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 |
|---|---|---|---|---|---|---|---|---|
37917
|
Ian Fells was the President of The Institute of Energy for 1978-79, then in 1993, he received the Michael Faraday medal and prize from the Royal Society.
|
{
"evidence": [
"Ian Fells_sentence_10",
"Ian Fells_sentence_11"
],
"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:\nIan Fells was the President of The Institute of Energy for 1978-79, then in 1993, he received the Michael Faraday medal and prize from the Royal Society.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Ian Fells_sentence_10",
"Ian Fells_sentence_11"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4184,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.151",
"value": "?search="
},
{
"operation": "Now on",
"time": "25.495",
"value": "?search="
},
{
"operation": "search",
"time": "35.896",
"value": "Ian Fells"
},
{
"operation": "Now on",
"time": "36.836",
"value": "Ian Fells"
},
{
"operation": "Highlighting",
"time": "55.822",
"value": "Ian Fells_sentence_10"
},
{
"operation": "Highlighting",
"time": "60.998",
"value": "Ian Fells_sentence_11"
},
{
"operation": "Highlighting",
"time": "143.628",
"value": "Ian Fells_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "144.198",
"value": "Ian Fells_sentence_0"
},
{
"operation": "finish",
"time": "147.794",
"value": "finish"
}
]
}
|
39042
|
The 2017 VCU Rams baseball team was their tenth season in the Atlantic Ten Conference and won their third Atlantic Ten Conference Baseball Tournament.
|
{
"evidence": [
"2017 VCU Rams baseball team_sentence_1"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe 2017 VCU Rams baseball team was their tenth season in the Atlantic Ten Conference and won their third Atlantic Ten Conference Baseball Tournament.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"2017 VCU Rams baseball team_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4185,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.133",
"value": "?search="
},
{
"operation": "search",
"time": "16.145",
"value": "2017 VCU Rams baseball team"
},
{
"operation": "Now on",
"time": "17.04",
"value": "2017 VCU Rams baseball team"
},
{
"operation": "Highlighting",
"time": "19.879",
"value": "2017 VCU Rams baseball team_sentence_1"
},
{
"operation": "hyperlink",
"time": "58.096",
"value": "VCU Rams baseball"
},
{
"operation": "Now on",
"time": "58.736",
"value": "VCU Rams baseball"
},
{
"operation": "hyperlink",
"time": "73.72",
"value": "Atlantic 10"
},
{
"operation": "Now on",
"time": "75.806",
"value": "Atlantic 10 Conference"
},
{
"operation": "back-button-clicked",
"time": "76.383",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "76.448",
"value": "VCU Rams baseball"
},
{
"operation": "hyperlink",
"time": "77.985",
"value": "Atlantic 10 Conference"
},
{
"operation": "Now on",
"time": "78.462",
"value": "Atlantic 10 Conference"
},
{
"operation": "hyperlink",
"time": "90.922",
"value": "4.3 Current tournament champions Atlantic 10 Conference_section_14"
},
{
"operation": "finish",
"time": "95.593",
"value": "finish"
}
]
}
|
exfever_6804
|
Fergie is a singer who sang a song that serviced mainstream radios through A&M Records, together with a vanity label founded by a music artist of Black Eyed Peas.
|
{
"evidence": [
"Fergie (singer)",
"Glamorous (Fergie song)",
"Will.i.am Music 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:\nFergie is a singer who sang a song that serviced mainstream radios through A&M Records, together with a vanity label founded by a music artist of Black Eyed Peas.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Fergie (singer)",
"Glamorous (Fergie song)",
"Will.i.am Music Group"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4186,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
23376
|
Love at First Sting is the ninth studio album released on 27 March 1984 on Harvest/EMI by German hard rock band Rammstein, which received a rating of 7/10 from Collector's Guide to Heavy Metal and 7.5/10 from Rock Hard.
|
{
"evidence": [
"Rammstein discography_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:\nLove at First Sting is the ninth studio album released on 27 March 1984 on Harvest/EMI by German hard rock band Rammstein, which received a rating of 7/10 from Collector's Guide to Heavy Metal and 7.5/10 from Rock Hard.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Rammstein discography_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4187,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.758",
"value": "?search="
},
{
"operation": "search",
"time": "16.324",
"value": "Love at First Sting"
},
{
"operation": "Now on",
"time": "17.779",
"value": "Love at First Sting"
},
{
"operation": "search",
"time": "47.911",
"value": "Rammstein discography"
},
{
"operation": "Now on",
"time": "49.087",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "51.288",
"value": "Rammstein discography"
},
{
"operation": "Now on",
"time": "52.348",
"value": "Rammstein discography"
},
{
"operation": "Page search",
"time": "64.252",
"value": "sting"
},
{
"operation": "Page search",
"time": "88.834",
"value": "love"
},
{
"operation": "Highlighting",
"time": "132.737",
"value": "Rammstein discography_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "133.853",
"value": "Rammstein discography_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "133.884",
"value": "Rammstein discography_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "133.885",
"value": "Rammstein discography_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "176.342",
"value": "Rammstein discography_cell_0_1_1"
},
{
"operation": "Highlighting deleted",
"time": "176.367",
"value": "Rammstein discography_header_cell_0_1_0"
},
{
"operation": "Highlighting deleted",
"time": "176.373",
"value": "Rammstein discography_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "180.775",
"value": "Rammstein discography_sentence_0"
},
{
"operation": "finish",
"time": "246.983",
"value": "finish"
}
]
}
|
exfever_6795
|
A. J. Cook has won an Emmy Award for her role in Criminal Minds.
|
{
"evidence": [
"A. J. Cook",
"Jennifer Jareau"
],
"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. J. Cook has won an Emmy Award for her role in Criminal Minds.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"A. J. Cook",
"Jennifer Jareau"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4188,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2993
|
Russia is the wealthiest country in the world.
|
{
"evidence": [
"Russia",
"Eastern Europe"
],
"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:\nRussia is the wealthiest country in the world.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Russia",
"Eastern Europe"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4189,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
65808
|
Michel Branamour Menard was a Canadian-born trader and merchant who co-founded Galveston, Texas.
|
{
"evidence": [
"Michel Branamour Menard_sentence_0",
"Michel Branamour Menard_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:\nMichel Branamour Menard was a Canadian-born trader and merchant who co-founded Galveston, Texas.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Michel Branamour Menard_sentence_0",
"Michel Branamour Menard_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4190,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.46",
"value": "?search="
},
{
"operation": "search",
"time": "25.131",
"value": "Michel Branamour Menard"
},
{
"operation": "Now on",
"time": "26.364",
"value": "Michel Branamour Menard"
},
{
"operation": "Highlighting",
"time": "36.121",
"value": "Michel Branamour Menard_sentence_0"
},
{
"operation": "Highlighting",
"time": "42.818",
"value": "Michel Branamour Menard_sentence_1"
},
{
"operation": "finish",
"time": "81.093",
"value": "finish"
}
]
}
|
73726
|
Bobby Hajjaj completed his early schooling at Maple Leaf International School and went to college at the University of Texas at Austin.
|
{
"evidence": [
"Bobby Hajjaj_sentence_13",
"Bobby Hajjaj_sentence_14"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nBobby Hajjaj completed his early schooling at Maple Leaf International School and went to college at the University of Texas at Austin.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Bobby Hajjaj_sentence_13",
"Bobby Hajjaj_sentence_14"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4191,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.779",
"value": "?search="
},
{
"operation": "search",
"time": "22.174",
"value": "Bobby Hajjaj"
},
{
"operation": "Now on",
"time": "23.072",
"value": "Bobby Hajjaj"
},
{
"operation": "Highlighting",
"time": "102.218",
"value": "Bobby Hajjaj_sentence_13"
},
{
"operation": "Highlighting",
"time": "106.071",
"value": "Bobby Hajjaj_sentence_14"
},
{
"operation": "finish",
"time": "144.535",
"value": "finish"
}
]
}
|
exfever_1666
|
Snapchat is a unique tool for businesses to connect with customers.
|
{
"evidence": [
"Miranda Kerr",
"Snapchat"
],
"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:\nSnapchat is a unique tool for businesses to connect with customers.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Miranda Kerr",
"Snapchat"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4192,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3558
|
The only school with a drama department is Juilliard.
|
{
"evidence": [
"Drama school",
"Arts administration"
],
"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 only school with a drama department is Juilliard.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Drama school",
"Arts administration"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4193,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_960
|
Katherine Heigl is an American actress that made her debut in acting in the 1992 American coming-of-age romantic drama film starring an artist known for her portrayals of offbeat characters, often in films with dark themes.
|
{
"evidence": [
"Katherine Heigl",
"That Night",
"Juliette Lewis"
],
"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:\nKatherine Heigl is an American actress that made her debut in acting in the 1992 American coming-of-age romantic drama film starring an artist known for her portrayals of offbeat characters, often in films with dark themes.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Katherine Heigl",
"That Night",
"Juliette Lewis"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4194,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7276
|
iPhone 4 is the first smartphone released in 2010.
|
{
"evidence": [
"IPhone 4",
"Apple Inc."
