thomas Dekker (writer)_title"
},
{
"operation": "Highlighting",
"time": "185.659",
"value": "Thomas Dekker (writer)_section_5"
},
{
"operation": "Highlighting",
"time": "185.664",
"value": "Thomas Dekker (writer)_section_7"
},
{
"operation": "hyperlink",
"time": "215.701",
"value": "The Wonderfull Yeare"
},
{
"operation": "Highlighting",
"time": "223.958",
"value": "The Wonderfull Yeare_sentence_0"
},
{
"operation": "Highlighting",
"time": "263.358",
"value": "The Wonderfull Yeare_sentence_10"
},
{
"operation": "Highlighting",
"time": "281.911",
"value": "The Wonderfull Yeare_sentence_9"
},
{
"operation": "finish",
"time": "347.449",
"value": "finish"
}
]
}
|
exfever_6025
|
Melanie Griffith, in Arthur Penn's neo-noir film Night Moves, appeared opposite an actor that was nominated for Best Supporting Actor came with a 1961 American biographical crime film.
|
{
"evidence": [
"Melanie Griffith",
"Gene Hackman",
"Bonnie and Clyde (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:\nMelanie Griffith, in Arthur Penn's neo-noir film Night Moves, appeared opposite an actor that was nominated for Best Supporting Actor came with a 1961 American biographical crime film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Melanie Griffith",
"Gene Hackman",
"Bonnie and Clyde (film)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4330,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_145
|
Saving Private Ryan is a 1990 American war film whose genre of filmmaking is with large-scale, sweeping scope and spectacle, directed by Steven Spielberg.
|
{
"evidence": [
"Saving Private Ryan",
"Epic 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:\nSaving Private Ryan is a 1990 American war film whose genre of filmmaking is with large-scale, sweeping scope and spectacle, directed by Steven Spielberg.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Saving Private Ryan",
"Epic film"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4331,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
69256
|
Devon Martinus is a South African rugby union player for Griquas which is a South African rugby union team that participates in the annual Currie Cup tournament.
|
{
"evidence": [
"Devon Martinus_sentence_0",
"Griquas (rugby)_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:\nDevon Martinus is a South African rugby union player for Griquas which is a South African rugby union team that participates in the annual Currie Cup tournament.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Devon Martinus_sentence_0",
"Griquas (rugby)_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4332,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.622",
"value": "?search="
},
{
"operation": "search",
"time": "22.475",
"value": "Devon Martinus"
},
{
"operation": "Now on",
"time": "23.037",
"value": "Devon Martinus"
},
{
"operation": "Highlighting",
"time": "34.771",
"value": "Devon Martinus_sentence_0"
},
{
"operation": "hyperlink",
"time": "39.107",
"value": "Griquas"
},
{
"operation": "Now on",
"time": "39.632",
"value": "Griquas (rugby)"
},
{
"operation": "Highlighting",
"time": "42.523",
"value": "Griquas (rugby)_sentence_0"
},
{
"operation": "finish",
"time": "65.034",
"value": "finish"
}
]
}
|
37559
|
The plot of Kung Fu Dunk, directed by Taiwanese director Kevin Chu (born December 1950), includes the character Li convincing Shi-jie to help them make some money for themselves, so they go to a casino owned by one of Wang Li's old friend's son, Brother Hu before eating.
|
{
"evidence": [
"Kung Fu Dunk_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:\nThe plot of Kung Fu Dunk, directed by Taiwanese director Kevin Chu (born December 1950), includes the character Li convincing Shi-jie to help them make some money for themselves, so they go to a casino owned by one of Wang Li's old friend's son, Brother Hu before eating.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Kung Fu Dunk_sentence_13"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4333,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.65",
"value": "?search="
},
{
"operation": "search",
"time": "6.155",
"value": "Kung Fu Dunk"
},
{
"operation": "Now on",
"time": "7.001",
"value": "Kung Fu Dunk"
},
{
"operation": "Page search",
"time": "14.968",
"value": "direc"
},
{
"operation": "Highlighting",
"time": "17.451",
"value": "Kung Fu Dunk_sentence_1"
},
{
"operation": "hyperlink",
"time": "20.541",
"value": "Kevin Chu"
},
{
"operation": "Now on",
"time": "21.211",
"value": "Kevin Chu"
},
{
"operation": "Highlighting",
"time": "22.597",
"value": "Kevin Chu_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "22.597",
"value": "Kevin Chu_title"
},
{
"operation": "Highlighting",
"time": "22.599",
"value": "Kevin Chu_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "22.599",
"value": "Kevin Chu_header_cell_0_0_0"
},
{
"operation": "back-button-clicked",
"time": "23.182",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "23.258",
"value": "Kung Fu Dunk"
},
{
"operation": "Page search",
"time": "32.199",
"value": "convincing Shi-jie"
},
{
"operation": "Page search",
"time": "36.051",
"value": "Shi-jie"
},
{
"operation": "Page search",
"time": "36.3",
"value": "Shi-jie"
},
{
"operation": "Page search",
"time": "44.011",
"value": "convin"
},
{
"operation": "Highlighting",
"time": "47.162",
"value": "Kung Fu Dunk_sentence_12"
},
{
"operation": "Highlighting",
"time": "54.398",
"value": "Kung Fu Dunk_sentence_13"
},
{
"operation": "Highlighting deleted",
"time": "80.841",
"value": "Kung Fu Dunk_sentence_12"
},
{
"operation": "Highlighting deleted",
"time": "81.876",
"value": "Kung Fu Dunk_sentence_1"
},
{
"operation": "finish",
"time": "86.739",
"value": "finish"
}
]
}
|
exfever_7384
|
The Caracazo is the name given to the wave of protests, riots, and looting that started on February 27, 1979, in a city in Miranda, Venezuela that was established in 1621 as Nuestra Senora de Copacabana de Los Guarenas.
|
{
"evidence": [
"Caracazo",
"Guarenas"
],
"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 Caracazo is the name given to the wave of protests, riots, and looting that started on February 27, 1979, in a city in Miranda, Venezuela that was established in 1621 as Nuestra Senora de Copacabana de Los Guarenas.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Caracazo",
"Guarenas"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4334,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2992
|
live-action animation is the most common film adaptation method used by the Americans,
|
{
"evidence": [
"James and the Giant Peach (film)",
"Stop motion"
],
"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:\nlive-action animation is the most common film adaptation method used by the Americans,\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"James and the Giant Peach (film)",
"Stop motion"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4335,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_499
|
Vantage Point is a 2008 American political action film that attempts to kill the head of the government of the United States of America.
|
{
"evidence": [
"Vantage Point (film)",
"President of the United States"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nVantage Point is a 2008 American political action film that attempts to kill the head of the government of the United States of America.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Vantage Point (film)",
"President of the United States"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4336,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1630
|
Dumb and Dumber is a 1994 American buddy comedy film starring a Canadian and American actor and comedian known for his energetic slapstick performances.
|
{
"evidence": [
"Dumb and Dumber",
"Jim Carrey"
],
"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:\nDumb and Dumber is a 1994 American buddy comedy film starring a Canadian and American actor and comedian known for his energetic slapstick performances.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Dumb and Dumber",
"Jim Carrey"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4337,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
72664
|
Ratu Atut Chosiyah is a current governor of the province of Banten, Indonesia who was suspended from office in 2014.
