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 |
|---|---|---|---|---|---|---|---|---|
62898
|
Ilan Shohat (born 21 September 1974), was Israel's youngest politician to hold public office in 2008.
|
{
"evidence": [
"Ilan Shohat_sentence_1",
"Ilan Shohat_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:\nIlan Shohat (born 21 September 1974), was Israel's youngest politician to hold public office in 2008.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Ilan Shohat_sentence_1",
"Ilan Shohat_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2284,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.971",
"value": "?search="
},
{
"operation": "search",
"time": "37.113",
"value": "Ilan Shohat"
},
{
"operation": "Now on",
"time": "37.7",
"value": "Ilan Shohat"
},
{
"operation": "Highlighting",
"time": "47.098",
"value": "Ilan Shohat_sentence_1"
},
{
"operation": "Highlighting",
"time": "52.064",
"value": "Ilan Shohat_sentence_0"
},
{
"operation": "finish",
"time": "158.327",
"value": "finish"
}
]
}
|
exfever_1140
|
Anderson Hays Cooper serves as a correspondent for a British television news magazine broadcast that was created by an American journalist and television executive who served as President of CBS News.
|
{
"evidence": [
"Anderson Cooper",
"60 Minutes",
"Bill Leonard (journalist)"
],
"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:\nAnderson Hays Cooper serves as a correspondent for a British television news magazine broadcast that was created by an American journalist and television executive who served as President of CBS News.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Anderson Cooper",
"60 Minutes",
"Bill Leonard (journalist)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2285,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
81250
|
In the 1932 state highway renumbering, Highway 345 renumbered to Route 201, while most of modern Route 97 was commissioned as well.
|
{
"evidence": [
"Connecticut Route 97_sentence_6",
"Connecticut Route 97_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:\nIn the 1932 state highway renumbering, Highway 345 renumbered to Route 201, while most of modern Route 97 was commissioned as well.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Connecticut Route 97_sentence_6",
"Connecticut Route 97_sentence_7"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2286,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.086",
"value": "?search="
},
{
"operation": "search",
"time": "24.452",
"value": "1932 state highway renumbering (Connecticut)"
},
{
"operation": "Now on",
"time": "25.468",
"value": "1932 state highway renumbering (Connecticut)"
},
{
"operation": "search",
"time": "162",
"value": "most of modern Route 97 was commissioned"
},
{
"operation": "Now on",
"time": "166.215",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "170.677",
"value": "Connecticut Route 97"
},
{
"operation": "Now on",
"time": "171.331",
"value": "Connecticut Route 97"
},
{
"operation": "Highlighting",
"time": "177.202",
"value": "Connecticut Route 97_sentence_7"
},
{
"operation": "Highlighting",
"time": "209.748",
"value": "Connecticut Route 97_sentence_6"
},
{
"operation": "Highlighting deleted",
"time": "218.259",
"value": "Connecticut Route 97_sentence_7"
},
{
"operation": "Highlighting",
"time": "218.442",
"value": "Connecticut Route 97_sentence_7"
},
{
"operation": "finish",
"time": "343.937",
"value": "finish"
}
]
}
|
58999
|
Pseudomyrmex spinicola are the less aggressive of several A. collinsii-inhabiting species, creating their colony in A. Collinsii.
|
{
"evidence": [
"Pseudomyrmex spinicola_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:\nPseudomyrmex spinicola are the less aggressive of several A. collinsii-inhabiting species, creating their colony in A. Collinsii.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Pseudomyrmex spinicola_sentence_4"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2287,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.894",
"value": "?search="
},
{
"operation": "search",
"time": "10.035",
"value": "Pseudomyrmex spinicola"
},
{
"operation": "Now on",
"time": "11.051",
"value": "Pseudomyrmex spinicola"
},
{
"operation": "Page search",
"time": "343.691",
"value": "aggre"
},
{
"operation": "Highlighting",
"time": "345.313",
"value": "Pseudomyrmex spinicola_sentence_4"
},
{
"operation": "finish",
"time": "351.078",
"value": "finish"
}
]
}
|
exfever_2832
|
Gorgeous Ladies of Wrestling is a women's professional wrestling promotion that began in 1986 and has continued in various forms after it left a telecommunication medium used for transmitting moving images in black-and-white or in color, and two or three dimensions and sound.
|
{
"evidence": [
"Gorgeous Ladies of Wrestling",
"Television"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nGorgeous Ladies of Wrestling is a women's professional wrestling promotion that began in 1986 and has continued in various forms after it left a telecommunication medium used for transmitting moving images in black-and-white or in color, and two or three dimensions and sound.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Gorgeous Ladies of Wrestling",
"Television"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2288,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
89512
|
Alaska Commercial Company (known as the Northern Commercial Company from 1901 to 1992) acquired the assets of the Russian-American Company in 1867; then in 1887, an ACC subsidiary was formed to breed blue foxes on Chirikof.
|
{
"evidence": [
"Alaska Commercial Company_sentence_1",
"Alaska Commercial Company_sentence_3"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAlaska Commercial Company (known as the Northern Commercial Company from 1901 to 1992) acquired the assets of the Russian-American Company in 1867; then in 1887, an ACC subsidiary was formed to breed blue foxes on Chirikof.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Alaska Commercial Company_sentence_1",
"Alaska Commercial Company_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2289,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.445",
"value": "?search="
},
{
"operation": "search",
"time": "92.462",
"value": "Alaska Commercial Company"
},
{
"operation": "Now on",
"time": "94.141",
"value": "Alaska Commercial Company"
},
{
"operation": "Highlighting",
"time": "98.472",
"value": "Alaska Commercial Company_sentence_1"
},
{
"operation": "Highlighting",
"time": "110.157",
"value": "Alaska Commercial Company_sentence_3"
},
{
"operation": "hyperlink",
"time": "269.801",
"value": "Maritime Fur Trade"
},
{
"operation": "Now on",
"time": "270.842",
"value": "Maritime fur trade"
},
{
"operation": "finish",
"time": "387.731",
"value": "finish"
}
]
}
|
exfever_5809
|
Gorgeous Ladies of Wrestling is organized by wrestling federations called promotions that began in 1986 and have continued in various forms after it left television.
|
{
"evidence": [
"Gorgeous Ladies of Wrestling",
"Women's professional wrestling"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nGorgeous Ladies of Wrestling is organized by wrestling federations called promotions that began in 1986 and have continued in various forms after it left television.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Gorgeous Ladies of Wrestling",
"Women's professional wrestling"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2290,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
58834
|
Newfoundland and Labrador Route 340 continues northwestward to intersect Route 331, a route that leads to ferries connecting Change Islands and Fogo Island with the main island.
|
{
"evidence": [
"Newfoundland and Labrador Route 340_sentence_8"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nNewfoundland and Labrador Route 340 continues northwestward to intersect Route 331, a route that leads to ferries connecting Change Islands and Fogo Island with the main island.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Newfoundland and Labrador Route 340_sentence_8"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2291,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.145",
"value": "?search="
},
{
"operation": "search",
"time": "15.576",
"value": "Route 331"
},
{
"operation": "Now on",
"time": "16.813",
"value": "List of highways numbered 331"
},
{
"operation": "hyperlink",
"time": "29.491",
"value": "Newfoundland and Labrador Route 331"
},
{
"operation": "Now on",
"time": "30.401",
"value": "Newfoundland and Labrador Route 331"
},
{
"operation": "search",
"time": "42.897",
"value": "Newfoundland and Labrador Route 340"
},
{
"operation": "Now on",
"time": "45.442",
"value": "Newfoundland and Labrador Route 340"
},
{
"operation": "Highlighting",
"time": "58.505",
"value": "Newfoundland and Labrador Route 340_sentence_8"
},
{
"operation": "finish",
"time": "75.973",
"value": "finish"
}
]
}
|
24443
|
Pratt was born in Boston, taught music and drama at Virginia and directed the Virginia Glee Club.
|
{
"evidence": [
"Harry Rogers Pratt_sentence_2",
"Harry Rogers Pratt_sentence_0",
"Harry Rogers Pratt_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:\nPratt was born in Boston, taught music and drama at Virginia and directed the Virginia Glee Club.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Harry Rogers Pratt_sentence_2",
"Harry Rogers Pratt_sentence_0",
"Harry Rogers Pratt_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2292,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.892",
"value": "?search="
},
{
"operation": "search",
"time": "12.493",
"value": "Pratt"
},
{
"operation": "Now on",
"time": "13.249",
"value": "Pratt"
},
{
"operation": "hyperlink",
"time": "34.259",
"value": "Andy Pratt (singer-songwriter)"
},
{
"operation": "Now on",
"time": "34.808",
"value": "Andy Pratt (singer-songwriter)"
},
{
"operation": "Page search",
"time": "56.602",
"value": "taught"
},
{
"operation": "back-button-clicked",
"time": "98.434",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "98.563",
"value": "Pratt"
},
{
"operation": "Page search",
"time": "139.46",
"value": "music"
},
{
"operation": "hyperlink",
"time": "146.446",
"value": "Harold Douglas Pratt Jr."
},
{
"operation": "Now on",
"time": "146.821",
"value": "Harold Douglas Pratt Jr."
},
{
"operation": "back-button-clicked",
"time": "158.509",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "158.611",
"value": "Pratt"
},
{
"operation": "Page search",
"time": "164.462",
"value": "music"
},
{
"operation": "search",
"time": "205.265",
"value": "Contains...Pratt was born in Boston"
},
{
"operation": "Now on",
"time": "207.199",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "222.158",
"value": "Harry Rogers Pratt"
},
{
"operation": "Now on",
"time": "222.818",
"value": "Harry Rogers Pratt"
},
{
"operation": "Highlighting",
"time": "225.744",
"value": "Harry Rogers Pratt_sentence_2"
},
{
"operation": "Highlighting",
"time": "238.403",
"value": "Harry Rogers Pratt_sentence_0"
},
{
"operation": "Page search",
"time": "254.879",
"value": "Glee"
},
{
"operation": "Highlighting",
"time": "257.099",
"value": "Harry Rogers Pratt_sentence_4"
},
{
"operation": "finish",
"time": "293.68",
"value": "finish"
}
]
}
|
75119
|
A Fine and Private Place is a fantasy novel by American writer Peter S. Beagle that was first published by Viking Press on May 23, 1960 and was later adapted into a musical by Erik Haagensen and Richard Isen.
|
{
"evidence": [
"A Fine and Private Place_sentence_1",
"A Fine and Private Place_sentence_2",
"A Fine and Private Place_sentence_40"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nA Fine and Private Place is a fantasy novel by American writer Peter S. Beagle that was first published by Viking Press on May 23, 1960 and was later adapted into a musical by Erik Haagensen and Richard Isen.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"A Fine and Private Place_sentence_1",
"A Fine and Private Place_sentence_2",
"A Fine and Private Place_sentence_40"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2293,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.429",
"value": "undefined"
},
{
"operation": "search",
"time": "7.896",
"value": "A Fine and Private Place"
},
{
"operation": "Now on",
"time": "9.013",
"value": "A Fine and Private Place"
},
{
"operation": "Highlighting",
"time": "13.356",
"value": "A Fine and Private Place_sentence_1"
},
{
"operation": "Highlighting",
"time": "20.916",
"value": "A Fine and Private Place_sentence_2"
},
{
"operation": "Highlighting",
"time": "41.481",
"value": "A Fine and Private Place_sentence_40"
},
{
"operation": "finish",
"time": "51.801",
"value": "finish"
}
]
}
|
42588
|
Sisa Koyamaibole belongs to Fiji, a team that was defeated by Wales but achieve victory over South Africa.
|
{
"evidence": [
"Sisa Koyamaibole_sentence_2"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSisa Koyamaibole belongs to Fiji, a team that was defeated by Wales but achieve victory over South Africa.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Sisa Koyamaibole_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2294,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.884",
"value": "?search="
},
{
"operation": "search",
"time": "9.479",
"value": "Sisa Koyamaibole"
},
{
"operation": "Now on",
"time": "10.42",
"value": "Sisa Koyamaibole"
},
{
"operation": "Highlighting",
"time": "31.938",
"value": "Sisa Koyamaibole_sentence_2"
},
{
"operation": "hyperlink",
"time": "38.83",
"value": "Fijian"
},
{
"operation": "Now on",
"time": "39.94",
"value": "Fiji"
},
{
"operation": "back-button-clicked",
"time": "44.396",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "44.449",
"value": "Sisa Koyamaibole"
},
{
"operation": "Page search",
"time": "60.366",
"value": "Fiji"
},
{
"operation": "Highlighting",
"time": "93.072",
"value": "Sisa Koyamaibole_sentence_12"
},
{
"operation": "Highlighting",
"time": "93.075",
"value": "Sisa Koyamaibole_section_0"
},
{
"operation": "Highlighting",
"time": "93.075",
"value": "Sisa Koyamaibole_section_1"
},
{
"operation": "Highlighting deleted",
"time": "117.852",
"value": "Sisa Koyamaibole_sentence_12"
},
{
"operation": "Highlighting deleted",
"time": "117.854",
"value": "Sisa Koyamaibole_section_0"
},
{
"operation": "Highlighting deleted",
"time": "117.855",
"value": "Sisa Koyamaibole_section_1"
},
{
"operation": "finish",
"time": "149.108",
"value": "finish"
}
]
}
|
exfever_7528
|
Florence is the capital city of Italy.