],
"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:\niPhone 4 is the first smartphone released in 2010.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"IPhone 4",
"Apple Inc."
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4195,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7174
|
Honest is the third studio album by American rapper Nayvadius DeMun Wilburn, an American singer known for his mumble-influenced vocal range and prolific output.
|
{
"evidence": [
"Honest (Future album)",
"Future (rapper)"
],
"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:\nHonest is the third studio album by American rapper Nayvadius DeMun Wilburn, an American singer known for his mumble-influenced vocal range and prolific output.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Honest (Future album)",
"Future (rapper)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4196,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
82784
|
Sugar Shuffle had a single author.
|
{
"evidence": [
"Sugar Shuffle_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:\nSugar Shuffle had a single author.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Sugar Shuffle_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4197,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.84",
"value": "?search="
},
{
"operation": "search",
"time": "40.377",
"value": "Sugar Shuffle"
},
{
"operation": "Now on",
"time": "41.04",
"value": "Sugar Shuffle"
},
{
"operation": "Highlighting",
"time": "48.591",
"value": "Sugar Shuffle_sentence_0"
},
{
"operation": "Highlighting",
"time": "61.487",
"value": "Sugar Shuffle_sentence_10"
},
{
"operation": "Highlighting deleted",
"time": "63.303",
"value": "Sugar Shuffle_sentence_10"
},
{
"operation": "finish",
"time": "65.455",
"value": "finish"
}
]
}
|
87588
|
Bruna or Rocca Bruna tower, located not so far from Piazza del Campo, was one of the city's highest towers in competition with the Mangia tower; and like most of Siena's towers, it was "elongated" in the sixteenth century.
|
{
"evidence": [
"Torre di Roccabruna_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:\nBruna or Rocca Bruna tower, located not so far from Piazza del Campo, was one of the city's highest towers in competition with the Mangia tower; and like most of Siena's towers, it was \"elongated\" in the sixteenth century.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Torre di Roccabruna_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4198,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.217",
"value": "?search="
},
{
"operation": "search",
"time": "33.96",
"value": "Contains...Bruna or Rocca Bruna tower"
},
{
"operation": "Now on",
"time": "34.893",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "41.784",
"value": "Torre di Roccabruna"
},
{
"operation": "Now on",
"time": "42.251",
"value": "Torre di Roccabruna"
},
{
"operation": "Page search",
"time": "47.51",
"value": "bruna"
},
{
"operation": "Page search",
"time": "59.285",
"value": "brunna or rocca"
},
{
"operation": "Highlighting",
"time": "71.689",
"value": "Torre di Roccabruna_sentence_1"
},
{
"operation": "hyperlink",
"time": "117.784",
"value": "Tuscany"
},
{
"operation": "Now on",
"time": "119.029",
"value": "Tuscany"
},
{
"operation": "Page search",
"time": "124.478",
"value": "campo"
},
{
"operation": "back-button-clicked",
"time": "139.633",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "139.715",
"value": "Torre di Roccabruna"
},
{
"operation": "Highlighting",
"time": "156.665",
"value": "Torre di Roccabruna_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "157.976",
"value": "Torre di Roccabruna_sentence_1"
},
{
"operation": "finish",
"time": "441.223",
"value": "finish"
}
]
}
|
exfever_4756
|
England is the largest country in United Kingdom.
|
{
"evidence": [
"Bradford",
"Textile manufacture during the Industrial Revolution"
],
"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:\nEngland is the largest country in United Kingdom.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Bradford",
"Textile manufacture during the Industrial Revolution"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4199,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1056
|
The law of value is a central concept in Karl Marx's critique of political economy, first expounded in his polemic book that was published in Paris and Brussels in 1837.
|
{
"evidence": [
"Law of value",
"The Poverty of Philosophy"
],
"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 law of value is a central concept in Karl Marx's critique of political economy, first expounded in his polemic book that was published in Paris and Brussels in 1837.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Law of value",
"The Poverty of Philosophy"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4200,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
73198
|
Delaware electors voted for Franklin Pierce, who won the 17th quadrennial presidential election of 1852.
|
{
"evidence": [
"1852 United States presidential election_sentence_1",
"1852 United States presidential election in Delaware_sentence_3",
"1852 United States presidential election_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:\nDelaware electors voted for Franklin Pierce, who won the 17th quadrennial presidential election of 1852.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"1852 United States presidential election_sentence_1",
"1852 United States presidential election in Delaware_sentence_3",
"1852 United States presidential election_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4201,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.604",
"value": "?search="
},
{
"operation": "search",
"time": "14.89",
"value": "Contains...17th quadrennial presidential election of 1852"
},
{
"operation": "Now on",
"time": "16.807",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "26.351",
"value": "1852 United States presidential election"
},
{
"operation": "Now on",
"time": "27.704",
"value": "1852 United States presidential election"
},
{
"operation": "Highlighting",
"time": "29.873",
"value": "1852 United States presidential election_sentence_1"
},
{
"operation": "search",
"time": "64.668",
"value": "1852 presidential election in delaware"
},
{
"operation": "Now on",
"time": "67.148",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "72.653",
"value": "Results 1852 United States presidential election in Delaware_section_0"
},
{
"operation": "Now on",
"time": "73.483",
"value": "1852 United States presidential election in Delaware#Results 1852 United States presidential election in Delaware section 0"
},
{
"operation": "hyperlink",
"time": "77.158",
"value": "United States presidential elections in Delaware"
},
{
"operation": "Now on",
"time": "80.564",
"value": "United States presidential elections in Delaware"
},
{
"operation": "Highlighting",
"time": "86.615",
"value": "United States presidential elections in Delaware_cell_3_2_2"
},
{
"operation": "Highlighting",
"time": "86.617",
"value": "United States presidential elections in Delaware_title"
},
{
"operation": "Highlighting",
"time": "86.619",
"value": "United States presidential elections in Delaware_section_2"
},
{
"operation": "Highlighting",
"time": "86.621",
"value": "United States presidential elections in Delaware_header_cell_3_0_2"
},
{
"operation": "Highlighting",
"time": "87.146",
"value": "United States presidential elections in Delaware_cell_3_2_1"
},
{
"operation": "Highlighting",
"time": "87.149",
"value": "United States presidential elections in Delaware_header_cell_3_0_1"
},
{
"operation": "Highlighting deleted",
"time": "87.561",
"value": "United States presidential elections in Delaware_cell_3_2_2"
},
{
"operation": "Highlighting deleted",
"time": "87.565",
"value": "United States presidential elections in Delaware_header_cell_3_0_2"
},
{
"operation": "Highlighting deleted",
"time": "96.812",
"value": "United States presidential elections in Delaware_cell_3_2_1"
},
{
"operation": "Highlighting deleted",
"time": "96.814",
"value": "United States presidential elections in Delaware_title"
},
{
"operation": "Highlighting deleted",
"time": "96.816",
"value": "United States presidential elections in Delaware_section_2"
},
{
"operation": "Highlighting deleted",
"time": "96.818",
"value": "United States presidential elections in Delaware_header_cell_3_0_1"