|
{
"evidence": [
"Ratu Atut Chosiyah_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:\nRatu Atut Chosiyah is a current governor of the province of Banten, Indonesia who was suspended from office in 2014.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Ratu Atut Chosiyah_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4338,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "3.401",
"value": "?search="
},
{
"operation": "search",
"time": "105.806",
"value": "Ratu Atut Chosiyah"
},
{
"operation": "Now on",
"time": "107.44",
"value": "Ratu Atut Chosiyah"
},
{
"operation": "Highlighting",
"time": "132.012",
"value": "Ratu Atut Chosiyah_sentence_0"
},
{
"operation": "finish",
"time": "195.627",
"value": "finish"
}
]
}
|
75997
|
Rolfe (born on October 15, 1859 in Newburyport, Massachusetts) graduated from Harvard University in 1881 and from Cornell University (Ph.D.) in 1885; then he taught at Cornell (1882–1885), and at Harvard (1889–1890).
|
{
"evidence": [
"John Carew Rolfe_sentence_0",
"John Carew Rolfe_sentence_1",
"John Carew Rolfe_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:\nRolfe (born on October 15, 1859 in Newburyport, Massachusetts) graduated from Harvard University in 1881 and from Cornell University (Ph.D.) in 1885; then he taught at Cornell (1882–1885), and at Harvard (1889–1890).\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"John Carew Rolfe_sentence_0",
"John Carew Rolfe_sentence_1",
"John Carew Rolfe_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4339,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.995",
"value": "?search="
},
{
"operation": "search",
"time": "21.013",
"value": "Rolfe"
},
{
"operation": "Now on",
"time": "21.725",
"value": "Rolfe"
},
{
"operation": "hyperlink",
"time": "50.147",
"value": "Rolfe (surname)"
},
{
"operation": "Now on",
"time": "50.541",
"value": "Rolfe (surname)"
},
{
"operation": "Page search",
"time": "58.219",
"value": "1859"
},
{
"operation": "hyperlink",
"time": "89.548",
"value": "Thomas Rolfe"
},
{
"operation": "Now on",
"time": "89.963",
"value": "Thomas Rolfe"
},
{
"operation": "search",
"time": "99.676",
"value": "rolfe 1859"
},
{
"operation": "Now on",
"time": "100.961",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "103.684",
"value": "John Rolfe (disambiguation)"
},
{
"operation": "Now on",
"time": "104.108",
"value": "John Rolfe (disambiguation)"
},
{
"operation": "hyperlink",
"time": "114.987",
"value": "John Rolfe"
},
{
"operation": "Now on",
"time": "115.41",
"value": "John Rolfe"
},
{
"operation": "search",
"time": "127.324",
"value": "rolfe 1859"
},
{
"operation": "Now on",
"time": "127.801",
"value": "undefined"
},
{
"operation": "search",
"time": "141.787",
"value": "John Carew Rolfe"
},
{
"operation": "Now on",
"time": "142.304",
"value": "John Carew Rolfe"
},
{
"operation": "Highlighting",
"time": "144.708",
"value": "John Carew Rolfe_sentence_0"
},
{
"operation": "Highlighting",
"time": "152.819",
"value": "John Carew Rolfe_sentence_1"
},
{
"operation": "Highlighting",
"time": "158.57",
"value": "John Carew Rolfe_sentence_2"
},
{
"operation": "finish",
"time": "184.859",
"value": "finish"
}
]
}
|
exfever_927
|
"Titanium" is a song by French DJ and music producer David Guetta taken from the Guettas's fifth studio album released on 26 August 2021.
|
{
"evidence": [
"Titanium (song)",
"Nothing but the Beat"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\n\"Titanium\" is a song by French DJ and music producer David Guetta taken from the Guettas's fifth studio album released on 26 August 2021.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Titanium (song)",
"Nothing but the Beat"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4340,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
22465
|
The 2007 World Port Tournament was an international football competition and the 17th edition of the tournament in which Brazil lost the tournament with a 2-0 defeat against Germany in the championship game.
|
{
"evidence": [
"2007 World Port Tournament_sentence_0",
"2007 World Port Tournament_sentence_1",
"2007 World Port Tournament_sentence_2"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe 2007 World Port Tournament was an international football competition and the 17th edition of the tournament in which Brazil lost the tournament with a 2-0 defeat against Germany in the championship game.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"2007 World Port Tournament_sentence_0",
"2007 World Port Tournament_sentence_1",
"2007 World Port Tournament_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4341,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.294",
"value": "?search="
},
{
"operation": "search",
"time": "20.801",
"value": "2007 World Port Tournament"
},
{
"operation": "Now on",
"time": "22.976",
"value": "2007 World Port Tournament"
},
{
"operation": "Highlighting",
"time": "29.261",
"value": "2007 World Port Tournament_sentence_0"
},
{
"operation": "Highlighting",
"time": "50.171",
"value": "2007 World Port Tournament_sentence_1"
},
{
"operation": "Highlighting",
"time": "68.323",
"value": "2007 World Port Tournament_sentence_2"
},
{
"operation": "finish",
"time": "85.203",
"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": 4342,
"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"
}
]
}
|
20454
|
Vogt joined the British Pharmacological Society and began work with Sir Henry Dale and Wilhelm Feldberg in 1936 at the National Institute for Medical Research, London.
|
{
"evidence": [
"British Journal of Pharmacology_sentence_0",
"Henry Hallett Dale_sentence_0",
"Henry Hallett Dale_sentence_9",
"Wilhelm Feldberg_sentence_0",
"Wilhelm Feldberg_sentence_5",
"Wilhelm Feldberg_sentence_13",
"Wilhelm Feldberg_sentence_16"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nVogt joined the British Pharmacological Society and began work with Sir Henry Dale and Wilhelm Feldberg in 1936 at the National Institute for Medical Research, London.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"British Journal of Pharmacology_sentence_0",
"Henry Hallett Dale_sentence_0",
"Henry Hallett Dale_sentence_9",
"Wilhelm Feldberg_sentence_0",
"Wilhelm Feldberg_sentence_5",
"Wilhelm Feldberg_sentence_13",
"Wilhelm Feldberg_sentence_16"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4343,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.813",
"value": "?search="
},
{
"operation": "search",
"time": "44.126",
"value": "Vogt"
},
{
"operation": "Now on",
"time": "45.292",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "49.803",
"value": "A. E. van Vogt"
},
{
"operation": "Now on",
"time": "51.178",
"value": "A. E. van Vogt"
},
{
"operation": "back-button-clicked",
"time": "58.596",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "59.424",
"value": "undefined"
},
{
"operation": "search",
"time": "85.897",
"value": "National Institute for Medical Research, London."