|
{
"evidence": [
"Leonardo da Vinci",
"Michelangelo"
],
"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:\nFlorence is the capital city of Italy.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Leonardo da Vinci",
"Michelangelo"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2295,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
13407
|
Fernando Morena was part of the team that won the Copa América in 1978, the oldest international football competition.
|
{
"evidence": [
"Fernando Morena_sentence_14"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nFernando Morena was part of the team that won the Copa América in 1978, the oldest international football competition.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Fernando Morena_sentence_14"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2296,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.82",
"value": "?search="
},
{
"operation": "search",
"time": "5.46",
"value": "Fernando Morena"
},
{
"operation": "Now on",
"time": "6.316",
"value": "Fernando Morena"
},
{
"operation": "Page search",
"time": "22.464",
"value": "1978"
},
{
"operation": "Highlighting",
"time": "25.224",
"value": "Fernando Morena_sentence_6"
},
{
"operation": "Highlighting",
"time": "25.225",
"value": "Fernando Morena_section_0"
},
{
"operation": "Page search",
"time": "52.787",
"value": "Copa"
},
{
"operation": "Highlighting",
"time": "66.103",
"value": "Fernando Morena_sentence_14"
},
{
"operation": "Highlighting deleted",
"time": "67.731",
"value": "Fernando Morena_sentence_6"
},
{
"operation": "Highlighting deleted",
"time": "67.733",
"value": "Fernando Morena_section_0"
},
{
"operation": "Page search",
"time": "75.341",
"value": "América"
},
{
"operation": "finish",
"time": "250.722",
"value": "finish"
}
]
}
|
exfever_2552
|
Aishwarya Rai is an actress who has received numerous accolades, including two awards that honor artistic and technical excellence in the Hindi-language film industry of a country in South Asia, which is the most populous democracy in the world.
|
{
"evidence": [
"Aishwarya Rai",
"Filmfare Awards",
"India"
],
"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:\nAishwarya Rai is an actress who has received numerous accolades, including two awards that honor artistic and technical excellence in the Hindi-language film industry of a country in South Asia, which is the most populous democracy in the world.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Aishwarya Rai",
"Filmfare Awards",
"India"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2297,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
39785
|
Patrick played college football for the Louisville Cardinals from 2007–2010, wherein he was the starting cornerback from 2008 to 2010 and recorded 53 tackles and two interceptions in 2009.
|
{
"evidence": [
"Johnny Patrick_sentence_4",
"Johnny Patrick_sentence_5",
"Johnny Patrick_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:\nPatrick played college football for the Louisville Cardinals from 2007–2010, wherein he was the starting cornerback from 2008 to 2010 and recorded 53 tackles and two interceptions in 2009.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Johnny Patrick_sentence_4",
"Johnny Patrick_sentence_5",
"Johnny Patrick_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2298,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.773",
"value": "?search="
},
{
"operation": "search",
"time": "36.489",
"value": "Louisville Cardinals football"
},
{
"operation": "Now on",
"time": "39.13",
"value": "Louisville Cardinals football"
},
{
"operation": "Page search",
"time": "51.19",
"value": "Patrick"
},
{
"operation": "hyperlink",
"time": "76.612",
"value": "Johnny Patrick"
},
{
"operation": "Now on",
"time": "77.312",
"value": "Johnny Patrick"
},
{
"operation": "Highlighting",
"time": "106.078",
"value": "Johnny Patrick_sentence_4"
},
{
"operation": "Highlighting",
"time": "108.345",
"value": "Johnny Patrick_sentence_5"
},
{
"operation": "Highlighting",
"time": "112.735",
"value": "Johnny Patrick_sentence_6"
},
{
"operation": "finish",
"time": "122.851",
"value": "finish"
}
]
}
|
exfever_1478
|
Dracula is a novel by a Belgian author.
|
{
"evidence": [
"Dracula",
"Bram Stoker"
],
"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:\nDracula is a novel by a Belgian author.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Dracula",
"Bram Stoker"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2299,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
17352
|
In 1904, Henry Littleton Groom unsuccessfully contested the seat of Drayton and Toowoomba in the Philippines and as a politician he was inferior to his younger brother, Littleton Groom.
|
{
"evidence": [
"Henry Littleton Groom_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:\nIn 1904, Henry Littleton Groom unsuccessfully contested the seat of Drayton and Toowoomba in the Philippines and as a politician he was inferior to his younger brother, Littleton Groom.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Henry Littleton Groom_sentence_6"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2300,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.942",
"value": "?search="
},
{
"operation": "search",
"time": "12.298",
"value": "Henry Littleton Groom"
},
{
"operation": "Now on",
"time": "13.18",
"value": "Henry Littleton Groom"
},
{
"operation": "Highlighting",
"time": "36.153",
"value": "Henry Littleton Groom_sentence_6"
},
{
"operation": "hyperlink",
"time": "50.429",
"value": "Queensland Legislative Assembly"
},
{
"operation": "Now on",
"time": "51.091",
"value": "Legislative Assembly of Queensland"
},
{
"operation": "back-button-clicked",
"time": "67.918",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "68.027",
"value": "Henry Littleton Groom"
},
{
"operation": "finish",
"time": "83.73",
"value": "finish"
}
]
}
|
exfever_7248
|
Jerry Maguire is a 1997 American romantic comedy-drama sports film that stars an American actress and director who received various accolades, including an Academy Award, a Golden Globe Award, three Peabody Awards, and four Primetime Emmy Awards.
|
{
"evidence": [
"Jerry Maguire",
"Regina King"
],
"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:\nJerry Maguire is a 1997 American romantic comedy-drama sports film that stars an American actress and director who received various accolades, including an Academy Award, a Golden Globe Award, three Peabody Awards, and four Primetime Emmy Awards.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jerry Maguire",
"Regina King"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2301,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4015
|
Legion is a fictional character appearing in Japanese comic books published under the brand name and primary imprint of Marvel Worldwide Inc., formerly Marvel Publishing, Inc.
|
{
"evidence": [
"Legion (Marvel Comics)",
"Marvel Comics"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nLegion is a fictional character appearing in Japanese comic books published under the brand name and primary imprint of Marvel Worldwide Inc., formerly Marvel Publishing, Inc.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Legion (Marvel Comics)",
"Marvel Comics"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2302,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8640
|
Grunge is an alternative ballad genre and features guitar sound that is a form of audio signal processing used to alter the sound of amplified electric musical instruments.
|
{
"evidence": [
"Grunge",
"Distortion (music)"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nGrunge is an alternative ballad genre and features guitar sound that is a form of audio signal processing used to alter the sound of amplified electric musical instruments.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Grunge",
"Distortion (music)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2303,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
77103
|
After the Ottoman conquest in the 13th and 16th centuries, large migrations of Serbs (distinguished themselves as warriors and diplomats) followed into the Pannonian Plain.
|
{
"evidence": [
"Serbian nobility_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:\nAfter the Ottoman conquest in the 13th and 16th centuries, large migrations of Serbs (distinguished themselves as warriors and diplomats) followed into the Pannonian Plain.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Serbian nobility_sentence_7"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2304,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.694",
"value": "?search="
},
{
"operation": "search",
"time": "340.737",
"value": "Serbian nobility"
},
{
"operation": "Now on",
"time": "341.757",
"value": "Serbian nobility"
},
{
"operation": "Highlighting",
"time": "352.864",
"value": "Serbian nobility_sentence_7"
},
{
"operation": "finish",
"time": "364.474",
"value": "finish"
}
]
}
|
14646
|
Lipovec pri Kostelu (big remote settlement) is in America under Kostel Municipality and it has a total area of 0.3 km with a total population of 250 last 2017.
|
{
"evidence": [
"Lipovec pri Kostelu_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:\nLipovec pri Kostelu (big remote settlement) is in America under Kostel Municipality and it has a total area of 0.3 km with a total population of 250 last 2017.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Lipovec pri Kostelu_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2305,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "3.005",
"value": "?search="
},
{
"operation": "search",
"time": "29.058",
"value": "Lipovec pri Kostelu"
},
{
"operation": "Now on",
"time": "29.983",
"value": "Lipovec pri Kostelu"
},
{
"operation": "Highlighting",
"time": "55.357",
"value": "Lipovec pri Kostelu_sentence_0"
},
{
"operation": "finish",
"time": "92.969",
"value": "finish"
}
]
}
|
51106
|
Paul Ashbee noted that the close clustering in the same area was reminiscent of the megalithic tomb-shrine traditions of continental Northern Europe, yet there is little evidence for deposition within the tomb shrines.
|
{
"evidence": [
"Medway Megaliths_sentence_63",
"Medway Megaliths_sentence_65"
],
"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:\nPaul Ashbee noted that the close clustering in the same area was reminiscent of the megalithic tomb-shrine traditions of continental Northern Europe, yet there is little evidence for deposition within the tomb shrines.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Medway Megaliths_sentence_63",
"Medway Megaliths_sentence_65"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2306,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.806",
"value": "?search="
},
{
"operation": "Now on",
"time": "13.33",
"value": "?search="
},
{
"operation": "search",
"time": "75.217",
"value": "Medway Megaliths"
},
{
"operation": "Now on",
"time": "76.273",
"value": "Medway Megaliths"
},
{
"operation": "Page search",
"time": "88.763",
"value": "Paul Ashbee"
},
{
"operation": "Highlighting",
"time": "123.921",
"value": "Medway Megaliths_sentence_63"
},
{
"operation": "Highlighting",
"time": "135.84",
"value": "Medway Megaliths_sentence_65"
},
{
"operation": "finish",
"time": "146.123",
"value": "finish"
}
]
}
|
exfever_4531
|
Brian Thomas Helgeland is an American screenwriter who wrote and directed the 2013 American biographical sports film about soccer player Jackie Robinson.
|
{
"evidence": [
"Brian Helgeland",
"42 (film)"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nBrian Thomas Helgeland is an American screenwriter who wrote and directed the 2013 American biographical sports film about soccer player Jackie Robinson.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Brian Helgeland",
"42 (film)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2307,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
29109
|
George Vertue was an English engraver and antiquary, who, at the age of 13, was apprenticed to a prominent heraldic engraver of French origin and later worked seven years under Michael Vandergucht, before operating independently, and eventually to become the first members of Godfrey Kneller's London Academy of Painting.
|
{
"evidence": [
"George Vertue_sentence_2",
"George Vertue_sentence_4",
"George Vertue_sentence_5",
"George Vertue_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:\nGeorge Vertue was an English engraver and antiquary, who, at the age of 13, was apprenticed to a prominent heraldic engraver of French origin and later worked seven years under Michael Vandergucht, before operating independently, and eventually to become the first members of Godfrey Kneller's London Academy of Painting.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"George Vertue_sentence_2",
"George Vertue_sentence_4",
"George Vertue_sentence_5",
"George Vertue_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2308,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.859",
"value": "?search="
},
{
"operation": "search",
"time": "36.165",
"value": "George Vertue"
},
{
"operation": "Now on",
"time": "37.444",
"value": "George Vertue"
},
{
"operation": "Highlighting",
"time": "47.133",
"value": "George Vertue_sentence_2"
},
{
"operation": "Highlighting",
"time": "51.259",
"value": "George Vertue_sentence_4"
},
{
"operation": "Highlighting",
"time": "57.501",
"value": "George Vertue_sentence_5"
},
{
"operation": "Highlighting",
"time": "64.605",
"value": "George Vertue_sentence_6"
},
{
"operation": "finish",
"time": "78.273",
"value": "finish"
}
]
}
|
18738
|
Ramy Rabia is an Algerian professional footballer who played for the Egypt National Football Team from 2012 to 2019 and made a total of 23 apps and 3 goals.
|
{
"evidence": [
"Ramy Rabia_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:\nRamy Rabia is an Algerian professional footballer who played for the Egypt National Football Team from 2012 to 2019 and made a total of 23 apps and 3 goals.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Ramy Rabia_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2309,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.555",
"value": "?search="
},
{
"operation": "search",
"time": "11.558",
"value": "Ramy Rabia"
},
{
"operation": "Now on",
"time": "13.394",
"value": "Ramy Rabia"
},
{
"operation": "Highlighting",
"time": "18.525",
"value": "Ramy Rabia_sentence_1"
},
{
"operation": "Page search",
"time": "29.167",
"value": "algerian"
},
{
"operation": "finish",
"time": "45.352",
"value": "finish"
}
]
}
|
33383
|
The Zhongruan, which is a plucked string instrument played with a plectrum is generally of plastic or ivory with pegs of wood or buffalo horn.
|
{
"evidence": [
"Zhongruan_sentence_2",
"Zhongruan_sentence_4",
"Zhongruan_sentence_18",
"Zhongruan_sentence_20"
],
"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 Zhongruan, which is a plucked string instrument played with a plectrum is generally of plastic or ivory with pegs of wood or buffalo horn.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Zhongruan_sentence_2",
"Zhongruan_sentence_4",
"Zhongruan_sentence_18",
"Zhongruan_sentence_20"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2310,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.938",
"value": "?search="
},
{
"operation": "search",
"time": "12.367",
"value": "Zhongruan"
},
{
"operation": "Now on",
"time": "13.743",
"value": "Zhongruan"
},
{
"operation": "Highlighting",
"time": "16.246",
"value": "Zhongruan_sentence_2"
},
{
"operation": "Highlighting",
"time": "21.485",
"value": "Zhongruan_sentence_4"
},
{
"operation": "Highlighting",
"time": "55.259",
"value": "Zhongruan_sentence_18"
},
{
"operation": "Highlighting",
"time": "61.441",
"value": "Zhongruan_sentence_20"
},
{
"operation": "finish",
"time": "91.483",
"value": "finish"
}
]
}
|
66663
|
Changyon County is in the South Hwanghae Province in South Korea.