},
{
"operation": "Highlighting",
"time": "97.802",
"value": "United States presidential elections in Delaware_cell_3_2_0"
},
{
"operation": "Highlighting",
"time": "97.804",
"value": "United States presidential elections in Delaware_title"
},
{
"operation": "Highlighting",
"time": "97.804",
"value": "United States presidential elections in Delaware_section_2"
},
{
"operation": "Highlighting",
"time": "97.805",
"value": "United States presidential elections in Delaware_header_cell_3_0_0"
},
{
"operation": "Highlighting",
"time": "98.409",
"value": "United States presidential elections in Delaware_cell_3_2_1"
},
{
"operation": "Highlighting",
"time": "98.412",
"value": "United States presidential elections in Delaware_header_cell_3_0_1"
},
{
"operation": "Highlighting",
"time": "102.793",
"value": "United States presidential elections in Delaware_cell_3_2_3"
},
{
"operation": "Highlighting",
"time": "102.796",
"value": "United States presidential elections in Delaware_header_cell_3_0_3"
},
{
"operation": "Highlighting deleted",
"time": "104.339",
"value": "United States presidential elections in Delaware_cell_3_2_3"
},
{
"operation": "Highlighting deleted",
"time": "104.343",
"value": "United States presidential elections in Delaware_header_cell_3_0_3"
},
{
"operation": "Highlighting",
"time": "104.81",
"value": "United States presidential elections in Delaware_cell_3_2_2"
},
{
"operation": "Highlighting",
"time": "104.812",
"value": "United States presidential elections in Delaware_header_cell_3_0_2"
},
{
"operation": "Highlighting",
"time": "105.268",
"value": "United States presidential elections in Delaware_cell_3_2_3"
},
{
"operation": "Highlighting",
"time": "105.27",
"value": "United States presidential elections in Delaware_header_cell_3_0_3"
},
{
"operation": "Highlighting",
"time": "106.418",
"value": "United States presidential elections in Delaware_cell_3_2_4"
},
{
"operation": "Highlighting",
"time": "106.421",
"value": "United States presidential elections in Delaware_header_cell_3_0_4"
},
{
"operation": "Highlighting",
"time": "113.235",
"value": "United States presidential elections in Delaware_cell_3_2_5"
},
{
"operation": "Highlighting",
"time": "113.239",
"value": "United States presidential elections in Delaware_header_cell_3_0_5"
},
{
"operation": "Highlighting",
"time": "113.999",
"value": "United States presidential elections in Delaware_cell_3_2_6"
},
{
"operation": "Highlighting",
"time": "114.002",
"value": "United States presidential elections in Delaware_header_cell_3_0_6"
},
{
"operation": "Highlighting",
"time": "118.759",
"value": "United States presidential elections in Delaware_cell_3_2_7"
},
{
"operation": "Highlighting",
"time": "118.762",
"value": "United States presidential elections in Delaware_header_cell_3_0_7"
},
{
"operation": "Highlighting",
"time": "119.208",
"value": "United States presidential elections in Delaware_cell_3_2_8"
},
{
"operation": "Highlighting",
"time": "119.212",
"value": "United States presidential elections in Delaware_header_cell_3_0_8"
},
{
"operation": "Highlighting",
"time": "119.725",
"value": "United States presidential elections in Delaware_cell_3_2_9"
},
{
"operation": "Highlighting",
"time": "119.727",
"value": "United States presidential elections in Delaware_header_cell_3_0_9"
},
{
"operation": "Highlighting deleted",
"time": "197.632",
"value": "United States presidential elections in Delaware_cell_3_2_0"
},
{
"operation": "Highlighting deleted",
"time": "197.636",
"value": "United States presidential elections in Delaware_header_cell_3_0_0"
},
{
"operation": "Highlighting deleted",
"time": "198.332",
"value": "United States presidential elections in Delaware_cell_3_2_1"
},
{
"operation": "Highlighting deleted",
"time": "198.336",
"value": "United States presidential elections in Delaware_header_cell_3_0_1"
},
{
"operation": "Highlighting deleted",
"time": "198.783",
"value": "United States presidential elections in Delaware_cell_3_2_2"
},
{
"operation": "Highlighting deleted",
"time": "198.786",
"value": "United States presidential elections in Delaware_header_cell_3_0_2"
},
{
"operation": "Highlighting deleted",
"time": "199.256",
"value": "United States presidential elections in Delaware_cell_3_2_3"
},
{
"operation": "Highlighting deleted",
"time": "199.259",
"value": "United States presidential elections in Delaware_header_cell_3_0_3"
},
{
"operation": "Highlighting deleted",
"time": "199.998",
"value": "United States presidential elections in Delaware_cell_3_2_4"
},
{
"operation": "Highlighting deleted",
"time": "200.003",
"value": "United States presidential elections in Delaware_header_cell_3_0_4"
},
{
"operation": "Highlighting deleted",
"time": "200.469",
"value": "United States presidential elections in Delaware_cell_3_2_5"
},
{
"operation": "Highlighting deleted",
"time": "200.472",
"value": "United States presidential elections in Delaware_header_cell_3_0_5"
},
{
"operation": "Highlighting deleted",
"time": "200.885",
"value": "United States presidential elections in Delaware_cell_3_2_6"
},
{
"operation": "Highlighting deleted",
"time": "200.888",
"value": "United States presidential elections in Delaware_header_cell_3_0_6"
},
{
"operation": "Highlighting deleted",
"time": "201.404",
"value": "United States presidential elections in Delaware_cell_3_2_7"
},
{
"operation": "Highlighting deleted",
"time": "201.408",
"value": "United States presidential elections in Delaware_header_cell_3_0_7"
},
{
"operation": "Highlighting deleted",
"time": "201.819",
"value": "United States presidential elections in Delaware_cell_3_2_8"
},
{
"operation": "Highlighting deleted",
"time": "201.823",
"value": "United States presidential elections in Delaware_header_cell_3_0_8"
},
{
"operation": "Highlighting deleted",
"time": "202.136",
"value": "United States presidential elections in Delaware_cell_3_2_9"
},
{
"operation": "Highlighting deleted",
"time": "202.138",
"value": "United States presidential elections in Delaware_title"
},
{
"operation": "Highlighting deleted",
"time": "202.139",
"value": "United States presidential elections in Delaware_section_2"
},
{
"operation": "Highlighting deleted",
"time": "202.141",
"value": "United States presidential elections in Delaware_header_cell_3_0_9"
},
{
"operation": "hyperlink",
"time": "203.289",
"value": "1852"
},
{
"operation": "Now on",
"time": "203.668",
"value": "1852 United States presidential election in Delaware"
},
{
"operation": "Highlighting",
"time": "209.604",
"value": "1852 United States presidential election in Delaware_sentence_3"
},
{
"operation": "hyperlink",
"time": "218.938",
"value": "1852 United States presidential election"
},
{
"operation": "Now on",
"time": "219.459",
"value": "1852 United States presidential election"
},
{
"operation": "Highlighting",
"time": "221.876",
"value": "1852 United States presidential election_sentence_2"
},
{
"operation": "finish",
"time": "230.422",
"value": "finish"
}
]
}
|
81421
|
Dorothea de Ficquelmont gave birth to her only daughter, Elisabeth-Alexandrine-Marie-Theresa de Ficquelmont, Princess Clary und Aldringen then in 1829, Dolly's husband was appointed Austrian Ambassador in Russia.
|
{
"evidence": [
"Dorothea de Ficquelmont_sentence_11",
"Dorothea de Ficquelmont_sentence_12"
],
"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:\nDorothea de Ficquelmont gave birth to her only daughter, Elisabeth-Alexandrine-Marie-Theresa de Ficquelmont, Princess Clary und Aldringen then in 1829, Dolly's husband was appointed Austrian Ambassador in Russia.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Dorothea de Ficquelmont_sentence_11",
"Dorothea de Ficquelmont_sentence_12"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4202,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.417",
"value": "?search="
},
{
"operation": "search",
"time": "40.774",
"value": "Dorothea de Ficquelmont"
},
{
"operation": "Now on",
"time": "41.794",
"value": "Dorothea de Ficquelmont"
},
{
"operation": "Highlighting",
"time": "51.199",
"value": "Dorothea de Ficquelmont_sentence_11"
},
{
"operation": "Highlighting",
"time": "68.78",
"value": "Dorothea de Ficquelmont_sentence_12"
},
{
"operation": "finish",
"time": "81.205",
"value": "finish"
}
]
}
|
73358
|
The Latter Day Saint movement held a policy of excommunication of erring members.