},
{
"operation": "Now on",
"time": "88.1",
"value": "undefined"
},
{
"operation": "search",
"time": "105.808",
"value": "National Institute for Medical Research"
},
{
"operation": "Now on",
"time": "106.984",
"value": "National Institute for Medical Research"
},
{
"operation": "Page search",
"time": "136.899",
"value": "Vogt"
},
{
"operation": "Page search",
"time": "163.184",
"value": "Sir Henry Dale and Wilhelm Feldberg i"
},
{
"operation": "search",
"time": "192.973",
"value": "British Pharmacological Society"
},
{
"operation": "Now on",
"time": "194.713",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "213.052",
"value": "Annette Dolphin"
},
{
"operation": "Now on",
"time": "214.208",
"value": "Annette Dolphin"
},
{
"operation": "search",
"time": "260.192",
"value": "Vogt Prize |"
},
{
"operation": "Now on",
"time": "261.744",
"value": "undefined"
},
{
"operation": "search",
"time": "276.059",
"value": "Vogt Prize"
},
{
"operation": "Now on",
"time": "276.943",
"value": "undefined"
},
{
"operation": "search",
"time": "305.463",
"value": "British Pharmacological Society"
},
{
"operation": "Now on",
"time": "306.166",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "308.701",
"value": "British Journal of Pharmacology"
},
{
"operation": "Now on",
"time": "309.503",
"value": "British Journal of Pharmacology"
},
{
"operation": "Highlighting",
"time": "311.179",
"value": "British Journal of Pharmacology_sentence_0"
},
{
"operation": "Page search",
"time": "341.543",
"value": "Vogt"
},
{
"operation": "search",
"time": "373.656",
"value": "vogt prize"
},
{
"operation": "Now on",
"time": "374.464",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "385.863",
"value": "next 20"
},
{
"operation": "Now on",
"time": "386.992",
"value": "undefined"
},
{
"operation": "search",
"time": "405.927",
"value": "Sir Henry Dale"
},
{
"operation": "Now on",
"time": "407.219",
"value": "Henry Hallett Dale"
},
{
"operation": "Highlighting",
"time": "422.703",
"value": "Henry Hallett Dale_sentence_0"
},
{
"operation": "Page search",
"time": "434.273",
"value": "vogt"
},
{
"operation": "Page search",
"time": "447.983",
"value": "vogt"
},
{
"operation": "Page search",
"time": "453.403",
"value": "Wilhelm Feldberg"
},
{
"operation": "Highlighting",
"time": "461.673",
"value": "Henry Hallett Dale_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "472.024",
"value": "Henry Hallett Dale_header_cell_0_0_0"
},
{
"operation": "Page search",
"time": "484.111",
"value": "e National Institute for Medical Research"
},
{
"operation": "Highlighting",
"time": "491.164",
"value": "Henry Hallett Dale_sentence_9"
},
{
"operation": "Page search",
"time": "514.436",
"value": "Wilhelm Feldberg"
},
{
"operation": "search",
"time": "519.744",
"value": "Wilhelm Feldberg"
},
{
"operation": "Now on",
"time": "521.333",
"value": "Wilhelm Feldberg"
},
{
"operation": "Highlighting",
"time": "523.875",
"value": "Wilhelm Feldberg_sentence_0"
},
{
"operation": "search",
"time": "541.025",
"value": "National Institute for Medical Research"
},
{
"operation": "Now on",
"time": "541.622",
"value": "National Institute for Medical Research"
},
{
"operation": "back-button-clicked",
"time": "545.436",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "545.504",
"value": "Wilhelm Feldberg"
},
{
"operation": "Page search",
"time": "548.742",
"value": "National Institute for Medical Research"
},
{
"operation": "Highlighting",
"time": "550.623",
"value": "Wilhelm Feldberg_sentence_5"
},
{
"operation": "Highlighting",
"time": "557.228",
"value": "Wilhelm Feldberg_sentence_13"
},
{
"operation": "Highlighting",
"time": "564.572",
"value": "Wilhelm Feldberg_sentence_16"
},
{
"operation": "Page search",
"time": "590.422",
"value": "Nvogt"
},
{
"operation": "Page search",
"time": "594.721",
"value": "vogt"
},
{
"operation": "search",
"time": "609.5",
"value": "British Pharmacological Society prizes"
},
{
"operation": "Now on",
"time": "610.962",
"value": "undefined"
},
{
"operation": "finish",
"time": "654.197",
"value": "finish"
}
]
}
|
89629
|
The William Tully House (also known as Hartsease or Heartsease), on the north side of North Cove Road (a historic road dating to the mid-17th century), is a two-and-a-half-story wood-frame structure, four bays wide, with a central chimney and centered doorway.
|
{
"evidence": [
"William Tully House_sentence_0",
"William Tully House_sentence_4",
"William Tully House_sentence_5",
"William Tully House_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 William Tully House (also known as Hartsease or Heartsease), on the north side of North Cove Road (a historic road dating to the mid-17th century), is a two-and-a-half-story wood-frame structure, four bays wide, with a central chimney and centered doorway.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"William Tully House_sentence_0",
"William Tully House_sentence_4",
"William Tully House_sentence_5",
"William Tully House_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4344,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.168",
"value": "?search="
},
{
"operation": "search",
"time": "9.395",
"value": "William Tully House"
},
{
"operation": "Now on",
"time": "10.366",
"value": "William Tully House"
},
{
"operation": "Highlighting",
"time": "12.804",
"value": "William Tully House_sentence_0"
},
{
"operation": "Highlighting",
"time": "26.847",
"value": "William Tully House_sentence_4"
},
{
"operation": "Highlighting",
"time": "35.427",
"value": "William Tully House_sentence_5"
},
{
"operation": "Highlighting",
"time": "41.531",
"value": "William Tully House_sentence_6"
},
{
"operation": "finish",
"time": "63.456",
"value": "finish"
}
]
}
|
13838
|
Sandy Nava, an American 19th century Major League Baseball player for five seasons from 1882 through 1886 who played in 28 games his rookie season, returned to the Grays for two more seasons, continuing to be the back-up catcher to Barney Gilligan, having his best year in 1883 when he batted .240 and scored 18 runs in 29 games.
|
{
"evidence": [
"Sandy Nava_sentence_0",
"Sandy Nava_sentence_5",
"Sandy Nava_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:\nSandy Nava, an American 19th century Major League Baseball player for five seasons from 1882 through 1886 who played in 28 games his rookie season, returned to the Grays for two more seasons, continuing to be the back-up catcher to Barney Gilligan, having his best year in 1883 when he batted .240 and scored 18 runs in 29 games.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Sandy Nava_sentence_0",
"Sandy Nava_sentence_5",
"Sandy Nava_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4345,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.567",
"value": "?search="
},
{
"operation": "search",
"time": "15.71",
"value": "Sandy Nava"
},
{
"operation": "Now on",
"time": "16.4",
"value": "Sandy Nava"
},
{
"operation": "Highlighting",
"time": "23.281",
"value": "Sandy Nava_sentence_0"
},
{
"operation": "Highlighting",
"time": "31.412",
"value": "Sandy Nava_sentence_5"
},
{
"operation": "Highlighting",
"time": "41.101",
"value": "Sandy Nava_sentence_6"
},
{
"operation": "finish",
"time": "49.398",
"value": "finish"
}
]
}
|
exfever_3920
|
Penguin Books is a British publishing house by Sir Allen Lane with his brothers Richard and John, as a line of an English publishing house existing as an independent entity.
|
{
"evidence": [
"Penguin Books",
"The Bodley Head"
],
"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:\nPenguin Books is a British publishing house by Sir Allen Lane with his brothers Richard and John, as a line of an English publishing house existing as an independent entity.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Penguin Books",
"The Bodley Head"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4346,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
84998
|
Jean Marie Auguste Bachelot de La Pylaie (May 25, 1786- October 12, 1856) was a botanist, explorer and archaeologist who studied at Laval, and then in Paris at the Muséum national d'histoire naturelle.