|
{
"evidence": [
"Changyon County_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:\nChangyon County is in the South Hwanghae Province in South Korea.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Changyon County_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2311,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.719",
"value": "?search="
},
{
"operation": "search",
"time": "10.009",
"value": "Changyon County"
},
{
"operation": "Now on",
"time": "10.694",
"value": "Changyon County"
},
{
"operation": "Highlighting",
"time": "13.099",
"value": "Changyon County_sentence_0"
},
{
"operation": "finish",
"time": "22.272",
"value": "finish"
}
]
}
|
65860
|
The planned payload weight for the Ju 322 was reduced to 16,000 kg, and later to 11,000 kg; then its maiden flight in April 1941 was towed by a Junkers Ju 90 (a 40-seat, four-engine airliner developed for and used by Deutsche Luft Hansa).
|
{
"evidence": [
"Junkers Ju 322_sentence_8",
"Junkers Ju 322_sentence_9",
"Junkers Ju 90_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 planned payload weight for the Ju 322 was reduced to 16,000 kg, and later to 11,000 kg; then its maiden flight in April 1941 was towed by a Junkers Ju 90 (a 40-seat, four-engine airliner developed for and used by Deutsche Luft Hansa).\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Junkers Ju 322_sentence_8",
"Junkers Ju 322_sentence_9",
"Junkers Ju 90_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2312,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.73",
"value": "?search="
},
{
"operation": "search",
"time": "14.176",
"value": "Ju 322"
},
{
"operation": "Now on",
"time": "23.612",
"value": "Junkers Ju 322"
},
{
"operation": "Highlighting",
"time": "54.599",
"value": "Junkers Ju 322_sentence_8"
},
{
"operation": "Highlighting",
"time": "62.178",
"value": "Junkers Ju 322_sentence_9"
},
{
"operation": "hyperlink",
"time": "74.65",
"value": "Junkers Ju 90"
},
{
"operation": "Now on",
"time": "76.42",
"value": "Junkers Ju 90"
},
{
"operation": "Highlighting",
"time": "79.124",
"value": "Junkers Ju 90_sentence_0"
},
{
"operation": "finish",
"time": "205.221",
"value": "finish"
}
]
}
|
exfever_1289
|
Unapologetic is the eight studio album by Barbadian singer Rihanna, which enlisted previous collaborators, including a record producing and songwriting team based in Los Angeles.
|
{
"evidence": [
"Unapologetic",
"Stargate (music producers)"
],
"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:\nUnapologetic is the eight studio album by Barbadian singer Rihanna, which enlisted previous collaborators, including a record producing and songwriting team based in Los Angeles.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Unapologetic",
"Stargate (music producers)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2313,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7580
|
Jerry Lewis was an American comedian, actor, singer, director, producer, writer, and humanitarian who made his debut in 1946 as part of the famous duo with an American singer, actor, and comedian of Ivorian descent.
|
{
"evidence": [
"Jerry Lewis",
"Dean Martin"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJerry Lewis was an American comedian, actor, singer, director, producer, writer, and humanitarian who made his debut in 1946 as part of the famous duo with an American singer, actor, and comedian of Ivorian descent.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jerry Lewis",
"Dean Martin"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2314,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5604
|
The 1983–84 NBA season ended with the Boston Celtics winning, beating an American professional team in a sport in which three teams compete with the objective of shooting through the defender's hoop.
|
{
"evidence": [
"1983–84 NBA season",
"Los Angeles Lakers",
"Basketball"
],
"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 1983–84 NBA season ended with the Boston Celtics winning, beating an American professional team in a sport in which three teams compete with the objective of shooting through the defender's hoop.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"1983–84 NBA season",
"Los Angeles Lakers",
"Basketball"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2315,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
2511
|
Robert Bateman Paul was ordained deacon and priest in 1822 before becoming an Archdeacon of Nelson in New Zealand from 1855 to 1860.
|
{
"evidence": [
"Bateman Paul_sentence_2",
"Bateman Paul_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:\nRobert Bateman Paul was ordained deacon and priest in 1822 before becoming an Archdeacon of Nelson in New Zealand from 1855 to 1860.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Bateman Paul_sentence_2",
"Bateman Paul_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2316,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "14.704",
"value": "Robert Bateman Paul"
},
{
"operation": "Highlighting",
"time": "30.105",
"value": "Bateman Paul_sentence_2"
},
{
"operation": "Highlighting",
"time": "37.31",
"value": "Bateman Paul_sentence_5"
},
{
"operation": "finish",
"time": "54.947",
"value": "finish"
}
]
}
|
76113
|
Stephen Joshua Solarz left Manila just as Benigno S. Aquino Jr. was coming home to challenge President Ferdinand E. Marcos (10th President of the Philippines), nevertheless he is remembered for his leadership on the Philippines.
|
{
"evidence": [
"Stephen Solarz_sentence_19",
"Stephen Solarz_sentence_18",
"History of the Philippines under Ferdinand Marcos_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:\nStephen Joshua Solarz left Manila just as Benigno S. Aquino Jr. was coming home to challenge President Ferdinand E. Marcos (10th President of the Philippines), nevertheless he is remembered for his leadership on the Philippines.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Stephen Solarz_sentence_19",
"Stephen Solarz_sentence_18",
"History of the Philippines under Ferdinand Marcos_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2317,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.161",
"value": "?search="
},
{
"operation": "search",
"time": "14.079",
"value": "Stephen Joshua Solarz"
},
{
"operation": "Now on",
"time": "14.78",
"value": "Stephen Solarz"
},
{
"operation": "Page search",
"time": "29.412",
"value": "aquino"
},
{
"operation": "Highlighting",
"time": "37.102",
"value": "Stephen Solarz_sentence_19"
},
{
"operation": "hyperlink",
"time": "45.911",
"value": "President"
},
{
"operation": "Now on",
"time": "46.94",
"value": "President of the Philippines"
},
{
"operation": "back-button-clicked",
"time": "50.432",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "50.821",
"value": "Stephen Solarz"
},
{
"operation": "Page search",
"time": "70.974",
"value": "leadership"
},
{
"operation": "Highlighting",
"time": "79.39",
"value": "Stephen Solarz_sentence_18"
},
{
"operation": "search",
"time": "103.736",
"value": "ferdinand marcos"
},
{
"operation": "Now on",
"time": "104.808",
"value": "undefined"
},
{
"operation": "search",
"time": "124.433",
"value": "Marcos"
},
{
"operation": "Now on",
"time": "125.114",
"value": "Marcos"
},
{
"operation": "back-button-clicked",
"time": "150.089",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "150.624",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "151.24",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "151.253",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "151.449",
"value": "Stephen Solarz"
},
{
"operation": "hyperlink",
"time": "167.476",
"value": "President"
},
{
"operation": "Now on",
"time": "167.968",
"value": "President of the Philippines"
},
{
"operation": "Page search",
"time": "179.389",
"value": "marcos"
},
{
"operation": "hyperlink",
"time": "260.606",
"value": "List of presidents of the Philippines"
},
{
"operation": "Now on",
"time": "261.253",
"value": "List of presidents of the Philippines"
},
{
"operation": "Page search",
"time": "265.392",
"value": "marcos"
},
{
"operation": "hyperlink",
"time": "319.466",
"value": "List of unofficial presidents of the Philippines"
},
{
"operation": "Now on",
"time": "320.287",
"value": "List of unofficial presidents of the Philippines"
},
{
"operation": "Page search",
"time": "325.174",
"value": "marcos"
},
{
"operation": "back-button-clicked",
"time": "345.117",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "345.297",
"value": "List of presidents of the Philippines"
},
{
"operation": "Page search",
"time": "357.676",
"value": "marcos"
},
{
"operation": "Highlighting",
"time": "372.301",
"value": "List of presidents of the Philippines_sentence_28"
},
{
"operation": "Highlighting",
"time": "372.302",
"value": "List of presidents of the Philippines_title"
},
{
"operation": "Highlighting",
"time": "372.303",
"value": "List of presidents of the Philippines_section_1"
},
{
"operation": "hyperlink",
"time": "378.149",
"value": "dictatorship of Marcos"
},
{
"operation": "Now on",
"time": "378.916",
"value": "History of the Philippines under Ferdinand Marcos"
},
{
"operation": "Page search",
"time": "393.134",
"value": "president"
},
{
"operation": "Highlighting",
"time": "405.629",
"value": "History of the Philippines under Ferdinand Marcos_sentence_3"
},
{
"operation": "finish",
"time": "428.669",
"value": "finish"
}
]
}
|
exfever_1979
|
"Touch My Body" was Mariah Carey's best-selling single of all time.?
|
{
"evidence": [
"Touch My Body",
"Album"
],
"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\"Touch My Body\" was Mariah Carey's best-selling single of all time.?\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Touch My Body",
"Album"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2318,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7889
|
New Horizons was launched as a part of a series of space exploration missions being conducted by NASA.
|
{
"evidence": [
"New Horizons",
"New Frontiers program"
],
"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:\nNew Horizons was launched as a part of a series of space exploration missions being conducted by NASA.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"New Horizons",
"New Frontiers program"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2319,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6421
|
Beowulf tells the story of the Scandinavian hero Beowulf, who gains fame as a young man by vanquishing the monster Grendel and Grendel's mother.
|
{
"evidence": [
"Middle-earth",
"Midgard"
],
"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:\nBeowulf tells the story of the Scandinavian hero Beowulf, who gains fame as a young man by vanquishing the monster Grendel and Grendel's mother.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Middle-earth",
"Midgard"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2320,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8534
|
Shallow Hal is a film directed by the American screenwriters.
|
{
"evidence": [
"Shallow Hal",
"Farrelly brothers"
],
"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:\nShallow Hal is a film directed by the American screenwriters.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Shallow Hal",
"Farrelly brothers"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2321,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3857
|
Naruto is a Japanese manga series based on two comics composed of a single standalone issue or chapter by Kishimoto.
|
{
"evidence": [
"Naruto",
"One-shot (comics)"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nNaruto is a Japanese manga series based on two comics composed of a single standalone issue or chapter by Kishimoto.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Naruto",
"One-shot (comics)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2322,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3147
|
Lion by Garth Davis became one of the highest-grossing Australian films of all time.
|
{
"evidence": [
"Lion (2016 film)",
"Dev Patel",
"Screen Actors Guild 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:\nLion by Garth Davis became one of the highest-grossing Australian films of all time.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Lion (2016 film)",
"Dev Patel",
"Screen Actors Guild Award"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2323,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4234
|
John D. Rockefeller was an Italian businessman born into a large family in a geographic region consisting of the portion of New York State lying north of the largest metropolitan area in the world by urban landmass.
|
{
"evidence": [
"John D. Rockefeller",
"Upstate New York",
"New York metropolitan area"
],
"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:\nJohn D. Rockefeller was an Italian businessman born into a large family in a geographic region consisting of the portion of New York State lying north of the largest metropolitan area in the world by urban landmass.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"John D. Rockefeller",
"Upstate New York",
"New York metropolitan area"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2324,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3914
|
Give Me Everything is a song by American rapper Pitbull featuring Shaffer Chimere Smith, a singer, dancer, and record producer.
|
{
"evidence": [
"Give Me Everything",
"Ne-Yo"
],
"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:\nGive Me Everything is a song by American rapper Pitbull featuring Shaffer Chimere Smith, a singer, dancer, and record producer.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Give Me Everything",
"Ne-Yo"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2325,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5248
|
A federal parliamentary constitutional monarchy is a form of monarchy in which the monarch exercises their authority in accordance with a constitution and is not alone in deciding.
|
{
"evidence": [
"Australia",
"Oceania"
],
"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 federal parliamentary constitutional monarchy is a form of monarchy in which the monarch exercises their authority in accordance with a constitution and is not alone in deciding.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Australia",
"Oceania"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2326,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2823
|
The song "7 Things" was co-written by Miley Cyrus, Tim James, and an American songwriter, record producer, music producer, and businesswoman.
|
{
"evidence": [
"7 Things",
"Antonina Armato"
],
"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 song \"7 Things\" was co-written by Miley Cyrus, Tim James, and an American songwriter, record producer, music producer, and businesswoman.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"7 Things",
"Antonina Armato"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2327,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
35677
|
SIU has a very active International Office, headed by Dr. Okello Andrew, that has seen the University through its many partnerships with leading universities neither within Europe nor within East Africa.