|
{
"evidence": [
"The Church of Jesus Christ of Latter-day Saints_sentence_146"
],
"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 Latter Day Saint movement held a policy of excommunication of erring members.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"The Church of Jesus Christ of Latter-day Saints_sentence_146"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4203,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.249",
"value": "?search="
},
{
"operation": "search",
"time": "31.056",
"value": "latter day saint movement excommunication"
},
{
"operation": "Now on",
"time": "34.376",
"value": "undefined"
},
{
"operation": "search",
"time": "60.423",
"value": "Latter-day Saints"
},
{
"operation": "Now on",
"time": "71.506",
"value": "The Church of Jesus Christ of Latter-day Saints"
},
{
"operation": "hyperlink",
"time": "106.755",
"value": "6 Controversy and criticism The Church of Jesus Christ of Latter-day Saints_section_22"
},
{
"operation": "hyperlink",
"time": "155.928",
"value": "List of sects in the Latter Day Saint movement"
},
{
"operation": "Now on",
"time": "163.18",
"value": "List of denominations in the Latter Day Saint movement"
},
{
"operation": "search",
"time": "254.683",
"value": "excommunication"
},
{
"operation": "Now on",
"time": "260.213",
"value": "Excommunication"
},
{
"operation": "hyperlink",
"time": "298.194",
"value": "1.8 The Church of Jesus Christ of Latter-day Saints Excommunication_section_19"
},
{
"operation": "Highlighting",
"time": "300.784",
"value": "Excommunication_sentence_137"
},
{
"operation": "Highlighting",
"time": "300.785",
"value": "Excommunication_title"
},
{
"operation": "Highlighting",
"time": "300.787",
"value": "Excommunication_section_0"
},
{
"operation": "Highlighting",
"time": "300.788",
"value": "Excommunication_section_19"
},
{
"operation": "Highlighting deleted",
"time": "349.174",
"value": "Excommunication_sentence_137"
},
{
"operation": "Highlighting deleted",
"time": "349.174",
"value": "Excommunication_title"
},
{
"operation": "Highlighting deleted",
"time": "349.177",
"value": "Excommunication_section_0"
},
{
"operation": "Highlighting deleted",
"time": "349.178",
"value": "Excommunication_section_19"
},
{
"operation": "hyperlink",
"time": "356.79",
"value": "The Church of Jesus Christ of Latter-day Saints"
},
{
"operation": "Now on",
"time": "370.865",
"value": "The Church of Jesus Christ of Latter-day Saints"
},
{
"operation": "hyperlink",
"time": "392.879",
"value": "3.4 Programs and organizations The Church of Jesus Christ of Latter-day Saints_section_14"
},
{
"operation": "search",
"time": "540.523",
"value": "intitle"
},
{
"operation": "Now on",
"time": "542.999",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "547.443",
"value": "Comparisons with Christian denominations outside the Latter Day Saint movement The Church of Jesus Christ of Latter-day Saints_section_8"
},
{
"operation": "Now on",
"time": "548.425",
"value": "The Church of Jesus Christ of Latter-day Saints#Comparisons with Christian denominations outside the Latter Day Saint movement The Church of Jesus Christ of Latter-day Saints section 8"
},
{
"operation": "Highlighting",
"time": "602.719",
"value": "The Church of Jesus Christ of Latter-day Saints_sentence_146"
},
{
"operation": "back-button-clicked",
"time": "634.333",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "635.976",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "660.528",
"value": "Comparisons with Christian denominations outside the Latter Day Saint movement The Church of Jesus Christ of Latter-day Saints_section_8"
},
{
"operation": "Now on",
"time": "661.514",
"value": "The Church of Jesus Christ of Latter-day Saints#Comparisons with Christian denominations outside the Latter Day Saint movement The Church of Jesus Christ of Latter-day Saints section 8"
},
{
"operation": "search",
"time": "796.32",
"value": "intitle"
},
{
"operation": "Now on",
"time": "797.752",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "800.668",
"value": "Origin Mormonism and polygamy_section_0"
},
{
"operation": "Now on",
"time": "802.741",
"value": "Mormonism and polygamy#Origin Mormonism and polygamy section 0"
},
{
"operation": "Highlighting",
"time": "819.395",
"value": "Mormonism and polygamy_sentence_34"
},
{
"operation": "Highlighting",
"time": "819.395",
"value": "Mormonism and polygamy_title"
},
{
"operation": "Highlighting",
"time": "819.396",
"value": "Mormonism and polygamy_section_0"
},
{
"operation": "search",
"time": "894.209",
"value": "intitle"
},
{
"operation": "Now on",
"time": "896.914",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "910.9",
"value": "Teachings on the multiple wives of God and Jesus Mormonism and polygamy_section_1"
},
{
"operation": "Now on",
"time": "912.017",
"value": "Mormonism and polygamy#Teachings on the multiple wives of God and Jesus Mormonism and polygamy section 1"
},
{
"operation": "finish",
"time": "953.815",
"value": "finish"
}
]
}
|
54943
|
Western Australia that has been held by multiple people such as William Angwin (who was Deputy Premier of Western Australia at the time) in 1924, and Frank Troy in 1933.
|
{
"evidence": [
"William Angwin_sentence_2",
"Frank Troy_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:\nWestern Australia that has been held by multiple people such as William Angwin (who was Deputy Premier of Western Australia at the time) in 1924, and Frank Troy in 1933.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"William Angwin_sentence_2",
"Frank Troy_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4204,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.168",
"value": "?search="
},
{
"operation": "search",
"time": "45.799",
"value": "western australia deputy premier"
},
{
"operation": "Now on",
"time": "48.222",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "50.734",
"value": "Deputy Premier of Western Australia"
},
{
"operation": "Now on",
"time": "51.811",
"value": "Deputy Premier of Western Australia"
},
{
"operation": "search",
"time": "109.872",
"value": "western australia"
},
{
"operation": "Now on",
"time": "118.431",
"value": "Western Australia"
},
{
"operation": "search",
"time": "143.223",
"value": "William Angwin"
},
{
"operation": "Now on",
"time": "144.047",
"value": "William Angwin"
},
{
"operation": "Highlighting",
"time": "153.021",
"value": "William Angwin_sentence_2"
},
{
"operation": "search",
"time": "216.432",
"value": "Frank Troy"
},
{
"operation": "Now on",
"time": "217.412",
"value": "Frank Troy"
},
{
"operation": "Highlighting",
"time": "258.681",
"value": "Frank Troy_header_cell_0_10_0"
},
{
"operation": "Highlighting deleted",
"time": "259.692",
"value": "Frank Troy_header_cell_0_10_0"
},
{
"operation": "Highlighting",
"time": "270.503",
"value": "Frank Troy_sentence_3"
},
{
"operation": "finish",
"time": "278.547",
"value": "finish"
}
]
}
|
67889
|
Randy Sparks had always wanted to form a music group, but it never happened due to his exclusive contract.
|
{
"evidence": [
"Randy Sparks_sentence_5"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nRandy Sparks had always wanted to form a music group, but it never happened due to his exclusive contract.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Randy Sparks_sentence_5"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4205,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "6.889",
"value": "?search="
},
{
"operation": "search",
"time": "12.928",
"value": "Randy Sparks"
},
{
"operation": "Now on",
"time": "14.464",
"value": "Randy Sparks"
},
{
"operation": "Highlighting",
"time": "24.686",
"value": "Randy Sparks_sentence_5"
},
{
"operation": "finish",
"time": "59.456",
"value": "finish"
}
]
}
|
exfever_7402
|
Azerbaijan is the biggest transcontinental country in the world.
|
{
"evidence": [
"Azerbaijan",
"Transcaucasia"
],
"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:\nAzerbaijan is the biggest transcontinental country in the world.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Azerbaijan",
"Transcaucasia"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4206,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_694
|
SpongeBob SquarePants is a Canadian comedy television series made using animation techniques with a common series title, usually related to one another.
|
{
"evidence": [
"SpongeBob SquarePants",
"Animated series"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSpongeBob SquarePants is a Canadian comedy television series made using animation techniques with a common series title, usually related to one another.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"SpongeBob SquarePants",
"Animated series"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4207,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
88159
|
Cates proposed that jammed systems differ from ordinary solids in that if the direction of the applied stress changes, the jam will break up; and sometimes, the change of direction required is very small.
|
{
"evidence": [
"Fragile matter_sentence_4",
"Fragile matter_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:\nCates proposed that jammed systems differ from ordinary solids in that if the direction of the applied stress changes, the jam will break up; and sometimes, the change of direction required is very small.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Fragile matter_sentence_4",
"Fragile matter_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4208,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.898",
"value": "?search="
},
{
"operation": "search",
"time": "38.664",
"value": "Fragile matter"
},
{
"operation": "Now on",
"time": "39.215",
"value": "Fragile matter"
},
{
"operation": "Highlighting",
"time": "49.235",
"value": "Fragile matter_sentence_4"
},
{
"operation": "Highlighting",
"time": "61.613",
"value": "Fragile matter_sentence_5"
},
{
"operation": "finish",
"time": "68.667",
"value": "finish"
}
]
}
|
exfever_771
|
Mahendra Singh Dhoni is a professional cricketer known as a right-handed player on the fielding side who stands behind the wicket or stumps.
|
{
"evidence": [
"MS Dhoni",
"Wicket-keeper"
],
"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:\nMahendra Singh Dhoni is a professional cricketer known as a right-handed player on the fielding side who stands behind the wicket or stumps.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"MS Dhoni",
"Wicket-keeper"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4209,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
23939
|
John Player Classic is wrongly believed to have taken place four years between 1970 and 1973, one of the winners is Bob Charles.
|
{
"evidence": [
"John Player Classic_sentence_0",
"John Player Classic_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:\nJohn Player Classic is wrongly believed to have taken place four years between 1970 and 1973, one of the winners is Bob Charles.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"John Player Classic_sentence_0",
"John Player Classic_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4210,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.846",
"value": "?search="
},
{
"operation": "Now on",
"time": "24.96",
"value": "?search="
},
{
"operation": "search",
"time": "46.297",
"value": "john player classic"
},
{
"operation": "Now on",
"time": "47.29",
"value": "John Player Classic"
},
{
"operation": "search",
"time": "156.959",
"value": "john player classic wrongly"
},
{
"operation": "Now on",
"time": "158.814",
"value": "undefined"
},
{
"operation": "search",
"time": "185.546",
"value": "john player classic 1971"
},
{
"operation": "Now on",
"time": "186.578",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "193.127",
"value": "John Deere Classic"
},
{
"operation": "Now on",
"time": "194.538",
"value": "John Deere Classic"
},
{
"operation": "search",
"time": "226.678",
"value": "john player classic"
},
{
"operation": "Now on",
"time": "227.502",
"value": "John Player Classic"
},
{
"operation": "Highlighting",
"time": "238.965",
"value": "John Player Classic_sentence_0"
},
{
"operation": "Highlighting",
"time": "245.856",
"value": "John Player Classic_sentence_3"
},
{
"operation": "finish",
"time": "291.841",
"value": "finish"
}
]
}
|
exfever_2884
|
Walter Charles Dance was a high-paid English actor.