|
{
"evidence": [
"Jean Bachelot La Pylaie_sentence_0",
"Jean Bachelot La Pylaie_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:\nJean Marie Auguste Bachelot de La Pylaie (May 25, 1786- October 12, 1856) was a botanist, explorer and archaeologist who studied at Laval, and then in Paris at the Muséum national d'histoire naturelle.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jean Bachelot La Pylaie_sentence_0",
"Jean Bachelot La Pylaie_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4347,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.168",
"value": "?search="
},
{
"operation": "search",
"time": "9.759",
"value": "Jean Marie Auguste Bachelot de La Pylaie"
},
{
"operation": "Now on",
"time": "11.412",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "33.218",
"value": "Jean Bachelot La Pylaie"
},
{
"operation": "Now on",
"time": "33.998",
"value": "Jean Bachelot La Pylaie"
},
{
"operation": "Highlighting",
"time": "38.054",
"value": "Jean Bachelot La Pylaie_sentence_0"
},
{
"operation": "Highlighting",
"time": "43.696",
"value": "Jean Bachelot La Pylaie_sentence_1"
},
{
"operation": "finish",
"time": "54.254",
"value": "finish"
}
]
}
|
50424
|
There were 897,861 Hindus (people who study Hinduism, an Abrahamic monotheistic religion based on the life and teachings of Jesus of Nazareth) in Odisha in 2001.
|
{
"evidence": [
"Hinduism_sentence_0",
"Hinduism_sentence_6"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThere were 897,861 Hindus (people who study Hinduism, an Abrahamic monotheistic religion based on the life and teachings of Jesus of Nazareth) in Odisha in 2001.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Hinduism_sentence_0",
"Hinduism_sentence_6"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4348,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.114",
"value": "?search="
},
{
"operation": "Now on",
"time": "23.574",
"value": "?search="
},
{
"operation": "search",
"time": "43.294",
"value": "Hinduism"
},
{
"operation": "Now on",
"time": "49.836",
"value": "Hinduism"
},
{
"operation": "Highlighting",
"time": "57.242",
"value": "Hinduism_sentence_0"
},
{
"operation": "Highlighting",
"time": "91.267",
"value": "Hinduism_sentence_4"
},
{
"operation": "Highlighting",
"time": "102.107",
"value": "Hinduism_sentence_6"
},
{
"operation": "Highlighting deleted",
"time": "103.682",
"value": "Hinduism_sentence_4"
},
{
"operation": "finish",
"time": "124.023",
"value": "finish"
}
]
}
|
exfever_1822
|
Dinosaurs continued their dominance throughout the Jurassic and a geological period that lasted from about 145 to 66 million years ago and the name is derived from a soft, white, porous, sedimentary carbonate rock.
|
{
"evidence": [
"Dinosaur",
"Cretaceous",
"Chalk"
],
"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:\nDinosaurs continued their dominance throughout the Jurassic and a geological period that lasted from about 145 to 66 million years ago and the name is derived from a soft, white, porous, sedimentary carbonate rock.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Dinosaur",
"Cretaceous",
"Chalk"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4349,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6790
|
An alcoholic drink, also called an alcoholic beverage, an adult beverage, or simply a drink, is a drink that contains a non-organic chemical compound.
|
{
"evidence": [
"Alcoholic drink",
"Ethanol"
],
"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:\nAn alcoholic drink, also called an alcoholic beverage, an adult beverage, or simply a drink, is a drink that contains a non-organic chemical compound.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Alcoholic drink",
"Ethanol"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4350,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
78280
|
Halo Online is a free-to-play first-person shooter that was heavily modified version of Halo 3.
|
{
"evidence": [
"Halo Online_sentence_1",
"Halo Online_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:\nHalo Online is a free-to-play first-person shooter that was heavily modified version of Halo 3.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Halo Online_sentence_1",
"Halo Online_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4351,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.449",
"value": "?search="
},
{
"operation": "search",
"time": "16.079",
"value": "Halo Online"
},
{
"operation": "Now on",
"time": "17.096",
"value": "Halo Online"
},
{
"operation": "Highlighting",
"time": "23.22",
"value": "Halo Online_sentence_1"
},
{
"operation": "Highlighting",
"time": "25.958",
"value": "Halo Online_sentence_0"
},
{
"operation": "finish",
"time": "34.943",
"value": "finish"
}
]
}
|
exfever_3442
|
The Terminator was considered a significant success, enhancing Schwarzenegger's and Cameron's careers.
|
{
"evidence": [
"Aliens (film)",
"James Cameron",
"The Abyss"
],
"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 Terminator was considered a significant success, enhancing Schwarzenegger's and Cameron's careers.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Aliens (film)",
"James Cameron",
"The Abyss"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4352,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6495
|
Chris Evans is an American actor who has made further appearances in film adaptations of publications that consist of comic art in the form of sequentially juxtaposed panels that represent individual scenes.
|
{
"evidence": [
"Chris Evans (actor)",
"Comic book"
],
"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:\nChris Evans is an American actor who has made further appearances in film adaptations of publications that consist of comic art in the form of sequentially juxtaposed panels that represent individual scenes.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Chris Evans (actor)",
"Comic book"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4353,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2515
|
Saamy is a 2003 Indian Tamil-language action film whose music was composed by an Indian composer from Chennai, Tamil Nadu.
|
{
"evidence": [
"Saamy",
"Harris Jayaraj"
],
"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:\nSaamy is a 2003 Indian Tamil-language action film whose music was composed by an Indian composer from Chennai, Tamil Nadu.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Saamy",
"Harris Jayaraj"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4354,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1659
|
Pineapple Express is a 2008 American stoner comedy film starring an American actor known for his role in a 2013 American crime film written and directed by Harmony Korine.
|
{
"evidence": [
"Pineapple Express (film)",
"James Franco",
"Spring Breakers"
],
"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:\nPineapple Express is a 2008 American stoner comedy film starring an American actor known for his role in a 2013 American crime film written and directed by Harmony Korine.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Pineapple Express (film)",
"James Franco",
"Spring Breakers"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4355,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2462
|
"The Game of Thrones" is the most viewed series that aired on HBO.
|
{
"evidence": [
"A Game of Thrones",
"World Fantasy Award",
"Nebula Award"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\n\"The Game of Thrones\" is the most viewed series that aired on HBO.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"A Game of Thrones",
"World Fantasy Award",
"Nebula Award"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4356,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7048
|
Billie Jean King is an American former world No. 1 badminton player who founded the principal organizing body of women's professional tennis, which governs the worldwide professional tennis tour for women.?
|
{
"evidence": [
"Billie Jean King",
"Women's Tennis Association"
],
"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:\nBillie Jean King is an American former world No. 1 badminton player who founded the principal organizing body of women's professional tennis, which governs the worldwide professional tennis tour for women.?\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Billie Jean King",
"Women's Tennis Association"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4357,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6796
|
Annie Parisse is a British actress who starred in the soap opera As the World Turns, for which she was nominated for an American accolade bestowed by the New York-based National Academy of Television Arts and Sciences in recognition of excellence in American daytime television programming.
|
{
"evidence": [
"Annie Parisse",
"Daytime Emmy Award"
],
"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:\nAnnie Parisse is a British actress who starred in the soap opera As the World Turns, for which she was nominated for an American accolade bestowed by the New York-based National Academy of Television Arts and Sciences in recognition of excellence in American daytime television programming.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Annie Parisse",
"Daytime Emmy Award"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4358,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
27631
|
Cape Amsterdam is 15 km from Sveagruva, the mined coals are transported by trucks from there to the quay, but in March 2011, there was a coal fire in a pile of around 80,000 tons of coal.