|
{
"evidence": [
"Somali International University_sentence_22"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSIU has a very active International Office, headed by Dr. Okello Andrew, that has seen the University through its many partnerships with leading universities neither within Europe nor within East Africa.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Somali International University_sentence_22"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2328,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.001",
"value": "?search="
},
{
"operation": "search",
"time": "0.009",
"value": "SIU"
},
{
"operation": "Now on",
"time": "0.01",
"value": "SIU"
},
{
"operation": "hyperlink",
"time": "0.022",
"value": "Southern Illinois University"
},
{
"operation": "Now on",
"time": "0.022",
"value": "Southern Illinois University"
},
{
"operation": "Page search",
"time": "0.028",
"value": "Okello"
},
{
"operation": "search",
"time": "0.048",
"value": "headed by Dr. Okello Andrew"
},
{
"operation": "Now on",
"time": "0.049",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "0.052",
"value": "Somali International University"
},
{
"operation": "Now on",
"time": "0.052",
"value": "Somali International University"
},
{
"operation": "Page search",
"time": "0.056",
"value": "active"
},
{
"operation": "Page search",
"time": "0.063",
"value": "international"
},
{
"operation": "Page search",
"time": "0.066",
"value": "international office"
},
{
"operation": "Highlighting",
"time": "0.07",
"value": "Somali International University_sentence_22"
},
{
"operation": "Highlighting",
"time": "0.077",
"value": "Somali International University_sentence_24"
},
{
"operation": "Highlighting deleted",
"time": "0.092",
"value": "Somali International University_sentence_24"
},
{
"operation": "finish",
"time": "0.147",
"value": "finish"
},
{
"operation": "Now on",
"time": "1620416098.689",
"value": "Somali International University"
},
{
"operation": "search",
"time": "1620416106.235",
"value": "SIU"
},
{
"operation": "Now on",
"time": "1620416106.783",
"value": "SIU"
},
{
"operation": "finish",
"time": "1620416117.93",
"value": "finish"
}
]
}
|
57687
|
Boracay, an inlet within the Croajingolong National Park, in the East Gippsland region of Victoria, Australia, covers a surface area of 38 hectares (94 acres) and features a ranger-managed camping ground, about an hour's drive from the nearest town, Cann River, along a rough stretch of dirt road.
|
{
"evidence": [
"Boracay_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:\nBoracay, an inlet within the Croajingolong National Park, in the East Gippsland region of Victoria, Australia, covers a surface area of 38 hectares (94 acres) and features a ranger-managed camping ground, about an hour's drive from the nearest town, Cann River, along a rough stretch of dirt road.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Boracay_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2329,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.809",
"value": "?search="
},
{
"operation": "search",
"time": "37.76",
"value": "Boracay"
},
{
"operation": "Now on",
"time": "39.042",
"value": "Boracay"
},
{
"operation": "hyperlink",
"time": "82.135",
"value": "Visayas"
},
{
"operation": "Now on",
"time": "83.111",
"value": "Visayas"
},
{
"operation": "back-button-clicked",
"time": "88.362",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "88.493",
"value": "Boracay"
},
{
"operation": "Highlighting",
"time": "91.568",
"value": "Boracay_sentence_0"
},
{
"operation": "finish",
"time": "100.265",
"value": "finish"
}
]
}
|
89977
|
In Spring in Fialta is misremembered as having been a story written by Vladimir Nadokov born in 1899, where Nina is attractive and had multiple affairs while Victor lacks the conviction of true love
|
{
"evidence": [
"Spring in Fialta_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:\nIn Spring in Fialta is misremembered as having been a story written by Vladimir Nadokov born in 1899, where Nina is attractive and had multiple affairs while Victor lacks the conviction of true love\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Spring in Fialta_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2330,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.189",
"value": "?search="
},
{
"operation": "search",
"time": "9.636",
"value": "Spring in Fialta"
},
{
"operation": "Now on",
"time": "10.721",
"value": "Spring in Fialta"
},
{
"operation": "Highlighting",
"time": "13.712",
"value": "Spring in Fialta_sentence_0"
},
{
"operation": "finish",
"time": "17.95",
"value": "finish"
}
]
}
|
87001
|
Mahakörgis Khan was given the title Ükegtü, they fought Tümeds and defeated Oirads who are part of Mongols.
|
{
"evidence": [
"Mahakörgis Khan_sentence_0",
"Mahakörgis Khan_sentence_8",
"Mahakörgis Khan_sentence_6",
"Tumed_sentence_13",
"Tumed_sentence_14",
"Mahakörgis Khan_sentence_5",
"Oirats_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:\nMahakörgis Khan was given the title Ükegtü, they fought Tümeds and defeated Oirads who are part of Mongols.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Mahakörgis Khan_sentence_0",
"Mahakörgis Khan_sentence_8",
"Mahakörgis Khan_sentence_6",
"Tumed_sentence_13",
"Tumed_sentence_14",
"Mahakörgis Khan_sentence_5",
"Oirats_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2331,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.115",
"value": "undefined"
},
{
"operation": "search",
"time": "10.368",
"value": "Mahakörgis Khan"
},
{
"operation": "Now on",
"time": "11.398",
"value": "Mahakörgis Khan"
},
{
"operation": "Page search",
"time": "23.644",
"value": "Ükegtü"
},
{
"operation": "Highlighting",
"time": "39.546",
"value": "Mahakörgis Khan_sentence_0"
},
{
"operation": "Highlighting",
"time": "40.815",
"value": "Mahakörgis Khan_sentence_8"
},
{
"operation": "Highlighting",
"time": "51.472",
"value": "Mahakörgis Khan_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "57.456",
"value": "Mahakörgis Khan_sentence_5"
},
{
"operation": "Page search",
"time": "67.628",
"value": "Tümeds"
},
{
"operation": "Highlighting",
"time": "103.45",
"value": "Mahakörgis Khan_sentence_6"
},
{
"operation": "hyperlink",
"time": "106.698",
"value": "Tümeds"
},
{
"operation": "Now on",
"time": "108.649",
"value": "Tümed"
},
{
"operation": "Highlighting",
"time": "154.934",
"value": "Tumed_sentence_13"
},
{
"operation": "Highlighting",
"time": "159.275",
"value": "Tumed_sentence_14"
},
{
"operation": "back-button-clicked",
"time": "164.709",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "164.998",
"value": "Mahakörgis Khan"
},
{
"operation": "Page search",
"time": "194.344",
"value": "fought"
},
{
"operation": "Highlighting",
"time": "211.751",
"value": "Mahakörgis Khan_sentence_5"
},
{
"operation": "hyperlink",
"time": "213.99",
"value": "Oirads"
},
{
"operation": "Now on",
"time": "215.169",
"value": "Oirats"
},
{
"operation": "Highlighting",
"time": "221.975",
"value": "Oirats_sentence_2"
},
{
"operation": "back-button-clicked",
"time": "229.354",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "229.632",
"value": "Mahakörgis Khan"
},
{
"operation": "hyperlink",
"time": "260.152",
"value": "Tümeds"
},
{
"operation": "Now on",
"time": "260.763",
"value": "Tümed"
},
{
"operation": "back-button-clicked",
"time": "270.105",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "270.372",
"value": "Mahakörgis Khan"
},
{
"operation": "hyperlink",
"time": "305.882",
"value": "Tümeds"
},
{
"operation": "Now on",
"time": "306.815",
"value": "Tümed"
},
{
"operation": "Page search",
"time": "315.417",
"value": "Mahakörgis Khan"
},
{
"operation": "finish",
"time": "333.443",
"value": "finish"
}
]
}
|
exfever_678
|
The Strain is an Afghan horror drama television series whose pilot episode, "Night Zero," premiered at the ATX Television Festival in the capital city, as well as the seat and largest city of Travis County.
|
{
"evidence": [
"The Strain (TV series)",
"Austin, Texas"
],
"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 Strain is an Afghan horror drama television series whose pilot episode, \"Night Zero,\" premiered at the ATX Television Festival in the capital city, as well as the seat and largest city of Travis County.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Strain (TV series)",
"Austin, Texas"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2332,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3925
|
Mark Wahlberg's Net Worth is $300 Million.
|
{
"evidence": [
"Mark Wahlberg",
"The Italian Job (2003 film)"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMark Wahlberg's Net Worth is $300 Million.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Mark Wahlberg",
"The Italian Job (2003 film)"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2333,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5547
|
Mammal is the largest group of vertebrates.
|
{
"evidence": [
"Mammal",
"Fur",
"Thermal insulation"
],
"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:\nMammal is the largest group of vertebrates.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Mammal",
"Fur",
"Thermal insulation"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2334,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8407
|
Attack the Block is a 2011 British science fiction comedy horror film written and directed by Joe Cornish and starring an English actress who came to prominence in a 2006 feature film debut Venus.
|
{
"evidence": [
"Attack the Block",
"Jodie Whittaker"
],
"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:\nAttack the Block is a 2011 British science fiction comedy horror film written and directed by Joe Cornish and starring an English actress who came to prominence in a 2006 feature film debut Venus.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Attack the Block",
"Jodie Whittaker"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2335,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
16578
|
Shulin, a 33.1288 km (12.7911 sq mi) land located in New Taipei City, China, a country in East Asia, has a total population of 183,946 in December 2018.
|
{
"evidence": [
"Shulin District_sentence_2"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nShulin, a 33.1288 km (12.7911 sq mi) land located in New Taipei City, China, a country in East Asia, has a total population of 183,946 in December 2018.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Shulin District_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2336,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.87",
"value": "?search="
},
{
"operation": "search",
"time": "22.725",
"value": "Shulini"
},
{
"operation": "Now on",
"time": "23.634",
"value": "Shulini"
},
{
"operation": "search",
"time": "38.789",
"value": "Shulin District"
},
{
"operation": "Now on",
"time": "39.896",
"value": "Shulin District"
},
{
"operation": "Highlighting",
"time": "57.77",
"value": "Shulin District_header_cell_0_6_0"
},
{
"operation": "Highlighting",
"time": "58.495",
"value": "Shulin District_header_cell_0_7_0"
},
{
"operation": "Highlighting",
"time": "59.526",
"value": "Shulin District_cell_0_7_1"
},
{
"operation": "Highlighting",
"time": "59.543",
"value": "Shulin District_header_cell_0_7_0"
},
{
"operation": "Highlighting",
"time": "59.547",
"value": "Shulin District_header_cell_0_6_0"
},
{
"operation": "Highlighting",
"time": "84.929",
"value": "Shulin District_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "91.287",
"value": "Shulin District_cell_0_7_1"
},
{
"operation": "Highlighting deleted",
"time": "91.3",
"value": "Shulin District_header_cell_0_7_0"
},
{
"operation": "Highlighting deleted",
"time": "91.304",
"value": "Shulin District_header_cell_0_6_0"
},
{
"operation": "finish",
"time": "113.536",
"value": "finish"
}
]
}
|
22352
|
Portuguese sports club União Desportiva Oliveirense won the Segunda Divisão – Zona Centro ahead of 18 other teams, promoting them to Liga de Honra.
|
{
"evidence": [
"U.D. Oliveirense_sentence_18",
"U.D. Oliveirense_sentence_23",
"U.D. Oliveirense (basketball)_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:\nPortuguese sports club União Desportiva Oliveirense won the Segunda Divisão – Zona Centro ahead of 18 other teams, promoting them to Liga de Honra.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"U.D. Oliveirense_sentence_18",
"U.D. Oliveirense_sentence_23",
"U.D. Oliveirense (basketball)_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2337,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.63",
"value": "undefined"
},
{
"operation": "search",
"time": "32.528",
"value": "Segunda Divisão – Zona Centro"
},
{
"operation": "Now on",
"time": "34.031",
"value": "undefined"
},
{
"operation": "search",
"time": "83.315",
"value": "U.D. Oliveirense"
},
{
"operation": "Now on",
"time": "84.211",
"value": "U.D. Oliveirense"
},
{
"operation": "Page search",
"time": "87.543",
"value": "promote"
},
{
"operation": "Highlighting",
"time": "93.512",
"value": "U.D. Oliveirense_sentence_18"
},
{
"operation": "Page search",
"time": "197.431",
"value": "honra"
},
{
"operation": "Highlighting",
"time": "202.612",
"value": "U.D. Oliveirense_sentence_23"
},
{
"operation": "hyperlink",
"time": "421.216",
"value": "U.D. Oliveirense (basketball)"
},
{
"operation": "Now on",
"time": "422.226",
"value": "Oliveirense Basquetebol"
},
{
"operation": "Page search",
"time": "426.918",
"value": "honra"
},
{
"operation": "Highlighting",
"time": "439.6",
"value": "U.D. Oliveirense (basketball)_sentence_0"
},
{
"operation": "back-button-clicked",
"time": "443.956",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "443.993",
"value": "U.D. Oliveirense"
},
{
"operation": "search",
"time": "465.42",
"value": "U. D. Oliveirense"
},
{
"operation": "Now on",
"time": "466.132",
"value": "U.D. Oliveirense"
},
{
"operation": "search",
"time": "479.471",
"value": "u. d. oliveirense football"
},
{
"operation": "Now on",
"time": "480.954",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "488.735",
"value": "U.D. Oliveirense (basketball)"
},
{
"operation": "Now on",
"time": "489.26",
"value": "U.D. Oliveirense (basketball)"
},
{
"operation": "hyperlink",
"time": "493.836",
"value": "football"
},
{
"operation": "Now on",
"time": "494.698",
"value": "Association football"
},
{
"operation": "finish",
"time": "537.506",
"value": "finish"
}
]
}
|
7785
|
Pomona Fox Theater is wrongly believed to be Pomona, Los Angeles County, California and was a first-run theater for many years but closed in 1977 for years before reopening in 1998.