|
{
"evidence": [
"Charles Dance",
"Alien 3"
],
"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:\nWalter Charles Dance was a high-paid English actor.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Charles Dance",
"Alien 3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4211,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6218
|
Meek Mill is an African rapper who was signed to Maybach Music Group, a record label owned by an American rapper and record executive who had a debut single, Hustlin', in 2006.
|
{
"evidence": [
"Meek Mill",
"Rick Ross"
],
"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:\nMeek Mill is an African rapper who was signed to Maybach Music Group, a record label owned by an American rapper and record executive who had a debut single, Hustlin', in 2006.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Meek Mill",
"Rick Ross"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4212,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5779
|
Cars Toons features the main character, a fictional anthropomorphic stock car.
|
{
"evidence": [
"Cars Toons",
"Lightning McQueen"
],
"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:\nCars Toons features the main character, a fictional anthropomorphic stock car.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Cars Toons",
"Lightning McQueen"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4213,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7209
|
God's Own Country is the tagline of Kerala Tourism.
|
{
"evidence": [
"Kerala",
"Malabar Coast"
],
"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:\nGod's Own Country is the tagline of Kerala Tourism.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Kerala",
"Malabar Coast"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4214,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
77378
|
Professor Sharp began teaching neither at Cornell nor at Yale in 1936, as the university's first appointment in biology; then he remained devoted to Cornell, creating and directing programs, and teaching at and remaining connected with the university for 56 years.
|
{
"evidence": [
"Lester W. Sharp_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:\nProfessor Sharp began teaching neither at Cornell nor at Yale in 1936, as the university's first appointment in biology; then he remained devoted to Cornell, creating and directing programs, and teaching at and remaining connected with the university for 56 years.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Lester W. Sharp_sentence_4"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4215,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.648",
"value": "?search="
},
{
"operation": "search",
"time": "30.605",
"value": "Contains...Professor Sharp"
},
{
"operation": "Now on",
"time": "32.124",
"value": "undefined"
},
{
"operation": "search",
"time": "175.766",
"value": "Contains...Yale in 1936"
},
{
"operation": "Now on",
"time": "177.798",
"value": "undefined"
},
{
"operation": "search",
"time": "217.456",
"value": "\"university's first appointment in biology\""
},
{
"operation": "Now on",
"time": "218.397",
"value": "undefined"
},
{
"operation": "search",
"time": "243.248",
"value": "\"appointment in biology\""
},
{
"operation": "Now on",
"time": "244.16",
"value": "undefined"
},
{
"operation": "search",
"time": "299.915",
"value": "Cornell University"
},
{
"operation": "Now on",
"time": "301.705",
"value": "Cornell University"
},
{
"operation": "Highlighting",
"time": "516.903",
"value": "Cornell University_sentence_403"
},
{
"operation": "Highlighting",
"time": "516.905",
"value": "Cornell University_title"
},
{
"operation": "Highlighting",
"time": "516.906",
"value": "Cornell University_section_28"
},
{
"operation": "Highlighting",
"time": "516.906",
"value": "Cornell University_section_30"
},
{
"operation": "search",
"time": "549.653",
"value": "List of Cornell University alumni"
},
{
"operation": "Now on",
"time": "552.888",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "603.725",
"value": "Cornell University"
},
{
"operation": "Now on",
"time": "605.58",
"value": "Cornell University"
},
{
"operation": "Highlighting deleted",
"time": "754.493",
"value": "Cornell University_sentence_403"
},
{
"operation": "Highlighting deleted",
"time": "754.496",
"value": "Cornell University_title"
},
{
"operation": "Highlighting deleted",
"time": "754.499",
"value": "Cornell University_section_28"
},
{
"operation": "Highlighting deleted",
"time": "754.501",
"value": "Cornell University_section_30"
},
{
"operation": "hyperlink",
"time": "790.007",
"value": "List of Cornell University faculty"
},
{
"operation": "Now on",
"time": "793.438",
"value": "List of Cornell University faculty"
},
{
"operation": "search",
"time": "1101.324",
"value": "List of Yale University people"
},
{
"operation": "Now on",
"time": "1104.156",
"value": "List of Yale University people"
},
{
"operation": "Page search",
"time": "1121.872",
"value": "Professor Sharp"
},
{
"operation": "search",
"time": "1214.423",
"value": "Professor Sharp 1936"
},
{
"operation": "Now on",
"time": "1216.299",
"value": "undefined"
},
{
"operation": "search",
"time": "1311.208",
"value": "Sharp professor at Cornell"
},
{
"operation": "Now on",
"time": "1312.823",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "1329.416",
"value": "Eoörnis pterovelox gobiensis"
},
{
"operation": "Now on",
"time": "1330.791",
"value": "Eoörnis pterovelox gobiensis"
},
{
"operation": "hyperlink",
"time": "1335.893",
"value": "Lester W. Sharp"
},
{
"operation": "Now on",
"time": "1336.984",
"value": "Lester W. Sharp"
},
{
"operation": "Highlighting",
"time": "1365.148",
"value": "Lester W. Sharp_sentence_4"
},
{
"operation": "finish",
"time": "1449.252",
"value": "finish"
}
]
}
|
exfever_2099
|
Jeffrey Lynn Goldblum is an American actor who has starred in several films, including a 2016 American science fiction action film directed by Will Smith.
|
{
"evidence": [
"Jeff Goldblum",
"Independence Day: Resurgence"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJeffrey Lynn Goldblum is an American actor who has starred in several films, including a 2016 American science fiction action film directed by Will Smith.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jeff Goldblum",
"Independence Day: Resurgence"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4216,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
67904
|
Central Europe is home to churches known for their architecture, stonework, and historical significance.
|
{
"evidence": [
"Central Europe_sentence_192",
"List of central European countries by development indexes_sentence_21",
"List of central European countries by development indexes_sentence_22"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nCentral Europe is home to churches known for their architecture, stonework, and historical significance.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Central Europe_sentence_192",
"List of central European countries by development indexes_sentence_21",
"List of central European countries by development indexes_sentence_22"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4217,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.793",
"value": "?search="
},
{
"operation": "search",
"time": "11.018",
"value": "Central Europe"
},
{
"operation": "Now on",
"time": "12.764",
"value": "Central Europe"
},
{
"operation": "search",
"time": "49.985",
"value": "home to churches known for their architecture, stonework, and historical significance"
},
{
"operation": "Now on",
"time": "54.173",
"value": "undefined"
},
{
"operation": "search",
"time": "78.764",
"value": "Central Europe churches"
},
{
"operation": "Now on",
"time": "80.585",
"value": "undefined"
},
{
"operation": "search",
"time": "96.333",
"value": "Central Europe"
},
{
"operation": "Now on",
"time": "96.984",
"value": "Central Europe"
},
{
"operation": "hyperlink",
"time": "141.447",
"value": "8.1 Architecture Central Europe_section_39"
},
{
"operation": "hyperlink",
"time": "166.671",
"value": "List of central European countries by development indexes § Architecture"
},
{
"operation": "Now on",
"time": "167.728",
"value": "List of central European countries by development indexes#Architecture"
},
{
"operation": "search",
"time": "200.192",
"value": "central Europe"
},
{
"operation": "Now on",
"time": "200.815",
"value": "Central Europe"
},
{
"operation": "search",
"time": "238.124",
"value": "architecture, stonework, and historical significance"
},
{
"operation": "Now on",
"time": "239.244",
"value": "undefined"
},
{
"operation": "search",
"time": "255.263",
"value": "Churches Central Europe"
},
{
"operation": "Now on",
"time": "256.399",
"value": "undefined"
},
{
"operation": "search",
"time": "281.074",
"value": "Central Europe"
},
{
"operation": "Now on",
"time": "282.03",
"value": "Central Europe"
},
{
"operation": "Highlighting",
"time": "299.236",
"value": "Central Europe_sentence_192"
},
{
"operation": "hyperlink",
"time": "300.952",
"value": "List of central European countries by development indexes § Architecture"
},
{
"operation": "Now on",
"time": "301.393",
"value": "List of central European countries by development indexes#Architecture"
},
{
"operation": "Highlighting",
"time": "309.064",
"value": "List of central European countries by development indexes_sentence_21"
},
{
"operation": "Highlighting",
"time": "310.889",
"value": "List of central European countries by development indexes_sentence_22"
},
{
"operation": "finish",
"time": "323.958",
"value": "finish"
}
]
}
|
78493
|
The 1947 Memorial Cup final, the 29th junior ice hockey championship, was a rematch of the 1945 Memorial Cup, and featured the first Memorial Cup games played in the province of Ontario.