|
{
"evidence": [
"Cape Amsterdam_sentence_2",
"Cape Amsterdam_sentence_3",
"Cape Amsterdam_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:\nCape Amsterdam is 15 km from Sveagruva, the mined coals are transported by trucks from there to the quay, but in March 2011, there was a coal fire in a pile of around 80,000 tons of coal.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Cape Amsterdam_sentence_2",
"Cape Amsterdam_sentence_3",
"Cape Amsterdam_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4359,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.675",
"value": "?search="
},
{
"operation": "search",
"time": "35.322",
"value": "Cape Amsterdam"
},
{
"operation": "Now on",
"time": "36.655",
"value": "Cape Amsterdam"
},
{
"operation": "Highlighting",
"time": "203.007",
"value": "Cape Amsterdam_sentence_2"
},
{
"operation": "Highlighting",
"time": "213.656",
"value": "Cape Amsterdam_sentence_3"
},
{
"operation": "Highlighting",
"time": "216.444",
"value": "Cape Amsterdam_sentence_4"
},
{
"operation": "finish",
"time": "255.438",
"value": "finish"
}
]
}
|
exfever_243
|
Michael Giacchino is an Indian film, television, and video game composer who collaborated with an American filmmaker who debuted as a feature director with the science-fiction comedy film Safety Not Guaranteed.
|
{
"evidence": [
"Michael Giacchino",
"Colin Trevorrow"
],
"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:\nMichael Giacchino is an Indian film, television, and video game composer who collaborated with an American filmmaker who debuted as a feature director with the science-fiction comedy film Safety Not Guaranteed.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Michael Giacchino",
"Colin Trevorrow"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4360,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8351
|
Diary of the Dead is a 2007 American horror film written and directed by George A. Romero that was distributed theatrically by an American independent film studio, founded in New York City by Bob and Harvey Weinstein.
|
{
"evidence": [
"Diary of the Dead",
"The Weinstein Company"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nDiary of the Dead is a 2007 American horror film written and directed by George A. Romero that was distributed theatrically by an American independent film studio, founded in New York City by Bob and Harvey Weinstein.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Diary of the Dead",
"The Weinstein Company"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4361,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5935
|
Woodrow Harrelson is an American actor and playwright who received various accolades, including recognition for excellence in American primetime television programming.
|
{
"evidence": [
"Woody Harrelson",
"Primetime Emmy Award"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nWoodrow Harrelson is an American actor and playwright who received various accolades, including recognition for excellence in American primetime television programming.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Woody Harrelson",
"Primetime Emmy Award"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4362,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7066
|
Toy Story is a computer-animated film that emphasizes humor that could result from situations intended to cause laughter by caricaturing the manner or spirit of serious works or by ludicrous treatment of their subjects.
|
{
"evidence": [
"Toy Story",
"Comedy film",
"Burlesque"
],
"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:\nToy Story is a computer-animated film that emphasizes humor that could result from situations intended to cause laughter by caricaturing the manner or spirit of serious works or by ludicrous treatment of their subjects.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Toy Story",
"Comedy film",
"Burlesque"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4363,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
70103
|
Berkeley cardinals are certain large cardinals suggested by Hugh Woodin and are currently accepted without errors in mathematics.
|
{
"evidence": [
"Berkeley cardinal_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:\nBerkeley cardinals are certain large cardinals suggested by Hugh Woodin and are currently accepted without errors in mathematics.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Berkeley cardinal_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4364,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.252",
"value": "?search="
},
{
"operation": "search",
"time": "39.316",
"value": "berkeley cardinals"
},
{
"operation": "Now on",
"time": "40.302",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "42.427",
"value": "Berkeley cardinal"
},
{
"operation": "Now on",
"time": "42.981",
"value": "Berkeley cardinal"
},
{
"operation": "Highlighting",
"time": "46.874",
"value": "Berkeley cardinal_sentence_0"
},
{
"operation": "Page search",
"time": "74.738",
"value": "error"
},
{
"operation": "Page search",
"time": "76.673",
"value": "errors"
},
{
"operation": "Page search",
"time": "84.201",
"value": "accepted"
},
{
"operation": "Page search",
"time": "87.378",
"value": "currently"
},
{
"operation": "Highlighting",
"time": "104.914",
"value": "Berkeley cardinal_sentence_2"
},
{
"operation": "hyperlink",
"time": "125.081",
"value": "axiom of countable choice"
},
{
"operation": "Now on",
"time": "125.498",
"value": "Axiom of countable choice"
},
{
"operation": "Page search",
"time": "138.737",
"value": "error"
},
{
"operation": "search",
"time": "156.498",
"value": "Hugh Woodin"
},
{
"operation": "Now on",
"time": "157.051",
"value": "W. Hugh Woodin"
},
{
"operation": "hyperlink",
"time": "193.225",
"value": "Mathematics"
},
{
"operation": "Now on",
"time": "194.259",
"value": "Mathematics"
},
{
"operation": "Page search",
"time": "199.493",
"value": "cardinal"
},
{
"operation": "search",
"time": "215.478",
"value": "Berkeley cardinal"
},
{
"operation": "Now on",
"time": "215.945",
"value": "Berkeley cardinal"
},
{
"operation": "hyperlink",
"time": "223.034",
"value": "large cardinals"
},
{
"operation": "Now on",
"time": "223.459",
"value": "Large cardinal"
},
{
"operation": "Page search",
"time": "231.29",
"value": "error"
},
{
"operation": "Page search",
"time": "248.186",
"value": "berkeley"
},
{
"operation": "hyperlink",
"time": "252.73",
"value": "List of large cardinal properties"
},
{
"operation": "Now on",
"time": "253.142",
"value": "List of large cardinal properties"
},
{
"operation": "hyperlink",
"time": "258.858",
"value": "Berkeley cardinal"
},
{
"operation": "Now on",
"time": "259.166",
"value": "Berkeley cardinal"
},
{
"operation": "Highlighting deleted",
"time": "277.939",
"value": "Berkeley cardinal_sentence_2"
},
{
"operation": "hyperlink",
"time": "280.738",
"value": "axiom of choice"
},
{
"operation": "Now on",
"time": "286.626",
"value": "Axiom of choice"
},
{
"operation": "Page search",
"time": "299.141",
"value": "berkeley"
},
{
"operation": "finish",
"time": "322.881",
"value": "finish"
}
]
}
|
exfever_7619
|
Jack Roosevelt Robinson was an American professional baseball player who became the first African American to play in a professional baseball organization and the oldest major professional sports league in the world played by 15 teams in the older of two leagues in the United States and Canada, and the world's oldest extant professional team sports league.
|
{
"evidence": [
"Jackie Robinson",
"Major League Baseball",
"National League"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJack Roosevelt Robinson was an American professional baseball player who became the first African American to play in a professional baseball organization and the oldest major professional sports league in the world played by 15 teams in the older of two leagues in the United States and Canada, and the world's oldest extant professional team sports league.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jackie Robinson",
"Major League Baseball",
"National League"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4365,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2645
|
The Martian was the debut film of Donald Glover.
|
{
"evidence": [
"The Martian (film)",
"Mars"
],
"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 Martian was the debut film of Donald Glover.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Martian (film)",
"Mars"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4366,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
13452
|
RCEs, acknowledged by the UNGA based on recommendations of the Ubuntu Committee of Peers for the RCEs, aspire to achieve the goals of the ESD by translating its global objectives into the context of the local communities in which they operate.