|
{
"evidence": [
"Pomona Fox Theater_sentence_1",
"Pomona Fox Theater_sentence_4",
"Pomona Fox Theater_sentence_5",
"Pomona Fox Theater_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:\nPomona Fox Theater is wrongly believed to be Pomona, Los Angeles County, California and was a first-run theater for many years but closed in 1977 for years before reopening in 1998.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Pomona Fox Theater_sentence_1",
"Pomona Fox Theater_sentence_4",
"Pomona Fox Theater_sentence_5",
"Pomona Fox Theater_sentence_6"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2338,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.761",
"value": "undefined"
},
{
"operation": "search",
"time": "14.48",
"value": "Pomona Fox Theater"
},
{
"operation": "Now on",
"time": "15.82",
"value": "Pomona Fox Theater"
},
{
"operation": "Highlighting",
"time": "24.611",
"value": "Pomona Fox Theater_sentence_1"
},
{
"operation": "Highlighting",
"time": "51.771",
"value": "Pomona Fox Theater_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "64.882",
"value": "Pomona Fox Theater_sentence_4"
},
{
"operation": "Highlighting",
"time": "67.374",
"value": "Pomona Fox Theater_sentence_4"
},
{
"operation": "Highlighting",
"time": "69",
"value": "Pomona Fox Theater_sentence_5"
},
{
"operation": "Highlighting",
"time": "85.91",
"value": "Pomona Fox Theater_sentence_6"
},
{
"operation": "finish",
"time": "168.424",
"value": "finish"
}
]
}
|
40230
|
Schwerelos is the twelfth studio album of Andrea Berg, a German schlager singer discovered by record producer Eugen Römer in 1992.
|
{
"evidence": [
"Schwerelos_sentence_0",
"Andrea Berg_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:\nSchwerelos is the twelfth studio album of Andrea Berg, a German schlager singer discovered by record producer Eugen Römer in 1992.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Schwerelos_sentence_0",
"Andrea Berg_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2339,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.707",
"value": "?search="
},
{
"operation": "search",
"time": "7.117",
"value": "Schwerelos"
},
{
"operation": "Now on",
"time": "7.971",
"value": "Schwerelos"
},
{
"operation": "Highlighting",
"time": "10.476",
"value": "Schwerelos_sentence_0"
},
{
"operation": "hyperlink",
"time": "43.08",
"value": "Andrea Berg"
},
{
"operation": "Now on",
"time": "43.708",
"value": "Andrea Berg"
},
{
"operation": "Page search",
"time": "47.064",
"value": "Eugen Römer"
},
{
"operation": "Highlighting",
"time": "49.984",
"value": "Andrea Berg_sentence_3"
},
{
"operation": "finish",
"time": "133.38",
"value": "finish"
}
]
}
|
3574
|
Miguel Pacios is an Italian painter who plays striker for Rodez AF.
|
{
"evidence": [
"Miguel Pacios_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:\nMiguel Pacios is an Italian painter who plays striker for Rodez AF.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Miguel Pacios_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2340,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "13.892",
"value": "Miguel Pacios"
},
{
"operation": "Highlighting",
"time": "23.156",
"value": "Miguel Pacios_table_caption_0"
},
{
"operation": "Highlighting deleted",
"time": "42.946",
"value": "Miguel Pacios_table_caption_0"
},
{
"operation": "Highlighting",
"time": "45.674",
"value": "Miguel Pacios_sentence_0"
},
{
"operation": "finish",
"time": "61.545",
"value": "finish"
}
]
}
|
66503
|
Elden Henson is an American actor who starred in The Battle of Shaker Heights(2003) and ran the film production company, Paramount Pictures.
|
{
"evidence": [
"The Battle of Shaker Heights_sentence_1",
"Elden Henson_sentence_0",
"Paramount Pictures_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:\nElden Henson is an American actor who starred in The Battle of Shaker Heights(2003) and ran the film production company, Paramount Pictures.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"The Battle of Shaker Heights_sentence_1",
"Elden Henson_sentence_0",
"Paramount Pictures_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2341,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.215",
"value": "?search="
},
{
"operation": "search",
"time": "8.611",
"value": "Elden Henson"
},
{
"operation": "Now on",
"time": "12.32",
"value": "Elden Henson"
},
{
"operation": "search",
"time": "23.691",
"value": "The Battle of Shaker Heights"
},
{
"operation": "Now on",
"time": "24.606",
"value": "The Battle of Shaker Heights"
},
{
"operation": "Highlighting",
"time": "27.039",
"value": "The Battle of Shaker Heights_cell_0_4_1"
},
{
"operation": "Highlighting",
"time": "27.053",
"value": "The Battle of Shaker Heights_header_cell_0_4_0"
},
{
"operation": "Highlighting",
"time": "27.053",
"value": "The Battle of Shaker Heights_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "33.198",
"value": "The Battle of Shaker Heights_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "34.849",
"value": "The Battle of Shaker Heights_cell_0_4_1"
},
{
"operation": "Highlighting deleted",
"time": "34.862",
"value": "The Battle of Shaker Heights_header_cell_0_4_0"
},
{
"operation": "Highlighting deleted",
"time": "34.864",
"value": "The Battle of Shaker Heights_header_cell_0_0_0"
},
{
"operation": "hyperlink",
"time": "36.228",
"value": "Elden Henson"
},
{
"operation": "Now on",
"time": "36.635",
"value": "Elden Henson"
},
{
"operation": "Highlighting",
"time": "38.85",
"value": "Elden Henson_sentence_0"
},
{
"operation": "back-button-clicked",
"time": "41.038",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "41.157",
"value": "The Battle of Shaker Heights"
},
{
"operation": "hyperlink",
"time": "50.44",
"value": "Elden Henson"
},
{
"operation": "Now on",
"time": "50.87",
"value": "Elden Henson"
},
{
"operation": "search",
"time": "74.866",
"value": "paramount pictures"
},
{
"operation": "Now on",
"time": "77.149",
"value": "Paramount Pictures"
},
{
"operation": "hyperlink",
"time": "157.986",
"value": "Charles Bluhdorn"
},
{
"operation": "Now on",
"time": "158.678",
"value": "Charles Bluhdorn"
},
{
"operation": "search",
"time": "193.661",
"value": "Paramount Pictures"
},
{
"operation": "Now on",
"time": "195.649",
"value": "Paramount Pictures"
},
{
"operation": "Highlighting",
"time": "212.904",
"value": "Paramount Pictures_sentence_0"
},
{
"operation": "finish",
"time": "228.753",
"value": "finish"
}
]
}
|
82970
|
Tahlia Wilson was a right handed batter in the 2018–19 Sydney Sixers WBBL season with a 62.50 strike rate.
|
{
"evidence": [
"Tahlia Wilson_sentence_1"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nTahlia Wilson was a right handed batter in the 2018–19 Sydney Sixers WBBL season with a 62.50 strike rate.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Tahlia Wilson_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2342,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.997",
"value": "?search="
},
{
"operation": "search",
"time": "316.829",
"value": "Tahlia Wilson"
},
{
"operation": "Now on",
"time": "317.873",
"value": "Tahlia Wilson"
},
{
"operation": "Highlighting",
"time": "332.026",
"value": "Tahlia Wilson_sentence_1"
},
{
"operation": "finish",
"time": "399.006",
"value": "finish"
}
]
}
|
exfever_5304
|
Star Trek is the longest-running media franchise in the world.
|
{
"evidence": [
"Star Trek (film series)",
"Science fiction"
],
"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:\nStar Trek is the longest-running media franchise in the world.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Star Trek (film series)",
"Science fiction"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2343,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6482
|
The Ku Klux Klan is an American white supremacist terrorist and a social group that advocates and practices hatred, hostility, or violence towards members of a race, ethnicity, nation, religion, gender, or any other designated sector of society.
|
{
"evidence": [
"Ku Klux Klan",
"Hate group"
],
"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 Ku Klux Klan is an American white supremacist terrorist and a social group that advocates and practices hatred, hostility, or violence towards members of a race, ethnicity, nation, religion, gender, or any other designated sector of society.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Ku Klux Klan",
"Hate group"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2344,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
37705
|
Women in Indian Armed Forces were assigned to various branches of the army including a specialist corps in the Indian Army which primarily provides medical services to all Army personnel.
|
{
"evidence": [
"Special forces of India_sentence_1",
"Women in Indian Armed Forces_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:\nWomen in Indian Armed Forces were assigned to various branches of the army including a specialist corps in the Indian Army which primarily provides medical services to all Army personnel.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Special forces of India_sentence_1",
"Women in Indian Armed Forces_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2345,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.107",
"value": "?search="
},
{
"operation": "search",
"time": "16.498",
"value": "Women in Indian Armed Forces"
},
{
"operation": "Now on",
"time": "17.387",
"value": "Women in Indian Armed Forces"
},
{
"operation": "Page search",
"time": "34.157",
"value": "army"
},
{
"operation": "Page search",
"time": "73.978",
"value": "specialist"
},
{
"operation": "Page search",
"time": "123.869",
"value": "medical"
},
{
"operation": "Highlighting",
"time": "229.562",
"value": "Women in Indian Armed Forces_sentence_0"
},
{
"operation": "hyperlink",
"time": "255.947",
"value": "Special Forces of India"
},
{
"operation": "Now on",
"time": "256.661",
"value": "Special forces of India"
},
{
"operation": "Page search",
"time": "268.727",
"value": "medical"
},
{
"operation": "Highlighting",
"time": "315.457",
"value": "Special forces of India_sentence_1"
},
{
"operation": "Highlighting",
"time": "323.626",
"value": "Special forces of India_sentence_1"
},
{
"operation": "back-button-clicked",
"time": "339.989",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "340.258",
"value": "Women in Indian Armed Forces"
},
{
"operation": "Highlighting",
"time": "344.347",
"value": "Women in Indian Armed Forces_sentence_0"
},
{
"operation": "finish",
"time": "350.559",
"value": "finish"
}
]
}
|
exfever_6146
|
The Beach Boys are an American rock band with five original lineup, including an American musician, singer, and songwriter who co-founded the band.
|
{
"evidence": [
"The Beach Boys",
"Carl Wilson"
],
"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 Beach Boys are an American rock band with five original lineup, including an American musician, singer, and songwriter who co-founded the band.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Beach Boys",
"Carl Wilson"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2346,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
77350
|
Changsha dialect, spoken primarily in Hong Kong, features voiceless unaspirated and voiceless aspirated Plosives.
|
{
"evidence": [
"Changsha dialect_sentence_6",
"Changsha_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:\nChangsha dialect, spoken primarily in Hong Kong, features voiceless unaspirated and voiceless aspirated Plosives.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Changsha dialect_sentence_6",
"Changsha_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2347,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.614",
"value": "?search="
},
{
"operation": "search",
"time": "15.817",
"value": "Changsha dialect,"
},
{
"operation": "Now on",
"time": "17.258",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "19.55",
"value": "Changsha dialect"
},
{
"operation": "Now on",
"time": "20.468",
"value": "Changsha dialect"
},
{
"operation": "Highlighting",
"time": "25.028",
"value": "Changsha dialect_sentence_0"
},
{
"operation": "Highlighting",
"time": "34.519",
"value": "Changsha dialect_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "43.556",
"value": "Changsha dialect_sentence_0"
},
{
"operation": "Highlighting",
"time": "98.093",
"value": "Changsha dialect_sentence_6"
},
{
"operation": "Highlighting deleted",
"time": "104.627",
"value": "Changsha dialect_sentence_1"
},
{
"operation": "hyperlink",
"time": "114.621",
"value": "Changsha"
},
{
"operation": "Now on",
"time": "116.016",
"value": "Changsha"
},
{
"operation": "Highlighting",
"time": "118.844",
"value": "Changsha_sentence_1"
},
{
"operation": "finish",
"time": "126.447",
"value": "finish"
}
]
}
|
82095
|
Eva Krížiková (who entered the film industry through a minor, backup role in Paľo Bielik's work The Mountains Are Stirring from 1952) had a voice acting role in the Cat on a Hot Tin Roof in 2005.
|
{
"evidence": [
"Eva Krížiková_sentence_4"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nEva Krížiková (who entered the film industry through a minor, backup role in Paľo Bielik's work The Mountains Are Stirring from 1952) had a voice acting role in the Cat on a Hot Tin Roof in 2005.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Eva Krížiková_sentence_4"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2348,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.312",
"value": "?search="
},
{
"operation": "search",
"time": "68.077",
"value": "Rajkumar"
},
{
"operation": "Now on",
"time": "69.259",
"value": "Rajkumar"
},
{
"operation": "hyperlink",
"time": "99.79",
"value": "Rajkumar (actor)"
},
{
"operation": "Now on",
"time": "101.784",
"value": "Rajkumar (actor)"
},
{
"operation": "search",
"time": "150.349",
"value": "Contains...The Mountains Are Stirring"
},
{
"operation": "Now on",
"time": "151.608",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "159.288",
"value": "Eva Krížiková"
},
{
"operation": "Now on",
"time": "160.174",
"value": "Eva Krížiková"
},
{
"operation": "Highlighting",
"time": "168.538",
"value": "Eva Krížiková_sentence_4"
},
{
"operation": "search",
"time": "225.357",
"value": "Cat on a Hot Tin Roof"
},
{
"operation": "Now on",
"time": "226.727",
"value": "Cat on a Hot Tin Roof"
},
{
"operation": "back-button-clicked",
"time": "266.299",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "266.392",
"value": "Eva Krížiková"
},
{
"operation": "Highlighting deleted",
"time": "295.178",
"value": "Eva Krížiková_sentence_4"
},
{
"operation": "Highlighting",
"time": "296.934",
"value": "Eva Krížiková_cell_0_2_1"
},
{
"operation": "Highlighting",
"time": "296.946",
"value": "Eva Krížiková_header_cell_0_2_0"
},
{
"operation": "Highlighting",
"time": "296.946",
"value": "Eva Krížiková_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "312.562",
"value": "Eva Krížiková_cell_0_2_1"
},
{
"operation": "Highlighting deleted",
"time": "312.576",
"value": "Eva Krížiková_header_cell_0_2_0"
},
{
"operation": "Highlighting deleted",
"time": "312.58",
"value": "Eva Krížiková_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "318.764",
"value": "Eva Krížiková_sentence_4"
},
{
"operation": "finish",
"time": "338.864",
"value": "finish"
}
]
}
|
exfever_4941
|
Jennifer McCarthy is an American model who starred in an American slasher film starring an American actor.