|
{
"evidence": [
"1947 Memorial Cup_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 1947 Memorial Cup final, the 29th junior ice hockey championship, was a rematch of the 1945 Memorial Cup, and featured the first Memorial Cup games played in the province of Ontario.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"1947 Memorial Cup_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4218,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.007",
"value": "?search="
},
{
"operation": "search",
"time": "36.076",
"value": "1947 Memorial Cup"
},
{
"operation": "Now on",
"time": "37.533",
"value": "1947 Memorial Cup"
},
{
"operation": "Highlighting",
"time": "53.245",
"value": "1947 Memorial Cup_sentence_2"
},
{
"operation": "finish",
"time": "75.713",
"value": "finish"
}
]
}
|
exfever_2162
|
The Vandals were a Spanish people who first inhabited what is now southern Poland which established Vandal kingdoms on a peninsula in southwestern Europe, defining the westernmost edge of Eurasia.
|
{
"evidence": [
"Vandals",
"Iberian Peninsula"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Vandals were a Spanish people who first inhabited what is now southern Poland which established Vandal kingdoms on a peninsula in southwestern Europe, defining the westernmost edge of Eurasia.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Vandals",
"Iberian Peninsula"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4219,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
60765
|
Felinus and Gratian, who were associated to Carpophorus and Fidelis, were all members of the Theban Legion and relics of Fidelis are claimed by Como only.
|
{
"evidence": [
"Felinus and Gratian_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:\nFelinus and Gratian, who were associated to Carpophorus and Fidelis, were all members of the Theban Legion and relics of Fidelis are claimed by Como only.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Felinus and Gratian_sentence_20"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4220,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "4.556",
"value": "?search="
},
{
"operation": "search",
"time": "15.103",
"value": "Felinus and Gratian"
},
{
"operation": "Now on",
"time": "17.389",
"value": "Felinus and Gratian"
},
{
"operation": "Page search",
"time": "29.915",
"value": "carpo"
},
{
"operation": "Highlighting",
"time": "36.399",
"value": "Felinus and Gratian_sentence_2"
},
{
"operation": "Page search",
"time": "53.667",
"value": "theban"
},
{
"operation": "Highlighting",
"time": "71.07",
"value": "Felinus and Gratian_sentence_20"
},
{
"operation": "finish",
"time": "89.446",
"value": "finish"
}
]
}
|
exfever_366
|
In the early 2000s, Wahlberg ventured into big budget action-oriented movies, such as a 2005 American heist action film with an English actor.
|
{
"evidence": [
"Mark Wahlberg",
"The Italian Job (2003 film)",
"Jason Statham"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nIn the early 2000s, Wahlberg ventured into big budget action-oriented movies, such as a 2005 American heist action film with an English actor.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Mark Wahlberg",
"The Italian Job (2003 film)",
"Jason Statham"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4221,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3078
|
Minions is a 2015 American computer-animated movie produced by Illumination Entertainment and distributed by Universal Pictures, whose genre is in a category of film that emphasizes humor and is designed to make the audience laugh through amusement.
|
{
"evidence": [
"Minions (film)",
"Comedy 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:\nMinions is a 2015 American computer-animated movie produced by Illumination Entertainment and distributed by Universal Pictures, whose genre is in a category of film that emphasizes humor and is designed to make the audience laugh through amusement.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Minions (film)",
"Comedy film"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4222,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
81313
|
Anoeschka von Meck (born in 1967) was a Namibian author who writes in the Afrikaans language and whose many achievements include being a matron at a children's home while also being a full-time reporter for Die Republikein and eventually releasing her breakthrough novel Vaselinetjie in 2004.
|
{
"evidence": [
"Anoeschka von Meck_sentence_0",
"Anoeschka von Meck_sentence_6",
"Anoeschka von Meck_sentence_7",
"Anoeschka von Meck_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:\nAnoeschka von Meck (born in 1967) was a Namibian author who writes in the Afrikaans language and whose many achievements include being a matron at a children's home while also being a full-time reporter for Die Republikein and eventually releasing her breakthrough novel Vaselinetjie in 2004.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Anoeschka von Meck_sentence_0",
"Anoeschka von Meck_sentence_6",
"Anoeschka von Meck_sentence_7",
"Anoeschka von Meck_sentence_8"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4223,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.853",
"value": "?search="
},
{
"operation": "search",
"time": "14.17",
"value": "Anoeschka von Meck"
},
{
"operation": "Now on",
"time": "15.393",
"value": "Anoeschka von Meck"
},
{
"operation": "Highlighting",
"time": "17.82",
"value": "Anoeschka von Meck_sentence_0"
},
{
"operation": "Highlighting",
"time": "29.108",
"value": "Anoeschka von Meck_sentence_6"
},
{
"operation": "Highlighting",
"time": "34.639",
"value": "Anoeschka von Meck_sentence_7"
},
{
"operation": "Highlighting",
"time": "39.571",
"value": "Anoeschka von Meck_sentence_8"
},
{
"operation": "finish",
"time": "46.83",
"value": "finish"
}
]
}
|
14433
|
According to the IEA, a policy advisor focusing on recycling, economic development, and environmental protection, energy security and renewable technology could make a direct contribution to heating.
|
{
"evidence": [
"International Energy Agency_sentence_77",
"International Energy Agency_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:\nAccording to the IEA, a policy advisor focusing on recycling, economic development, and environmental protection, energy security and renewable technology could make a direct contribution to heating.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"International Energy Agency_sentence_77",
"International Energy Agency_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4224,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.658",
"value": "?search="
},
{
"operation": "search",
"time": "12.483",
"value": "IEA"
},
{
"operation": "Now on",
"time": "14.373",
"value": "IEA"
},
{
"operation": "hyperlink",
"time": "54.454",
"value": "International Energy Agency"
},
{
"operation": "Now on",
"time": "56.444",
"value": "International Energy Agency"
},
{
"operation": "back-button-clicked",
"time": "61.82",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "62.056",
"value": "IEA"
},
{
"operation": "hyperlink",
"time": "65.711",
"value": "International Energy Agency"
},
{
"operation": "Now on",
"time": "66.664",
"value": "International Energy Agency"
},
{
"operation": "Page search",
"time": "93.05",
"value": "advisor"
},
{
"operation": "Highlighting",
"time": "115.615",
"value": "International Energy Agency_sentence_77"
},
{
"operation": "Page search",
"time": "180.91",
"value": "recycle"
},
{
"operation": "Page search",
"time": "195.991",
"value": "recycl"
},
{
"operation": "Page search",
"time": "212.62",
"value": "focus"
},
{
"operation": "Highlighting",
"time": "225.982",
"value": "International Energy Agency_sentence_3"
},
{
"operation": "Page search",
"time": "253.012",
"value": "heat"
},
{
"operation": "finish",
"time": "314.057",
"value": "finish"
}
]
}
|
88530
|
Humphrey Henchman was appointed canon of Salisbury Cathedral in 1610 and was later ejected from his position, he alsoh elped the future Charles II to escape the country.
|
{
"evidence": [
"Humphrey Henchman_sentence_5"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nHumphrey Henchman was appointed canon of Salisbury Cathedral in 1610 and was later ejected from his position, he alsoh elped the future Charles II to escape the country.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Humphrey Henchman_sentence_5"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4225,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.031",
"value": "?search="
},
{
"operation": "search",
"time": "3.769",
"value": "Humphrey Henchman"
},
{
"operation": "Now on",
"time": "4.447",
"value": "Humphrey Henchman"
},
{
"operation": "Highlighting",
"time": "97.627",
"value": "Humphrey Henchman_sentence_5"
},
{
"operation": "finish",
"time": "106.22",
"value": "finish"
}
]
}
|
exfever_4329
|
iZombie is an American supernatural procedural crime drama television series that is a loose adaptation of the comic book series of the same name, co-created by an author who was best known for his alternate history novels and short stories.
|
{
"evidence": [
"IZombie (TV series)",
"Chris Roberson (author)"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\niZombie is an American supernatural procedural crime drama television series that is a loose adaptation of the comic book series of the same name, co-created by an author who was best known for his alternate history novels and short stories.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"IZombie (TV series)",
"Chris Roberson (author)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4226,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6297
|
Brittany Anne Murphy-Monjack was an Australian actress and singer who had supporting roles in independent films such as a 1998 American black comedy film, starring an American actor known for his roles in films such as Idiocracy.
|
{
"evidence": [
"Brittany Murphy",
"Bongwater (film)",
"Luke Wilson"
],
"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:\nBrittany Anne Murphy-Monjack was an Australian actress and singer who had supporting roles in independent films such as a 1998 American black comedy film, starring an American actor known for his roles in films such as Idiocracy.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Brittany Murphy",
"Bongwater (film)",
"Luke Wilson"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4227,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
71460
|
Fuji TV changed their corporate logo from the old “Channel 8” logo to the “Medama” logo after which they bought Nintendo in order to create two games for the Famicom.