|
{
"evidence": [
"Regional Centres of Expertise_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:\nRCEs, acknowledged by the UNGA based on recommendations of the Ubuntu Committee of Peers for the RCEs, aspire to achieve the goals of the ESD by translating its global objectives into the context of the local communities in which they operate.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Regional Centres of Expertise_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4367,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.022",
"value": "?search="
},
{
"operation": "search",
"time": "22.225",
"value": "Regional Centres of Expertise"
},
{
"operation": "Now on",
"time": "22.971",
"value": "Regional Centres of Expertise"
},
{
"operation": "Page search",
"time": "30.101",
"value": "UNGA based"
},
{
"operation": "Page search",
"time": "36.94",
"value": "acknowledge"
},
{
"operation": "Highlighting",
"time": "43.147",
"value": "Regional Centres of Expertise_sentence_3"
},
{
"operation": "Page search",
"time": "59.411",
"value": "UNGA"
},
{
"operation": "finish",
"time": "69.207",
"value": "finish"
}
]
}
|
exfever_4124
|
Domitian was adamant in his love for Domitia Longina.
|
{
"evidence": [
"Colosseum",
"Domitian"
],
"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:\nDomitian was adamant in his love for Domitia Longina.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Colosseum",
"Domitian"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4368,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5392
|
Arrested Development is a 2003 television film in Europe that is produced by an American actor, and producer that came to fame as a child actor, guest-starring in several television series.
|
{
"evidence": [
"Arrested Development (TV series)",
"Ron Howard"
],
"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:\nArrested Development is a 2003 television film in Europe that is produced by an American actor, and producer that came to fame as a child actor, guest-starring in several television series.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Arrested Development (TV series)",
"Ron Howard"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4369,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
73988
|
Rijksmuseum Research Library is the largest public art history research library in the Netherlands with an online catalog that contains over 400,000 monographs, 3,400 periodicals, and 90,000 art sales catalogs, while being a part of the State Hermitage Museum, also the largest art museum in the country that displays 8,000 objects of art and history.
|
{
"evidence": [
"Rijksmuseum Research Library_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:\nRijksmuseum Research Library is the largest public art history research library in the Netherlands with an online catalog that contains over 400,000 monographs, 3,400 periodicals, and 90,000 art sales catalogs, while being a part of the State Hermitage Museum, also the largest art museum in the country that displays 8,000 objects of art and history.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Rijksmuseum Research Library_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4370,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.78",
"value": "?search="
},
{
"operation": "search",
"time": "4.298",
"value": "Rijksmuseum Research Library"
},
{
"operation": "Now on",
"time": "5.072",
"value": "Rijksmuseum Research Library"
},
{
"operation": "Highlighting",
"time": "9.188",
"value": "Rijksmuseum Research Library_sentence_0"
},
{
"operation": "Highlighting",
"time": "13.286",
"value": "Rijksmuseum Research Library_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "35.536",
"value": "Rijksmuseum Research Library_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "36.778",
"value": "Rijksmuseum Research Library_sentence_3"
},
{
"operation": "Highlighting",
"time": "37.743",
"value": "Rijksmuseum Research Library_sentence_1"
},
{
"operation": "finish",
"time": "44.199",
"value": "finish"
}
]
}
|
15014
|
The Danish footballer for Boldklubben 1908 who used to play with two clubs from 2011 to 2013 appearing in 47 games making 16 goals in total is Nichola Rohde.
|
{
"evidence": [
"Boldklubben 1908_sentence_0",
"Boldklubben 1908_sentence_1",
"Boldklubben 1908_sentence_4",
"Boldklubben 1908_sentence_5",
"Boldklubben 1908_sentence_6",
"List of Boldklubben 1908 seasons_sentence_0",
"List of Boldklubben 1908 seasons_sentence_5"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Danish footballer for Boldklubben 1908 who used to play with two clubs from 2011 to 2013 appearing in 47 games making 16 goals in total is Nichola Rohde.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Boldklubben 1908_sentence_0",
"Boldklubben 1908_sentence_1",
"Boldklubben 1908_sentence_4",
"Boldklubben 1908_sentence_5",
"Boldklubben 1908_sentence_6",
"List of Boldklubben 1908 seasons_sentence_0",
"List of Boldklubben 1908 seasons_sentence_5"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4371,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.887",
"value": "?search="
},
{
"operation": "search",
"time": "30.511",
"value": "nichola rhode"
},
{
"operation": "Now on",
"time": "32.008",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "34.131",
"value": "nichols rhode"
},
{
"operation": "Now on",
"time": "35.77",
"value": "undefined"
},
{
"operation": "search",
"time": "50.497",
"value": "Boldklubben 1909"
},
{
"operation": "Now on",
"time": "52.025",
"value": "Boldklubben 1909"
},
{
"operation": "search",
"time": "110.864",
"value": "nichol* rohde"
},
{
"operation": "Now on",
"time": "112.706",
"value": "undefined"
},
{
"operation": "search",
"time": "121.735",
"value": "nichol rohde"
},
{
"operation": "Now on",
"time": "122.788",
"value": "undefined"
},
{
"operation": "search",
"time": "145.496",
"value": "List of Boldklubben 1908 seasons"
},
{
"operation": "Now on",
"time": "147.038",
"value": "List of Boldklubben 1908 seasons"
},
{
"operation": "search",
"time": "164.978",
"value": "Boldklubben 1908"
},
{
"operation": "Now on",
"time": "166.805",
"value": "Boldklubben 1908"
},
{
"operation": "search",
"time": "194.601",
"value": "List of Boldklubben 1908 seasons"
},
{
"operation": "Now on",
"time": "195.752",
"value": "List of Boldklubben 1908 seasons"
},
{
"operation": "hyperlink",
"time": "204.47",
"value": "B 1908"
},
{
"operation": "Now on",
"time": "205.363",
"value": "Boldklubben 1908"
},
{
"operation": "Highlighting",
"time": "223.27",
"value": "Boldklubben 1908_sentence_0"
},
{
"operation": "Highlighting",
"time": "224.685",
"value": "Boldklubben 1908_sentence_1"
},
{
"operation": "Highlighting",
"time": "232.037",
"value": "Boldklubben 1908_sentence_4"
},
{
"operation": "Highlighting",
"time": "233.507",
"value": "Boldklubben 1908_sentence_5"
},
{
"operation": "Highlighting",
"time": "234.135",
"value": "Boldklubben 1908_sentence_6"
},
{
"operation": "search",
"time": "276.091",
"value": "2011 boldklubben 1908"
},
{
"operation": "Now on",
"time": "278.353",
"value": "undefined"
},
{
"operation": "search",
"time": "287.167",
"value": "List of Boldklubben 1908 seasons"
},
{
"operation": "Now on",
"time": "289.195",
"value": "List of Boldklubben 1908 seasons"
},
{
"operation": "Highlighting",
"time": "291.3",
"value": "List of Boldklubben 1908 seasons_sentence_0"
},
{
"operation": "Highlighting",
"time": "295.068",
"value": "List of Boldklubben 1908 seasons_sentence_5"
},
{
"operation": "hyperlink",
"time": "314.346",
"value": "B 1908"
},
{
"operation": "Now on",
"time": "315.125",
"value": "Boldklubben 1908"
},
{
"operation": "finish",
"time": "335.497",
"value": "finish"
}
]
}
|
49115
|
Melaleuca conothamnoides is a woody branching shrub that can only be found in the south-west of Western Australia.