|
{
"evidence": [
"Jenny McCarthy",
"Scream 3",
"Lance Henriksen"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJennifer McCarthy is an American model who starred in an American slasher film starring an American actor.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jenny McCarthy",
"Scream 3",
"Lance Henriksen"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2349,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
66707
|
Buche Nangal is a village in India that derived its name from a past chieftain of the town.
|
{
"evidence": [
"Buche Nangal_sentence_0",
"Buche Nangal_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:\nBuche Nangal is a village in India that derived its name from a past chieftain of the town.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Buche Nangal_sentence_0",
"Buche Nangal_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2350,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.45",
"value": "?search="
},
{
"operation": "search",
"time": "10.298",
"value": "Buche Nangal"
},
{
"operation": "Now on",
"time": "11.561",
"value": "Buche Nangal"
},
{
"operation": "Highlighting",
"time": "13.915",
"value": "Buche Nangal_sentence_0"
},
{
"operation": "Highlighting",
"time": "18.567",
"value": "Buche Nangal_sentence_1"
},
{
"operation": "finish",
"time": "31.832",
"value": "finish"
}
]
}
|
21432
|
The Brilliant Mind of Edison Lee daily strip usually runs two to four panels and it does not appear on Sundays; it is drawn in great detail and objects such as cars and props are presented as close to reality as possible.
|
{
"evidence": [
"The Brilliant Mind of Edison Lee_sentence_20"
],
"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 Brilliant Mind of Edison Lee daily strip usually runs two to four panels and it does not appear on Sundays; it is drawn in great detail and objects such as cars and props are presented as close to reality as possible.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"The Brilliant Mind of Edison Lee_sentence_20"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2351,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.679",
"value": "?search="
},
{
"operation": "search",
"time": "15.915",
"value": "The Brilliant Mind of Edison Lee"
},
{
"operation": "Now on",
"time": "16.892",
"value": "The Brilliant Mind of Edison Lee"
},
{
"operation": "Highlighting",
"time": "54.395",
"value": "The Brilliant Mind of Edison Lee_sentence_20"
},
{
"operation": "finish",
"time": "69.426",
"value": "finish"
}
]
}
|
5813
|
Kai Krause (named one of the top 15 innovators in 2005) moved to California (39.5 million residents) in 1978 and worked with early synthesizers to make sound effects.
|
{
"evidence": [
"Kai Krause_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:\nKai Krause (named one of the top 15 innovators in 2005) moved to California (39.5 million residents) in 1978 and worked with early synthesizers to make sound effects.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Kai Krause_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2352,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.399",
"value": "?search="
},
{
"operation": "search",
"time": "14.469",
"value": "Kai Krause"
},
{
"operation": "Now on",
"time": "15.797",
"value": "Kai Krause"
},
{
"operation": "Highlighting",
"time": "37.087",
"value": "Kai Krause_sentence_4"
},
{
"operation": "Highlighting",
"time": "46.01",
"value": "Kai Krause_sentence_1"
},
{
"operation": "hyperlink",
"time": "48.294",
"value": "California"
},
{
"operation": "Now on",
"time": "50.576",
"value": "California"
},
{
"operation": "back-button-clicked",
"time": "52.217",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "52.273",
"value": "Kai Krause"
},
{
"operation": "Highlighting deleted",
"time": "54.96",
"value": "Kai Krause_sentence_4"
},
{
"operation": "finish",
"time": "97.262",
"value": "finish"
}
]
}
|
exfever_5260
|
Edgar Allan Poe was one of the country's earliest practitioners of a piece of prose fiction that can typically be read in one sitting.
|
{
"evidence": [
"Edgar Allan Poe",
"Short story"
],
"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:\nEdgar Allan Poe was one of the country's earliest practitioners of a piece of prose fiction that can typically be read in one sitting.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Edgar Allan Poe",
"Short story"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2353,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
61905
|
Dondogdorjyn Erdenebat attended university in Irkutsk, the largest city in Irkutsk Oblast, Russia.
|
{
"evidence": [
"Dondogdorjyn Erdenebat_sentence_8",
"Irkutsk_sentence_1",
"Dondogdorjyn Erdenebat_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:\nDondogdorjyn Erdenebat attended university in Irkutsk, the largest city in Irkutsk Oblast, Russia.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Dondogdorjyn Erdenebat_sentence_8",
"Irkutsk_sentence_1",
"Dondogdorjyn Erdenebat_sentence_7"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2354,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.2",
"value": "?search="
},
{
"operation": "search",
"time": "159.058",
"value": "Dondogdorjyn Erdenebat"
},
{
"operation": "Now on",
"time": "160.089",
"value": "Dondogdorjyn Erdenebat"
},
{
"operation": "Highlighting",
"time": "164.191",
"value": "Dondogdorjyn Erdenebat_header_cell_0_7_0"
},
{
"operation": "Highlighting",
"time": "164.667",
"value": "Dondogdorjyn Erdenebat_cell_0_7_1"
},
{
"operation": "Highlighting",
"time": "164.676",
"value": "Dondogdorjyn Erdenebat_header_cell_0_7_0"
},
{
"operation": "Highlighting",
"time": "164.676",
"value": "Dondogdorjyn Erdenebat_header_cell_0_4_0"
},
{
"operation": "hyperlink",
"time": "176.649",
"value": "Alma mater"
},
{
"operation": "Now on",
"time": "177.182",
"value": "Alma mater"
},
{
"operation": "Highlighting",
"time": "180.277",
"value": "Alma mater_sentence_2"
},
{
"operation": "Highlighting",
"time": "180.279",
"value": "Alma mater_title"
},
{
"operation": "back-button-clicked",
"time": "181.872",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "181.956",
"value": "Dondogdorjyn Erdenebat"
},
{
"operation": "Highlighting deleted",
"time": "190.676",
"value": "Dondogdorjyn Erdenebat_cell_0_7_1"
},
{
"operation": "Highlighting deleted",
"time": "190.684",
"value": "Dondogdorjyn Erdenebat_header_cell_0_7_0"
},
{
"operation": "Highlighting deleted",
"time": "190.685",
"value": "Dondogdorjyn Erdenebat_header_cell_0_4_0"
},
{
"operation": "Highlighting",
"time": "207.015",
"value": "Dondogdorjyn Erdenebat_sentence_8"
},
{
"operation": "Page search",
"time": "215.531",
"value": "Irkutsk"
},
{
"operation": "search",
"time": "220.077",
"value": "Irkutsk"
},
{
"operation": "Now on",
"time": "221.359",
"value": "Irkutsk"
},
{
"operation": "Highlighting",
"time": "229.629",
"value": "Irkutsk_sentence_1"
},
{
"operation": "back-button-clicked",
"time": "268.237",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "268.327",
"value": "Dondogdorjyn Erdenebat"
},
{
"operation": "Highlighting",
"time": "298.997",
"value": "Dondogdorjyn Erdenebat_sentence_7"
},
{
"operation": "finish",
"time": "319.517",
"value": "finish"
}
]
}
|
18075
|
Soul Soldier is a 1970 blaxploitation (an ethnic subgenre of the exploitation film that emerged in the United States during the early 1970s) Western film that was initially produced by Hirschman-Northern Productions and was reshot by John Cardos, which was entirely shot on an Arriflex 35 IIC.
|
{
"evidence": [
"Soul Soldier_sentence_6",
"Soul Soldier_sentence_7",
"Soul Soldier_sentence_9",
"Soul Soldier_sentence_8",
"Blaxploitation_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:\nSoul Soldier is a 1970 blaxploitation (an ethnic subgenre of the exploitation film that emerged in the United States during the early 1970s) Western film that was initially produced by Hirschman-Northern Productions and was reshot by John Cardos, which was entirely shot on an Arriflex 35 IIC.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Soul Soldier_sentence_6",
"Soul Soldier_sentence_7",
"Soul Soldier_sentence_9",
"Soul Soldier_sentence_8",
"Blaxploitation_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2355,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.075",
"value": "?search="
},
{
"operation": "search",
"time": "11.814",
"value": "Soul Soldier"
},
{
"operation": "Now on",
"time": "12.741",
"value": "Soul Soldier"
},
{
"operation": "Highlighting",
"time": "29.846",
"value": "Soul Soldier_sentence_6"
},
{
"operation": "Highlighting",
"time": "40.918",
"value": "Soul Soldier_sentence_7"
},
{
"operation": "Highlighting",
"time": "56.045",
"value": "Soul Soldier_sentence_9"
},
{
"operation": "Highlighting",
"time": "63.381",
"value": "Soul Soldier_sentence_8"
},
{
"operation": "hyperlink",
"time": "73.741",
"value": "blaxploitation"
},
{
"operation": "Now on",
"time": "75.203",
"value": "Blaxploitation"
},
{
"operation": "Highlighting",
"time": "82.046",
"value": "Blaxploitation_sentence_2"
},
{
"operation": "finish",
"time": "94.653",
"value": "finish"
}
]
}
|
exfever_1696
|
Peggy Sue Got Married is a 1986 American fantasy comedy-drama film directed by an American producer, screenwriter, and director who controls a film's artistic and dramatic aspects and visualizes the screenplay while guiding the film crew and actors in the fulfillment of that vision.
|
{
"evidence": [
"Peggy Sue Got Married",
"Francis Ford Coppola",
"Film director"
],
"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:\nPeggy Sue Got Married is a 1986 American fantasy comedy-drama film directed by an American producer, screenwriter, and director who controls a film's artistic and dramatic aspects and visualizes the screenplay while guiding the film crew and actors in the fulfillment of that vision.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Peggy Sue Got Married",
"Francis Ford Coppola",
"Film director"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2356,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
87013
|
The Finnish House of Nobility is comprised of 357 families, of which 148 are still alive with four still bearing the title of duke and 25 the title of baron.
|
{
"evidence": [
"List of Finnish noble families_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 Finnish House of Nobility is comprised of 357 families, of which 148 are still alive with four still bearing the title of duke and 25 the title of baron.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"List of Finnish noble families_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2357,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.736",
"value": "?search="
},
{
"operation": "search",
"time": "16.225",
"value": "Finnish house of nobility"
},
{
"operation": "Now on",
"time": "16.878",
"value": "House of Nobility (Finland)"
},
{
"operation": "Highlighting",
"time": "195.753",
"value": "House of Nobility (Finland)_sentence_0"
},
{
"operation": "Highlighting",
"time": "195.754",
"value": "House of Nobility (Finland)_title"
},
{
"operation": "Highlighting deleted",
"time": "197.288",
"value": "House of Nobility (Finland)_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "197.289",
"value": "House of Nobility (Finland)_title"
},
{
"operation": "hyperlink",
"time": "245.592",
"value": "Finnish nobility"
},
{
"operation": "Now on",
"time": "246.786",
"value": "Finnish nobility"
},
{
"operation": "Page search",
"time": "269.164",
"value": "house"
},
{
"operation": "Highlighting",
"time": "284.018",
"value": "Finnish nobility_sentence_12"
},
{
"operation": "Highlighting",
"time": "284.019",
"value": "Finnish nobility_title"
},
{
"operation": "Highlighting",
"time": "324.313",
"value": "Finnish nobility_sentence_3"
},
{
"operation": "Page search",
"time": "334.164",
"value": "families"
},
{
"operation": "hyperlink",
"time": "383.369",
"value": "List of Finnish noble families"
},
{
"operation": "Now on",
"time": "383.921",
"value": "List of Finnish noble families"
},
{
"operation": "Highlighting",
"time": "386.88",
"value": "List of Finnish noble families_sentence_1"
},
{
"operation": "Highlighting",
"time": "392.08",
"value": "List of Finnish noble families_sentence_0"
},
{
"operation": "Highlighting",
"time": "395.888",
"value": "List of Finnish noble families_sentence_1"
},
{
"operation": "Highlighting",
"time": "413.208",
"value": "List of Finnish noble families_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "430.352",
"value": "List of Finnish noble families_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "431.016",
"value": "List of Finnish noble families_sentence_0"
},
{
"operation": "hyperlink",
"time": "431.727",
"value": "Finnish House of Nobility"
},
{
"operation": "Now on",
"time": "432.313",
"value": "House of Nobility (Finland)"
},
{
"operation": "finish",
"time": "455.201",
"value": "finish"
}
]
}
|
56945
|
Late Night Berlin, premiered on March 12, 2018 and hosted by Klaas Heufer-Umlauf, is the only late night comedy show that is really recorded in the said location.
|
{
"evidence": [
"Late Night Berlin_sentence_10",
"Late Night Berlin_sentence_11",
"Late Night Berlin_sentence_0",
"Late Night Berlin_sentence_1"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nLate Night Berlin, premiered on March 12, 2018 and hosted by Klaas Heufer-Umlauf, is the only late night comedy show that is really recorded in the said location.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Late Night Berlin_sentence_10",
"Late Night Berlin_sentence_11",
"Late Night Berlin_sentence_0",
"Late Night Berlin_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2358,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.608",
"value": "?search="
},
{
"operation": "search",
"time": "39.357",
"value": "Late Night Berlin"
},
{
"operation": "Now on",
"time": "40.516",
"value": "Late Night Berlin"
},
{
"operation": "Page search",
"time": "62.148",
"value": "only"
},
{
"operation": "Highlighting",
"time": "109.21",
"value": "Late Night Berlin_sentence_10"
},
{
"operation": "Highlighting",
"time": "110.122",
"value": "Late Night Berlin_sentence_11"
},
{
"operation": "Highlighting",
"time": "150.473",
"value": "Late Night Berlin_sentence_0"
},
{
"operation": "Highlighting",
"time": "154.544",
"value": "Late Night Berlin_sentence_1"
},
{
"operation": "finish",
"time": "167.6",
"value": "finish"
}
]
}
|
50474
|
Australia has won the World Championship five times, the most of any participating country.