|
{
"evidence": [
"Fuji TV_sentence_17"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nFuji TV changed their corporate logo from the old “Channel 8” logo to the “Medama” logo after which they bought Nintendo in order to create two games for the Famicom.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Fuji TV_sentence_17"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4228,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.733",
"value": "?search="
},
{
"operation": "search",
"time": "10.418",
"value": "Fuji TV"
},
{
"operation": "Now on",
"time": "12.906",
"value": "Fuji TV"
},
{
"operation": "Highlighting",
"time": "818.681",
"value": "Fuji TV_sentence_16"
},
{
"operation": "Highlighting",
"time": "843.496",
"value": "Fuji TV_sentence_17"
},
{
"operation": "finish",
"time": "863.223",
"value": "finish"
}
]
}
|
50255
|
The study of Matheny et al and in 2006 included Volvariella gloiocephala that was placed as the sister group of Pluteus (a large genus of plants with over 300 species).
|
{
"evidence": [
"Pluteus_sentence_0"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe study of Matheny et al and in 2006 included Volvariella gloiocephala that was placed as the sister group of Pluteus (a large genus of plants with over 300 species).\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Pluteus_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4229,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.804",
"value": "?search="
},
{
"operation": "search",
"time": "18.594",
"value": "Contains...Matheny et al"
},
{
"operation": "Now on",
"time": "19.32",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "43.497",
"value": "Clavariaceae"
},
{
"operation": "Now on",
"time": "44.364",
"value": "Clavariaceae"
},
{
"operation": "search",
"time": "94.117",
"value": "Contains...in 2006 included Volvariella gloiocephala"
},
{
"operation": "Now on",
"time": "94.889",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "99.596",
"value": "Volvopluteus"
},
{
"operation": "Now on",
"time": "100.422",
"value": "Volvopluteus"
},
{
"operation": "Highlighting",
"time": "103.075",
"value": "Volvopluteus_sentence_22"
},
{
"operation": "Highlighting",
"time": "103.076",
"value": "Volvopluteus_title"
},
{
"operation": "Highlighting",
"time": "103.077",
"value": "Volvopluteus_section_5"
},
{
"operation": "Highlighting",
"time": "105.619",
"value": "Volvopluteus_sentence_23"
},
{
"operation": "Highlighting deleted",
"time": "114.09",
"value": "Volvopluteus_sentence_23"
},
{
"operation": "Highlighting",
"time": "115.147",
"value": "Volvopluteus_sentence_23"
},
{
"operation": "search",
"time": "149.243",
"value": "Pluteus"
},
{
"operation": "Now on",
"time": "150.107",
"value": "Pluteus"
},
{
"operation": "Highlighting",
"time": "155.57",
"value": "Pluteus_sentence_0"
},
{
"operation": "finish",
"time": "168.345",
"value": "finish"
}
]
}
|
61871
|
William Vance served in the Senate neither from 1886 nor to 1892; then in 1892, he assumed his terminal position as the private secretary to two-term Governor Murphy J. Foster, Sr.
|
{
"evidence": [
"William Washington Vance_sentence_10"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nWilliam Vance served in the Senate neither from 1886 nor to 1892; then in 1892, he assumed his terminal position as the private secretary to two-term Governor Murphy J. Foster, Sr.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"William Washington Vance_sentence_10"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4230,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.39",
"value": "?search="
},
{
"operation": "search",
"time": "17.263",
"value": "William Vance"
},
{
"operation": "Now on",
"time": "18.2",
"value": "William Vance"
},
{
"operation": "hyperlink",
"time": "23.788",
"value": "William R. Vance"
},
{
"operation": "Now on",
"time": "24.174",
"value": "William R. Vance"
},
{
"operation": "search",
"time": "54.557",
"value": "William Vance McMaken"
},
{
"operation": "Now on",
"time": "55.27",
"value": "William Vance McMaken"
},
{
"operation": "search",
"time": "66.241",
"value": "William Vance Rinehart"
},
{
"operation": "Now on",
"time": "67.271",
"value": "William V. Rinehart"
},
{
"operation": "search",
"time": "78.133",
"value": "william vance"
},
{
"operation": "Now on",
"time": "78.664",
"value": "William Vance"
},
{
"operation": "search",
"time": "152.749",
"value": "Murphy J. Foster"
},
{
"operation": "Now on",
"time": "153.766",
"value": "Murphy J. Foster"
},
{
"operation": "Page search",
"time": "181.611",
"value": "vance"
},
{
"operation": "Highlighting",
"time": "187.048",
"value": "Murphy J. Foster_sentence_25"
},
{
"operation": "Highlighting",
"time": "187.049",
"value": "Murphy J. Foster_title"
},
{
"operation": "Highlighting",
"time": "187.049",
"value": "Murphy J. Foster_section_2"
},
{
"operation": "hyperlink",
"time": "193.804",
"value": "William Washington Vance"
},
{
"operation": "Now on",
"time": "194.517",
"value": "William Washington Vance"
},
{
"operation": "Highlighting",
"time": "205.452",
"value": "William Washington Vance_sentence_10"
},
{
"operation": "Now on",
"time": "229.499",
"value": "William Washington Vance"
},
{
"operation": "finish",
"time": "236.918",
"value": "finish"
}
]
}
|
exfever_5680
|
The Connaught Tunnel is in a southeastern Canadian province that borders one of the three prairie provinces.
|
{
"evidence": [
"Connaught Tunnel",
"British Columbia",
"Alberta"
],
"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 Connaught Tunnel is in a southeastern Canadian province that borders one of the three prairie provinces.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Connaught Tunnel",
"British Columbia",
"Alberta"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4231,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
24363
|
Weishi County is under administration of Kaifeng City in the central part of Henan province, China.
|
{
"evidence": [
"Weishi County_sentence_1",
"Weishi County_sentence_0"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nWeishi County is under administration of Kaifeng City in the central part of Henan province, China.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Weishi County_sentence_1",
"Weishi County_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4232,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.455",
"value": "?search="
},
{
"operation": "search",
"time": "8.002",
"value": "Weishi County"
},
{
"operation": "Now on",
"time": "8.936",
"value": "Weishi County"
},
{
"operation": "Highlighting",
"time": "60.989",
"value": "Weishi County_sentence_1"
},
{
"operation": "Highlighting",
"time": "63.611",
"value": "Weishi County_sentence_0"
},
{
"operation": "Now on",
"time": "89.273",
"value": "Weishi County"
},
{
"operation": "Now on",
"time": "93.359",
"value": "Weishi County"
},
{
"operation": "finish",
"time": "118.47",
"value": "finish"
}
]
}
|
65030
|
New Indies Style is a baroque architectural style that employs the use of 'double facade' which protects the facade from heavy rainfall and strong sunlight.
|
{
"evidence": [
"New Indies Style_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:\nNew Indies Style is a baroque architectural style that employs the use of 'double facade' which protects the facade from heavy rainfall and strong sunlight.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"New Indies Style_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4233,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "3.796",
"value": "?search="
},
{
"operation": "search",
"time": "26.518",
"value": "New Indies Style"
},
{
"operation": "Now on",
"time": "28.206",
"value": "New Indies Style"
},
{
"operation": "Highlighting",
"time": "36.815",
"value": "New Indies Style_sentence_0"
},
{
"operation": "finish",
"time": "65.477",
"value": "finish"
}
]
}
|
exfever_3538
|
Funny or Die, a comedy video website and film/television production company, continues to make TV shows, including an American comedy game show hosted by comedian and actor Will Smith.
|
{
"evidence": [
"Funny or Die",
"Billy on the Street"
],
"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:\nFunny or Die, a comedy video website and film/television production company, continues to make TV shows, including an American comedy game show hosted by comedian and actor Will Smith.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Funny or Die",
"Billy on the Street"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4234,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7662
|
Roman Reigns is an American professional wrestler and a former professional football player in a family of football team sports primarily played in the United States and Canada.
|
{
"evidence": [
"Roman Reigns",
"Gridiron football"
],
"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:\nRoman Reigns is an American professional wrestler and a former professional football player in a family of football team sports primarily played in the United States and Canada.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Roman Reigns",
"Gridiron football"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4235,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
88793
|
Luis de Grandes Pascual worked for various European political groups and was elected in 1977 as a UCD deputy for Guadalajara.
|
{
"evidence": [
"Luis de Grandes Pascual_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:\nLuis de Grandes Pascual worked for various European political groups and was elected in 1977 as a UCD deputy for Guadalajara.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Luis de Grandes Pascual_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4236,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.008",
"value": "?search="
},
{
"operation": "search",
"time": "10.137",
"value": "Luis de Grandes Pascual"
},
{
"operation": "Now on",
"time": "10.812",
"value": "Luis de Grandes Pascual"
},
{
"operation": "Highlighting",
"time": "58.002",
"value": "Luis de Grandes Pascual_sentence_2"
},
{
"operation": "finish",
"time": "99.321",
"value": "finish"
}
]
}
|
exfever_2546
|
Tamera Darvette Mowry is an American actress who starred in the 2005 Disney Channel original movie that cast a Canadian actress who first gained fame for her teen role as Tamera Campbell on the ABC/WB sitcom Sister.