|
{
"evidence": [
"Melaleuca conothamnoides_sentence_0",
"Melaleuca conothamnoides_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:\nMelaleuca conothamnoides is a woody branching shrub that can only be found in the south-west of Western Australia.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Melaleuca conothamnoides_sentence_0",
"Melaleuca conothamnoides_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4372,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.836",
"value": "?search="
},
{
"operation": "search",
"time": "16.063",
"value": "Melaleuca conothamnoides"
},
{
"operation": "Now on",
"time": "16.726",
"value": "Melaleuca conothamnoides"
},
{
"operation": "Highlighting",
"time": "22.595",
"value": "Melaleuca conothamnoides_sentence_0"
},
{
"operation": "Highlighting",
"time": "40.034",
"value": "Melaleuca conothamnoides_sentence_2"
},
{
"operation": "hyperlink",
"time": "47.815",
"value": "3 Distribution and habitat Melaleuca conothamnoides_section_2"
},
{
"operation": "finish",
"time": "82.362",
"value": "finish"
}
]
}
|
exfever_2640
|
Christopher O'Dowd is the most famous Irish actor and comedian.
|
{
"evidence": [
"Chris O'Dowd",
"Cuban Fury"
],
"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:\nChristopher O'Dowd is the most famous Irish actor and comedian.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Chris O'Dowd",
"Cuban Fury"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4373,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
34899
|
Animals Australia conducted an investigation of the treatment of exported Australian cattle in Indonesia worth $328 million, animals had their throats cut while fully conscious and sparked mass protests across Australia.
|
{
"evidence": [
"Australian live export industry_sentence_11",
"Australian live export industry_sentence_12",
"Australian live export industry_sentence_13"
],
"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:\nAnimals Australia conducted an investigation of the treatment of exported Australian cattle in Indonesia worth $328 million, animals had their throats cut while fully conscious and sparked mass protests across Australia.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Australian live export industry_sentence_11",
"Australian live export industry_sentence_12",
"Australian live export industry_sentence_13"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4374,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.493",
"value": "?search="
},
{
"operation": "search",
"time": "32.86",
"value": "Animals Australia"
},
{
"operation": "Now on",
"time": "34.709",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "37.087",
"value": "Animals Australia"
},
{
"operation": "Now on",
"time": "38.107",
"value": "Animals Australia"
},
{
"operation": "Page search",
"time": "54.516",
"value": "protest"
},
{
"operation": "Page search",
"time": "54.774",
"value": "protest"
},
{
"operation": "Page search",
"time": "54.995",
"value": "protest"
},
{
"operation": "Page search",
"time": "55.174",
"value": "protest"
},
{
"operation": "search",
"time": "74.227",
"value": "Animals Australia conducted an investigation of the treatment of exported Australian cattle"
},
{
"operation": "Now on",
"time": "77.115",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "84.224",
"value": "Australian live export industry"
},
{
"operation": "Now on",
"time": "85.159",
"value": "Australian live export industry"
},
{
"operation": "Page search",
"time": "88.458",
"value": "Animals Australia conducted an investigation of the treatment of exported Australian cattle"
},
{
"operation": "Page search",
"time": "88.679",
"value": "Animals Australia conducted an investigation of the treatment of exported Australian cattle"
},
{
"operation": "Page search",
"time": "88.833",
"value": "Animals Australia conducted an investigation of the treatment of exported Australian cattle"
},
{
"operation": "Page search",
"time": "89.008",
"value": "Animals Australia conducted an investigation of the treatment of exported Australian cattle"
},
{
"operation": "Page search",
"time": "92.577",
"value": "exported Australian cattle"
},
{
"operation": "Page search",
"time": "92.922",
"value": "exported Australian cattle"
},
{
"operation": "Page search",
"time": "93.176",
"value": "exported Australian cattle"
},
{
"operation": "Page search",
"time": "93.272",
"value": "exported Australian cattle"
},
{
"operation": "Highlighting",
"time": "99.283",
"value": "Australian live export industry_sentence_11"
},
{
"operation": "Highlighting",
"time": "121.935",
"value": "Australian live export industry_sentence_12"
},
{
"operation": "Highlighting",
"time": "130.248",
"value": "Australian live export industry_sentence_13"
},
{
"operation": "Page search",
"time": "144.166",
"value": "328"
},
{
"operation": "Page search",
"time": "144.386",
"value": "328"
},
{
"operation": "Page search",
"time": "144.593",
"value": "328"
},
{
"operation": "Highlighting deleted",
"time": "156.957",
"value": "Australian live export industry_sentence_11"
},
{
"operation": "Highlighting",
"time": "157.771",
"value": "Australian live export industry_sentence_11"
},
{
"operation": "Highlighting deleted",
"time": "159.806",
"value": "Australian live export industry_sentence_13"
},
{
"operation": "Highlighting deleted",
"time": "160.198",
"value": "Australian live export industry_sentence_12"
},
{
"operation": "Highlighting deleted",
"time": "160.556",
"value": "Australian live export industry_sentence_11"
},
{
"operation": "Highlighting",
"time": "161.274",
"value": "Australian live export industry_sentence_11"
},
{
"operation": "Highlighting",
"time": "161.816",
"value": "Australian live export industry_sentence_12"
},
{
"operation": "Highlighting",
"time": "162.353",
"value": "Australian live export industry_sentence_13"
},
{
"operation": "finish",
"time": "220.722",
"value": "finish"
}
]
}
|
55829
|
Joo Won has appeared in multiple television series such as in King of Baking, Kim Takgu in 2010, Bridal Mask in 2011, and Alice in 2020.
|
{
"evidence": [
"Joo Won_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:\nJoo Won has appeared in multiple television series such as in King of Baking, Kim Takgu in 2010, Bridal Mask in 2011, and Alice in 2020.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Joo Won_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4375,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.268",
"value": "?search="
},
{
"operation": "search",
"time": "8.996",
"value": "Joo Won"
},
{
"operation": "Now on",
"time": "11.519",
"value": "Joo Won"
},
{
"operation": "Highlighting",
"time": "18.917",
"value": "Joo Won_sentence_2"
},
{
"operation": "finish",
"time": "41.418",
"value": "finish"
}
]
}
|
25960
|
Reseda alba is a genus of Reseda in the kingdom of Plantae under the order of Brassicales.
|
{
"evidence": [
"Reseda alba_sentence_0",
"Genus_sentence_4"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nReseda alba is a genus of Reseda in the kingdom of Plantae under the order of Brassicales.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Reseda alba_sentence_0",
"Genus_sentence_4"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4376,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.594",
"value": "?search="
},
{
"operation": "search",
"time": "10.484",
"value": "Reseda alba"
},
{
"operation": "Now on",
"time": "11.151",
"value": "Reseda alba"
},
{
"operation": "Highlighting",
"time": "18.758",
"value": "Reseda alba_sentence_0"
},
{
"operation": "search",
"time": "69.357",
"value": "genus"
},
{
"operation": "Now on",
"time": "70.11",
"value": "Genus"
},
{
"operation": "Highlighting",
"time": "80.902",
"value": "Genus_sentence_4"
},
{
"operation": "finish",
"time": "92.568",
"value": "finish"
}
]
}
|
78828
|
Jacob Jordeans was a Flemish painter and tapestry designer who lived his entire life in Antwerp before his death from a mysterious Antwerp disease called 'zweetziekte' or 'polderkoorts.