|
{
"evidence": [
"Cricket_sentence_18"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAustralia has won the World Championship five times, the most of any participating country.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Cricket_sentence_18"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2359,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.943",
"value": "?search="
},
{
"operation": "search",
"time": "7.443",
"value": "Australia"
},
{
"operation": "Now on",
"time": "9.691",
"value": "Australia"
},
{
"operation": "search",
"time": "16.283",
"value": "World Championship"
},
{
"operation": "Now on",
"time": "18.375",
"value": "undefined"
},
{
"operation": "search",
"time": "28.739",
"value": "World Championship australia"
},
{
"operation": "Now on",
"time": "30.221",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "80.942",
"value": "World Championship Wrestling (Australia)"
},
{
"operation": "Now on",
"time": "81.82",
"value": "World Championship Wrestling (Australia)"
},
{
"operation": "Highlighting",
"time": "99.892",
"value": "World Championship Wrestling (Australia)_cell_1_2_0"
},
{
"operation": "Highlighting",
"time": "99.893",
"value": "World Championship Wrestling (Australia)_title"
},
{
"operation": "Highlighting",
"time": "99.893",
"value": "World Championship Wrestling (Australia)_section_2"
},
{
"operation": "Highlighting",
"time": "99.895",
"value": "World Championship Wrestling (Australia)_header_cell_1_0_0"
},
{
"operation": "Highlighting",
"time": "100.393",
"value": "World Championship Wrestling (Australia)_cell_1_3_0"
},
{
"operation": "Highlighting deleted",
"time": "103.356",
"value": "World Championship Wrestling (Australia)_cell_1_2_0"
},
{
"operation": "Highlighting deleted",
"time": "103.774",
"value": "World Championship Wrestling (Australia)_cell_1_3_0"
},
{
"operation": "Highlighting deleted",
"time": "103.775",
"value": "World Championship Wrestling (Australia)_title"
},
{
"operation": "Highlighting deleted",
"time": "103.776",
"value": "World Championship Wrestling (Australia)_section_2"
},
{
"operation": "Highlighting deleted",
"time": "103.778",
"value": "World Championship Wrestling (Australia)_header_cell_1_0_0"
},
{
"operation": "search",
"time": "122.595",
"value": "World Championship australia five times"
},
{
"operation": "Now on",
"time": "124.304",
"value": "undefined"
},
{
"operation": "search",
"time": "223.983",
"value": "Australia World Championship five times"
},
{
"operation": "Now on",
"time": "225.79",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "249.56",
"value": "Cricket"
},
{
"operation": "Now on",
"time": "254.086",
"value": "Cricket"
},
{
"operation": "Highlighting",
"time": "272.458",
"value": "Cricket_sentence_18"
},
{
"operation": "finish",
"time": "286.07",
"value": "finish"
}
]
}
|
33023
|
Ruth Cavin worked as an associate publisher and specialized in mystery fiction.
|
{
"evidence": [
"Ruth Cavin_sentence_0",
"Ruth Cavin_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:\nRuth Cavin worked as an associate publisher and specialized in mystery fiction.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Ruth Cavin_sentence_0",
"Ruth Cavin_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2360,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.773",
"value": "?search="
},
{
"operation": "search",
"time": "3.9",
"value": "Ruth Cavin"
},
{
"operation": "Now on",
"time": "4.678",
"value": "Ruth Cavin"
},
{
"operation": "Highlighting",
"time": "9.835",
"value": "Ruth Cavin_sentence_0"
},
{
"operation": "Highlighting",
"time": "22.307",
"value": "Ruth Cavin_sentence_1"
},
{
"operation": "finish",
"time": "32.516",
"value": "finish"
}
]
}
|
exfever_2537
|
Priyanka Chopra is the fifth Indian to win Miss World.
|
{
"evidence": [
"Priyanka Chopra",
"Padma Shri"
],
"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:\nPriyanka Chopra is the fifth Indian to win Miss World.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Priyanka Chopra",
"Padma Shri"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2361,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4557
|
Alicia Amanda Vikander is trained as a ballet dancer at one of the oldest ballet companies in Europe.
|
{
"evidence": [
"Alicia Vikander",
"Royal Swedish Ballet"
],
"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:\nAlicia Amanda Vikander is trained as a ballet dancer at one of the oldest ballet companies in Europe.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Alicia Vikander",
"Royal Swedish Ballet"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2362,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7408
|
Gianluigi Buffon has already recorded 420 clean sheets.
|
{
"evidence": [
"Gianluigi Buffon",
"Goalkeeper (association football)",
"Association football"
],
"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:\nGianluigi Buffon has already recorded 420 clean sheets.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Gianluigi Buffon",
"Goalkeeper (association football)",
"Association football"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2363,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8876
|
Jason Bourne is a 2016 American action-thriller film that is a direct sequel to the 2007 action-thriller film directed by Paul Greengrass.
|
{
"evidence": [
"Jason Bourne (film)",
"The Bourne Ultimatum (film)"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJason Bourne is a 2016 American action-thriller film that is a direct sequel to the 2007 action-thriller film directed by Paul Greengrass.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jason Bourne (film)",
"The Bourne Ultimatum (film)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2364,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
19497
|
Bernard Pagel obtained his Ph.D. in Cambridge in 1955 and became a Research Fellow at Sidney Sussex college in 1953-1956, then later became a Deputy Scientific Officer at Royal Greenwich Observatory, an observatory where the prime meridian passes through it.
|
{
"evidence": [
"Bernard Pagel_sentence_3",
"Bernard Pagel_sentence_4",
"Bernard Pagel_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:\nBernard Pagel obtained his Ph.D. in Cambridge in 1955 and became a Research Fellow at Sidney Sussex college in 1953-1956, then later became a Deputy Scientific Officer at Royal Greenwich Observatory, an observatory where the prime meridian passes through it.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Bernard Pagel_sentence_3",
"Bernard Pagel_sentence_4",
"Bernard Pagel_sentence_5"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2365,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.303",
"value": "?search="
},
{
"operation": "search",
"time": "10.882",
"value": "Bernard Pagel"
},
{
"operation": "Now on",
"time": "12.413",
"value": "Bernard Pagel"
},
{
"operation": "Highlighting",
"time": "28.407",
"value": "Bernard Pagel_sentence_3"
},
{
"operation": "Highlighting",
"time": "32.939",
"value": "Bernard Pagel_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "49.14",
"value": "Bernard Pagel_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "50.477",
"value": "Bernard Pagel_sentence_3"
},
{
"operation": "Highlighting",
"time": "51.731",
"value": "Bernard Pagel_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "59.979",
"value": "Bernard Pagel_sentence_5"
},
{
"operation": "Highlighting",
"time": "61.028",
"value": "Bernard Pagel_sentence_3"
},
{
"operation": "Highlighting",
"time": "61.936",
"value": "Bernard Pagel_sentence_4"
},
{
"operation": "Highlighting",
"time": "63.804",
"value": "Bernard Pagel_sentence_5"
},
{
"operation": "finish",
"time": "90.715",
"value": "finish"
}
]
}
|
55382
|
The internal urethral sphincter is controlled by the hypogastric nerve via signals arising in the pontine micturition center, also known as also known as Barrington's nucleus.
|
{
"evidence": [
"Internal urethral sphincter_sentence_5",
"Internal urethral sphincter_sentence_6",
"Pontine micturition center_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 internal urethral sphincter is controlled by the hypogastric nerve via signals arising in the pontine micturition center, also known as also known as Barrington's nucleus.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Internal urethral sphincter_sentence_5",
"Internal urethral sphincter_sentence_6",
"Pontine micturition center_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2366,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.108",
"value": "?search="
},
{
"operation": "search",
"time": "24.292",
"value": "Internal urethral sphincter"
},
{
"operation": "Now on",
"time": "25.394",
"value": "Internal urethral sphincter"
},
{
"operation": "Highlighting",
"time": "145.1",
"value": "Internal urethral sphincter_sentence_5"
},
{
"operation": "Highlighting",
"time": "167.596",
"value": "Internal urethral sphincter_sentence_6"
},
{
"operation": "hyperlink",
"time": "169.539",
"value": "pontine micturition center"
},
{
"operation": "Now on",
"time": "170.425",
"value": "Pontine micturition center"
},
{
"operation": "Highlighting",
"time": "174.813",
"value": "Pontine micturition center_sentence_0"
},
{
"operation": "finish",
"time": "200.367",
"value": "finish"
}
]
}
|
exfever_72
|
Captain America is a superhero who appeared in American comic books published by Marvel Comics and created by cartoonists Joe Simon and an American comic book artist widely regarded as one of the medium's innovators and the most prolific and influential creators.
|
{
"evidence": [
"Captain America",
"Jack Kirby"
],
"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:\nCaptain America is a superhero who appeared in American comic books published by Marvel Comics and created by cartoonists Joe Simon and an American comic book artist widely regarded as one of the medium's innovators and the most prolific and influential creators.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Captain America",
"Jack Kirby"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2367,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3637
|
Donkey is a fictional fast-talking donkey voiced primarily by an American actor who rose to fame on the sketch comedy show Saturday Night Live.
|
{
"evidence": [
"Donkey (Shrek)",
"Eddie Murphy"
],
"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:\nDonkey is a fictional fast-talking donkey voiced primarily by an American actor who rose to fame on the sketch comedy show Saturday Night Live.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Donkey (Shrek)",
"Eddie Murphy"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2368,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
35741
|
Sławomir Skrzypek was the President of the National Bank of Poland, he was born in 1963 and died and still lives in Russia.
|
{
"evidence": [
"Sławomir Skrzypek_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:\nSławomir Skrzypek was the President of the National Bank of Poland, he was born in 1963 and died and still lives in Russia.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Sławomir Skrzypek_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2369,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.834",
"value": "?search="
},
{
"operation": "search",
"time": "13.696",
"value": "Sławomir Skrzypek"
},
{
"operation": "Now on",
"time": "14.593",
"value": "Sławomir Skrzypek"
},
{
"operation": "Highlighting",
"time": "17.325",
"value": "Sławomir Skrzypek_sentence_0"
},
{
"operation": "finish",
"time": "55.54",
"value": "finish"
}
]
}
|
exfever_7387
|
William McKinley was the 25th president of the United States during the period of armed conflict between Spain and the United States the aftermath of the internal explosion of the USS Maine in Havana Harbor happened in an administrative district of the Spanish Empire created in 1607 as part of Habsburg Spain's attempt to better defend and administer its Caribbean possessions.
|
{
"evidence": [
"William McKinley",
"Spanish–American War",
"Captaincy General of Cuba"
],
"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:\nWilliam McKinley was the 25th president of the United States during the period of armed conflict between Spain and the United States the aftermath of the internal explosion of the USS Maine in Havana Harbor happened in an administrative district of the Spanish Empire created in 1607 as part of Habsburg Spain's attempt to better defend and administer its Caribbean possessions.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"William McKinley",
"Spanish–American War",
"Captaincy General of Cuba"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2370,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_717
|
The United Nations (UN) is an intergovernmental organization headquartered on international territory in the most populous city in the United States.
|
{
"evidence": [
"United Nations",
"New York City"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe United Nations (UN) is an intergovernmental organization headquartered on international territory in the most populous city in the United States.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"United Nations",
"New York City"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2371,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8743
|
George Tuska is a newspaper comic strip artist best known for his 1960s work on various Captain Marvel titles and the crime fiction series that has crime comics genre that sensationalized recountings of the deeds of gangsters such as an American comic book artist Carl Larson.
|
{
"evidence": [
"George Tuska",
"Crime Does Not Pay (comics)",
"George Tuska"
],
"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:\nGeorge Tuska is a newspaper comic strip artist best known for his 1960s work on various Captain Marvel titles and the crime fiction series that has crime comics genre that sensationalized recountings of the deeds of gangsters such as an American comic book artist Carl Larson.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"George Tuska",
"Crime Does Not Pay (comics)",
"George Tuska"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2372,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6541
|
The phalanx was the first military formation used in Ancient Greek warfare.
|
{
"evidence": [
"Phalanx",
"Pole weapon",
"Pike square"
],
"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 phalanx was the first military formation used in Ancient Greek warfare.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Phalanx",
"Pole weapon",
"Pike square"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2373,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
44071
|
The courtside reporter in the 2015–16 Fox Sports North was neither Marney Gellner nor Anthony LaPanta; while the studio host was Tom Hanneman.