|
{
"evidence": [
"Jacob Jordaens_sentence_0",
"Jacob Jordaens_sentence_3",
"Jacob Jordaens_sentence_62"
],
"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:\nJacob Jordeans was a Flemish painter and tapestry designer who lived his entire life in Antwerp before his death from a mysterious Antwerp disease called 'zweetziekte' or 'polderkoorts.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jacob Jordaens_sentence_0",
"Jacob Jordaens_sentence_3",
"Jacob Jordaens_sentence_62"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4377,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.303",
"value": "?search="
},
{
"operation": "search",
"time": "4.18",
"value": "Jacob Jordeans"
},
{
"operation": "Now on",
"time": "5.199",
"value": "Jacob Jordaens"
},
{
"operation": "Highlighting",
"time": "8.196",
"value": "Jacob Jordaens_sentence_0"
},
{
"operation": "Highlighting",
"time": "20.328",
"value": "Jacob Jordaens_sentence_3"
},
{
"operation": "Highlighting",
"time": "28.666",
"value": "Jacob Jordaens_sentence_62"
},
{
"operation": "finish",
"time": "35.203",
"value": "finish"
}
]
}
|
exfever_1391
|
The Twilight Saga is a series of five vampire-themed romances that belong to the fantasy genre with fantastic themes, usually in a world created from fictional media.
|
{
"evidence": [
"The Twilight Saga (film series)",
"Fantasy film",
"Fantasy world"
],
"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 Twilight Saga is a series of five vampire-themed romances that belong to the fantasy genre with fantastic themes, usually in a world created from fictional media.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Twilight Saga (film series)",
"Fantasy film",
"Fantasy world"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4378,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
65783
|
2005 Melanesian Championships in Athletics is falsely believed to have had over ten events, one of the gold metal winners was Otis Gowa
|
{
"evidence": [
"2005 Melanesian Championships in Athletics_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:\n2005 Melanesian Championships in Athletics is falsely believed to have had over ten events, one of the gold metal winners was Otis Gowa\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"2005 Melanesian Championships in Athletics_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4379,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.503",
"value": "?search="
},
{
"operation": "search",
"time": "23.344",
"value": "2005 Melanesian Championships in Athletics"
},
{
"operation": "Now on",
"time": "24.517",
"value": "2005 Melanesian Championships in Athletics"
},
{
"operation": "Highlighting",
"time": "46.048",
"value": "2005 Melanesian Championships in Athletics_sentence_3"
},
{
"operation": "Highlighting",
"time": "102.169",
"value": "2005 Melanesian Championships in Athletics_header_cell_1_0_1"
},
{
"operation": "Highlighting",
"time": "102.173",
"value": "2005 Melanesian Championships in Athletics_section_0"
},
{
"operation": "Highlighting",
"time": "102.174",
"value": "2005 Melanesian Championships in Athletics_section_1"
},
{
"operation": "Highlighting",
"time": "103.329",
"value": "2005 Melanesian Championships in Athletics_cell_1_1_1"
},
{
"operation": "Highlighting",
"time": "103.344",
"value": "2005 Melanesian Championships in Athletics_header_cell_1_0_1"
},
{
"operation": "Highlighting deleted",
"time": "122.153",
"value": "2005 Melanesian Championships in Athletics_cell_1_1_1"
},
{
"operation": "Highlighting deleted",
"time": "122.157",
"value": "2005 Melanesian Championships in Athletics_section_0"
},
{
"operation": "Highlighting deleted",
"time": "122.159",
"value": "2005 Melanesian Championships in Athletics_section_1"
},
{
"operation": "Highlighting deleted",
"time": "122.161",
"value": "2005 Melanesian Championships in Athletics_header_cell_1_0_1"
},
{
"operation": "finish",
"time": "171.079",
"value": "finish"
}
]
}
|
24934
|
The muksun, part of the Salmonidae family, is a whitefish found in the freshened areas of the Kara and Laptev Seas that can live no more than five years of age.
|
{
"evidence": [
"Muksun_sentence_4"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe muksun, part of the Salmonidae family, is a whitefish found in the freshened areas of the Kara and Laptev Seas that can live no more than five years of age.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Muksun_sentence_4"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4380,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.798",
"value": "undefined"
},
{
"operation": "search",
"time": "5.913",
"value": "Muksun"
},
{
"operation": "Now on",
"time": "6.764",
"value": "Muksun"
},
{
"operation": "Highlighting",
"time": "9.86",
"value": "Muksun_sentence_4"
},
{
"operation": "finish",
"time": "24.501",
"value": "finish"
}
]
}
|
exfever_5303
|
Justin Timberlake is the forty-fifth American singer who has sold over 88 million records.
|
{
"evidence": [
"Justin Timberlake",
"Songwriters Hall of Fame",
"Los Angeles"
],
"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:\nJustin Timberlake is the forty-fifth American singer who has sold over 88 million records.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Justin Timberlake",
"Songwriters Hall of Fame",
"Los Angeles"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4381,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7350
|
Lana Wachowski and Lilly Wachowski achieved fame with their third film The Matrix, a major box office success for which they won the annual awards given by the American Academy of Science Fiction, Fantasy & Horror Films.
|
{
"evidence": [
"The Wachowskis",
"Saturn Award for Best Director"
],
"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:\nLana Wachowski and Lilly Wachowski achieved fame with their third film The Matrix, a major box office success for which they won the annual awards given by the American Academy of Science Fiction, Fantasy & Horror Films.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Wachowskis",
"Saturn Award for Best Director"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4382,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
91994
|
Aonyōbō is a blue-skinned ogre-like, (which is frequently featured in mythology, folklore, and fiction throughout the world) spirit of poverty and misfortune who takes the appearance of an ancient court noblewoman, and legend has it that they are court ladies who serve noble families until they are married off to a worthy suitor.
|
{
"evidence": [
"Aonyōbō_sentence_1",
"Ogre_sentence_6",
"Aonyōbō_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:\nAonyōbō is a blue-skinned ogre-like, (which is frequently featured in mythology, folklore, and fiction throughout the world) spirit of poverty and misfortune who takes the appearance of an ancient court noblewoman, and legend has it that they are court ladies who serve noble families until they are married off to a worthy suitor.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Aonyōbō_sentence_1",
"Ogre_sentence_6",
"Aonyōbō_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4383,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.067",
"value": "?search="
},
{
"operation": "Now on",
"time": "11.249",
"value": "?search="
},
{
"operation": "search",
"time": "51.486",
"value": "Aonyōbō"
},
{
"operation": "Now on",
"time": "52.469",
"value": "Aonyōbō"
},
{
"operation": "Highlighting",
"time": "59.851",
"value": "Aonyōbō_sentence_1"
},
{
"operation": "hyperlink",
"time": "204.85",
"value": "Yōkai"
},
{
"operation": "Now on",
"time": "206.154",
"value": "Yōkai"
},
{
"operation": "back-button-clicked",
"time": "262.139",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "262.334",
"value": "Aonyōbō"
},
{
"operation": "hyperlink",
"time": "264.497",
"value": "Japanese mythology"
},
{
"operation": "Now on",
"time": "265.33",
"value": "Japanese mythology"
},
{
"operation": "back-button-clicked",
"time": "334.649",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "334.833",
"value": "Aonyōbō"
},
{
"operation": "hyperlink",
"time": "411.976",
"value": "ogre"
},
{
"operation": "Now on",
"time": "412.622",
"value": "Ogre"
},
{
"operation": "Highlighting",
"time": "419.882",
"value": "Ogre_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "423.681",
"value": "Ogre_sentence_5"
},
{
"operation": "Highlighting",
"time": "425.969",
"value": "Ogre_sentence_6"
},
{
"operation": "back-button-clicked",
"time": "712.208",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "712.456",
"value": "Aonyōbō"
},
{
"operation": "Highlighting",
"time": "722.272",
"value": "Aonyōbō_sentence_3"
},
{
"operation": "finish",
"time": "752.345",
"value": "finish"
}
]
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.