|
{
"evidence": [
"Tom Hanneman_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 courtside reporter in the 2015–16 Fox Sports North was neither Marney Gellner nor Anthony LaPanta; while the studio host was Tom Hanneman.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Tom Hanneman_sentence_5"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2374,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.676",
"value": "?search="
},
{
"operation": "search",
"time": "35.482",
"value": "2015–16 Fox Sports North"
},
{
"operation": "Now on",
"time": "38.639",
"value": "undefined"
},
{
"operation": "search",
"time": "55.65",
"value": "courtside reporter in the 2015–16 Fox Sports North"
},
{
"operation": "Now on",
"time": "57.546",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "71.676",
"value": "Sports commentator"
},
{
"operation": "Now on",
"time": "72.767",
"value": "Sports commentator"
},
{
"operation": "Page search",
"time": "79.091",
"value": "fox"
},
{
"operation": "search",
"time": "123.538",
"value": "Marney Gellner"
},
{
"operation": "Now on",
"time": "124.97",
"value": "undefined"
},
{
"operation": "search",
"time": "171.075",
"value": "\"Marney Gellner\" \"fox\" \"Anthony LaPanta\""
},
{
"operation": "Now on",
"time": "171.953",
"value": "undefined"
},
{
"operation": "search",
"time": "186.423",
"value": "Anthony LaPanta"
},
{
"operation": "Now on",
"time": "187.861",
"value": "undefined"
},
{
"operation": "search",
"time": "208.154",
"value": "\"Anthony LaPanta\" \"fox\""
},
{
"operation": "Now on",
"time": "208.829",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "211.758",
"value": "List of Minnesota Wild broadcasters"
},
{
"operation": "Now on",
"time": "212.79",
"value": "List of Minnesota Wild broadcasters"
},
{
"operation": "Page search",
"time": "223.034",
"value": "LaPanta"
},
{
"operation": "search",
"time": "267.261",
"value": "Tom Hanneman"
},
{
"operation": "Now on",
"time": "268.567",
"value": "Tom Hanneman"
},
{
"operation": "Page search",
"time": "283.668",
"value": "fox"
},
{
"operation": "search",
"time": "339.944",
"value": "2015–16 Fox Sports North"
},
{
"operation": "Now on",
"time": "341.521",
"value": "undefined"
},
{
"operation": "search",
"time": "387.982",
"value": "\"2015–16 Fox Sports North\" \"gellner\""
},
{
"operation": "Now on",
"time": "388.675",
"value": "undefined"
},
{
"operation": "search",
"time": "411.931",
"value": "Fox Sports North 2015-16"
},
{
"operation": "Now on",
"time": "413.292",
"value": "undefined"
},
{
"operation": "search",
"time": "450.198",
"value": "Marney Gellner"
},
{
"operation": "Now on",
"time": "450.904",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "454.896",
"value": "Minnesota Lynx"
},
{
"operation": "Now on",
"time": "457.86",
"value": "Minnesota Lynx"
},
{
"operation": "Page search",
"time": "461.805",
"value": "Marney Gellner"
},
{
"operation": "back-button-clicked",
"time": "501.161",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "502.21",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "524.601",
"value": "Tom Hanneman"
},
{
"operation": "Now on",
"time": "524.967",
"value": "Tom Hanneman"
},
{
"operation": "Page search",
"time": "530.127",
"value": "Marney Gellner"
},
{
"operation": "Highlighting",
"time": "535.382",
"value": "Tom Hanneman_sentence_5"
},
{
"operation": "Page search",
"time": "602.713",
"value": "lapanta"
},
{
"operation": "search",
"time": "647.878",
"value": "\"Anthony LaPanta\" \"Hanneman\""
},
{
"operation": "Now on",
"time": "649.238",
"value": "undefined"
},
{
"operation": "search",
"time": "672.274",
"value": "\"Anthony LaPanta\" \"fox\""
},
{
"operation": "Now on",
"time": "672.953",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "675.997",
"value": "List of Minnesota Wild broadcasters"
},
{
"operation": "Now on",
"time": "676.671",
"value": "List of Minnesota Wild broadcasters"
},
{
"operation": "Page search",
"time": "683.337",
"value": "lapanta"
},
{
"operation": "finish",
"time": "709.952",
"value": "finish"
}
]
}
|
exfever_6646
|
Social anxiety disorder is an anxiety disorder characterized by sentiments of fear and anxiety in social situations and has physical symptoms of rapid pulsation and a regular beating of the heart.
|
{
"evidence": [
"Social anxiety disorder",
"Palpitations"
],
"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:\nSocial anxiety disorder is an anxiety disorder characterized by sentiments of fear and anxiety in social situations and has physical symptoms of rapid pulsation and a regular beating of the heart.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Social anxiety disorder",
"Palpitations"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2375,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
3320
|
The first published writing of Louisa Parr, a British writer who married a surgeon and collector named George Parr, was a success and was issued under the pen name of Mrs Olinthus Lobb.
|
{
"evidence": [
"Louisa Parr_sentence_1",
"Louisa Parr_sentence_4",
"Louisa Parr_sentence_8"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe first published writing of Louisa Parr, a British writer who married a surgeon and collector named George Parr, was a success and was issued under the pen name of Mrs Olinthus Lobb.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Louisa Parr_sentence_1",
"Louisa Parr_sentence_4",
"Louisa Parr_sentence_8"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2376,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "17.235",
"value": "Louisa Parr"
},
{
"operation": "Highlighting",
"time": "19.813",
"value": "Louisa Parr_sentence_1"
},
{
"operation": "Highlighting",
"time": "67.763",
"value": "Louisa Parr_sentence_4"
},
{
"operation": "Page search",
"time": "77.898",
"value": "surg"
},
{
"operation": "Highlighting",
"time": "79.999",
"value": "Louisa Parr_sentence_8"
},
{
"operation": "finish",
"time": "88.003",
"value": "finish"
}
]
}
|
3795
|
Tilian Pearson has been a vocalist for the bands Tides of Man and Dance Gavin Dance, who he toured with in February and March of 2017 along with the band Coheed and Cambria.
|
{
"evidence": [
"Tilian Pearson_sentence_1",
"Tilian Pearson_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:\nTilian Pearson has been a vocalist for the bands Tides of Man and Dance Gavin Dance, who he toured with in February and March of 2017 along with the band Coheed and Cambria.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Tilian Pearson_sentence_1",
"Tilian Pearson_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2377,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "16.056",
"value": "Tilian Pearson"
},
{
"operation": "Highlighting",
"time": "40.453",
"value": "Tilian Pearson_sentence_1"
},
{
"operation": "Highlighting",
"time": "43.652",
"value": "Tilian Pearson_sentence_2"
},
{
"operation": "hyperlink",
"time": "63.46",
"value": "2.2 2017–present"
},
{
"operation": "hyperlink",
"time": "128.716",
"value": "Dance Gavin Dance"
},
{
"operation": "back-button-clicked",
"time": "224.822",
"value": "back-button-clicked"
},
{
"operation": "search",
"time": "252.693",
"value": "coheed"
},
{
"operation": "hyperlink",
"time": "278.996",
"value": "1.7 The Color Before the Sun (2015–2017) Coheed and Cambria_section_7"
},
{
"operation": "Page search",
"time": "304.548",
"value": "dance gavin dance"
},
{
"operation": "finish",
"time": "334.011",
"value": "finish"
}
]
}
|
70190
|
St. Peter's Basilica is a tourist attraction in Rome, found in the Vatican City, and considered to be the "home of the Roman Catholic Church."
|
{
"evidence": [
"St. Peter's Basilica_sentence_3"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSt. Peter's Basilica is a tourist attraction in Rome, found in the Vatican City, and considered to be the \"home of the Roman Catholic Church.\"\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"St. Peter's Basilica_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 2378,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.075",
"value": "?search="
},
{
"operation": "search",
"time": "12.193",
"value": "St. Peter's Basilica"
},
{
"operation": "Now on",
"time": "14.521",
"value": "St. Peter's Basilica"
},
{
"operation": "Page search",
"time": "117.484",
"value": "tourisst"
},
{
"operation": "Page search",
"time": "119.731",
"value": "tourist"
},
{
"operation": "Highlighting",
"time": "268.809",
"value": "St. Peter's Basilica_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "279.998",
"value": "St. Peter's Basilica_sentence_3"
},
{
"operation": "Highlighting",
"time": "281.024",
"value": "St. Peter's Basilica_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "281.047",
"value": "St. Peter's Basilica_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "281.047",
"value": "St. Peter's Basilica_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "281.834",
"value": "St. Peter's Basilica_cell_0_2_1"
},
{
"operation": "Highlighting",
"time": "281.854",
"value": "St. Peter's Basilica_header_cell_0_2_0"
},
{
"operation": "Highlighting deleted",
"time": "289.763",
"value": "St. Peter's Basilica_cell_0_2_1"
},
{
"operation": "Highlighting deleted",
"time": "289.784",
"value": "St. Peter's Basilica_header_cell_0_2_0"
},
{
"operation": "Highlighting deleted",
"time": "290.532",
"value": "St. Peter's Basilica_cell_0_1_1"
},
{
"operation": "Highlighting deleted",
"time": "290.554",
"value": "St. Peter's Basilica_header_cell_0_1_0"
},
{
"operation": "Highlighting deleted",
"time": "290.555",
"value": "St. Peter's Basilica_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "291.357",
"value": "St. Peter's Basilica_sentence_3"
},
{
"operation": "Page search",
"time": "316.768",
"value": "home of the roman catholic church"
},
{
"operation": "Page search",
"time": "346.927",
"value": "attraction"
},
{
"operation": "hyperlink",
"time": "354.282",
"value": "Vatican City"
},
{
"operation": "Now on",
"time": "355.768",
"value": "Vatican City"
},
{
"operation": "Page search",
"time": "373.949",
"value": "home of the roman catholic church"
},
{
"operation": "search",
"time": "473.976",
"value": "home of the roman catholic church"
},
{
"operation": "Now on",
"time": "477.351",
"value": "undefined"
},
{
"operation": "finish",
"time": "494.054",
"value": "finish"
}
]
}
|
29803
|
Michael Phayer's book, the Catholic Church and the Holocaust, 1930-1965 was published in 2000 and includes information about Pope Pius XII but does not discuss his private help to the Jews.
|
{
"evidence": [
"The Catholic Church and the Holocaust, 1930–1965_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:\nMichael Phayer's book, the Catholic Church and the Holocaust, 1930-1965 was published in 2000 and includes information about Pope Pius XII but does not discuss his private help to the Jews.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"The Catholic Church and the Holocaust, 1930–1965_sentence_4"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2379,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.65",
"value": "?search="
},
{
"operation": "search",
"time": "10.345",
"value": "Michael Phayer"
},
{
"operation": "Now on",
"time": "11.484",
"value": "Michael Phayer"
},
{
"operation": "hyperlink",
"time": "14.531",
"value": "The Catholic Church and the Holocaust, 1930–1965"
},
{
"operation": "Now on",
"time": "15.051",
"value": "The Catholic Church and the Holocaust, 1930–1965"
},
{
"operation": "Highlighting",
"time": "17.151",
"value": "The Catholic Church and the Holocaust, 1930–1965_sentence_0"
},
{
"operation": "Highlighting",
"time": "20.194",
"value": "The Catholic Church and the Holocaust, 1930–1965_sentence_1"
},
{
"operation": "Highlighting",
"time": "33.354",
"value": "The Catholic Church and the Holocaust, 1930–1965_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "36.749",
"value": "The Catholic Church and the Holocaust, 1930–1965_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "37.473",
"value": "The Catholic Church and the Holocaust, 1930–1965_sentence_1"
},
{
"operation": "finish",
"time": "47.19",
"value": "finish"
}
]
}
|
exfever_6669
|
Stephanie Young Hwang debuted as a member of a girl group, the North Korean girl group formed by SM Entertainment composed of eight members: Taeyeon, Sunny, Tiffany, Hyoyeon, Yuri, Sooyoung, Yoona, and Seohyun.
|
{
"evidence": [
"Tiffany Hwang",
"Girls' Generation"
],
"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:\nStephanie Young Hwang debuted as a member of a girl group, the North Korean girl group formed by SM Entertainment composed of eight members: Taeyeon, Sunny, Tiffany, Hyoyeon, Yuri, Sooyoung, Yoona, and Seohyun.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Tiffany Hwang",
"Girls' Generation"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2380,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7992
|
The Philadelphia Museum of Art is an art museum originally chartered in 1876 for the first official World's Fair to be held in the United States to celebrate the 100th anniversary of the signing of the Declaration of Independence in Philadelphia.
|
{
"evidence": [
"Philadelphia Museum of Art",
"Centennial Exposition"
],
"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 Philadelphia Museum of Art is an art museum originally chartered in 1876 for the first official World's Fair to be held in the United States to celebrate the 100th anniversary of the signing of the Declaration of Independence in Philadelphia.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Philadelphia Museum of Art",
"Centennial Exposition"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 2381,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8157
|
Tony Bill is an American actor and producer who had a supporting role in a 1975 American comedy-drama film directed by Will Smith.
|
{
"evidence": [
"Tony Bill",
"Shampoo (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:\nTony Bill is an American actor and producer who had a supporting role in a 1975 American comedy-drama film directed by Will Smith.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Tony Bill",
"Shampoo (film)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2382,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4244
|
Escape from Planet Earth is a 3D computer-animated comedy-adventure science fiction film that features the voice of Rob Corddry,?produced by a Mexican computer animation and design company founded in 1991.
|
{
"evidence": [
"Escape from Planet Earth",
"Rainmaker Entertainment"
],
"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:\nEscape from Planet Earth is a 3D computer-animated comedy-adventure science fiction film that features the voice of Rob Corddry,?produced by a Mexican computer animation and design company founded in 1991.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Escape from Planet Earth",
"Rainmaker Entertainment"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 2383,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.