|
{
"evidence": [
"Tamera Mowry",
"Twitches (film)",
"Tamera Mowry"
],
"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:\nTamera Darvette Mowry is an American actress who starred in the 2005 Disney Channel original movie that cast a Canadian actress who first gained fame for her teen role as Tamera Campbell on the ABC/WB sitcom Sister.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Tamera Mowry",
"Twitches (film)",
"Tamera Mowry"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4237,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2813
|
Chris McKenna is a French television writer who has written for an American television sitcom starring an American actress and director.
|
{
"evidence": [
"Chris McKenna (writer)",
"Community (TV series)",
"Gillian Jacobs"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nChris McKenna is a French television writer who has written for an American television sitcom starring an American actress and director.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Chris McKenna (writer)",
"Community (TV series)",
"Gillian Jacobs"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4238,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7459
|
George Cukor was assigned by David O. Selznick, the RKO studio's Head of Production, to direct several of RKO's major films, including a 1934 American Pre-Code satirical comedy film.
|
{
"evidence": [
"George Cukor",
"Our Betters"
],
"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 Cukor was assigned by David O. Selznick, the RKO studio's Head of Production, to direct several of RKO's major films, including a 1934 American Pre-Code satirical comedy film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"George Cukor",
"Our Betters"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4239,
"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": 4240,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8484
|
The Handmaid's Tale is a futuristic dystopian novel by Canadian author Margaret Atwood, set in a near-future of a region comprising six states in the Northeastern United States including Connecticut, Maine, and Massachusetts.
|
{
"evidence": [
"The Handmaid's Tale",
"New England"
],
"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 Handmaid's Tale is a futuristic dystopian novel by Canadian author Margaret Atwood, set in a near-future of a region comprising six states in the Northeastern United States including Connecticut, Maine, and Massachusetts.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Handmaid's Tale",
"New England"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4241,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2739
|
Pineapple Express is a 2008 American stoner comedy film produced by an American comedian, director, producer, and screenwriter known as the founder of Apatow Productions.
|
{
"evidence": [
"Pineapple Express (film)",
"Judd Apatow"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nPineapple Express is a 2008 American stoner comedy film produced by an American comedian, director, producer, and screenwriter known as the founder of Apatow Productions.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Pineapple Express (film)",
"Judd Apatow"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4242,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
13325
|
In July 2020, further plan details for the Headbolt Lane, a proposed new railway station in the Northwood area of Kirkby, Merseyside, England, were announced by the Liver City Region Combined Authority.
|
{
"evidence": [
"Headbolt Lane railway station_sentence_0",
"Headbolt Lane railway station_sentence_3"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nIn July 2020, further plan details for the Headbolt Lane, a proposed new railway station in the Northwood area of Kirkby, Merseyside, England, were announced by the Liver City Region Combined Authority.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Headbolt Lane railway station_sentence_0",
"Headbolt Lane railway station_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4243,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.181",
"value": "?search="
},
{
"operation": "search",
"time": "21.086",
"value": "Headbolt Lane railway station"
},
{
"operation": "Now on",
"time": "22.266",
"value": "Headbolt Lane railway station"
},
{
"operation": "Highlighting",
"time": "25.683",
"value": "Headbolt Lane railway station_sentence_0"
},
{
"operation": "Highlighting",
"time": "35.392",
"value": "Headbolt Lane railway station_sentence_3"
},
{
"operation": "finish",
"time": "87.979",
"value": "finish"
}
]
}
|
82878
|
Holmleigh Park High School was opened in 1971 as Beaufort School, it was later renamed Beaufort Community School but was never an academy.
|
{
"evidence": [
"Holmleigh Park High School_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:\nHolmleigh Park High School was opened in 1971 as Beaufort School, it was later renamed Beaufort Community School but was never an academy.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Holmleigh Park High School_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4244,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.853",
"value": "?search="
},
{
"operation": "search",
"time": "643.489",
"value": "Contains...Holmleigh Park High School"
},
{
"operation": "Now on",
"time": "644.613",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "648.652",
"value": "Holmleigh Park High School"
},
{
"operation": "Now on",
"time": "649.123",
"value": "Holmleigh Park High School"
},
{
"operation": "Highlighting",
"time": "662.964",
"value": "Holmleigh Park High School_sentence_3"
},
{
"operation": "Highlighting",
"time": "662.967",
"value": "Holmleigh Park High School_section_0"
},
{
"operation": "Highlighting",
"time": "667.504",
"value": "Holmleigh Park High School_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "678.946",
"value": "Holmleigh Park High School_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "679.361",
"value": "Holmleigh Park High School_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "679.364",
"value": "Holmleigh Park High School_section_0"
},
{
"operation": "Highlighting",
"time": "681.223",
"value": "Holmleigh Park High School_sentence_0"
},
{
"operation": "finish",
"time": "693.892",
"value": "finish"
}
]
}
|
71226
|
Shikva, a love-inspired ballad released in Pakistan as a digital download in 2011, was written by Prashant Vasal and nominated for Best Music Single at the 3rd Annual Hum Awards.
|
{
"evidence": [
"Shikva_sentence_3",
"Shikva_sentence_2",
"Shikva_sentence_4",
"Shikva_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:\nShikva, a love-inspired ballad released in Pakistan as a digital download in 2011, was written by Prashant Vasal and nominated for Best Music Single at the 3rd Annual Hum Awards.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Shikva_sentence_3",
"Shikva_sentence_2",
"Shikva_sentence_4",
"Shikva_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4245,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.769",
"value": "?search="
},
{
"operation": "search",
"time": "16.746",
"value": "Shikva"
},
{
"operation": "Now on",
"time": "17.659",
"value": "Shikva"
},
{
"operation": "Highlighting",
"time": "28.584",
"value": "Shikva_sentence_3"
},
{
"operation": "Highlighting",
"time": "36.121",
"value": "Shikva_sentence_2"
},
{
"operation": "Highlighting",
"time": "49.341",
"value": "Shikva_sentence_4"
},
{
"operation": "Highlighting",
"time": "81.725",
"value": "Shikva_sentence_6"
},
{
"operation": "finish",
"time": "102.056",
"value": "finish"
}
]
}
|
19342
|
The Bernal Heights branch of the San Francisco Public Library system, which has 27 branches in total, has always been in a single location.
|
{
"evidence": [
"San Francisco Public Library_sentence_40",
"San Francisco Public Library_sentence_41",
"San Francisco Public Library_sentence_43"
],
"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 Bernal Heights branch of the San Francisco Public Library system, which has 27 branches in total, has always been in a single location.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"San Francisco Public Library_sentence_40",
"San Francisco Public Library_sentence_41",
"San Francisco Public Library_sentence_43"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4246,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.606",
"value": "?search="
},
{
"operation": "search",
"time": "14.869",
"value": "san francisco public library"
},
{
"operation": "Now on",
"time": "15.66",
"value": "San Francisco Public Library"
},
{
"operation": "Highlighting",
"time": "18.283",
"value": "San Francisco Public Library_cell_0_4_1"
},
{
"operation": "Highlighting",
"time": "18.292",
"value": "San Francisco Public Library_header_cell_0_4_0"
},
{
"operation": "hyperlink",
"time": "29.85",
"value": "2.3 Bernal Heights San Francisco Public Library_section_6"
},
{
"operation": "Highlighting",
"time": "134.263",
"value": "San Francisco Public Library_sentence_40"
},
{
"operation": "Highlighting",
"time": "135.651",
"value": "San Francisco Public Library_sentence_41"
},
{
"operation": "Highlighting",
"time": "158.29",
"value": "San Francisco Public Library_sentence_43"
},
{
"operation": "finish",
"time": "161.965",
"value": "finish"
}
]
}
|
exfever_7262
|
The Twilight Saga is a series of three fantasy romance novels written by Stephanie Meyer, with the theme that literature covers the spectrum of literary works concerned with bloodsuckers.
|
{
"evidence": [
"Twilight (novel series)",
"Vampire literature"
],
"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 Twilight Saga is a series of three fantasy romance novels written by Stephanie Meyer, with the theme that literature covers the spectrum of literary works concerned with bloodsuckers.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Twilight (novel series)",
"Vampire literature"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4247,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7397
|
Logan is a 2017 American superhero film, which is the final installment in the Wolverine trilogy following a 2009 American superhero film that was written by an American screenwriter who has primarily worked in the action genre as the writer of the film Swordfish.
|
{
"evidence": [
"Logan (film)",
"X-Men Origins: Wolverine",
"Skip Woods"
],
"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:\nLogan is a 2017 American superhero film, which is the final installment in the Wolverine trilogy following a 2009 American superhero film that was written by an American screenwriter who has primarily worked in the action genre as the writer of the film Swordfish.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Logan (film)",
"X-Men Origins: Wolverine",
"Skip Woods"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4248,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
27963
|
Landon Cassill won four International Kart Federation (IKF) championships, he competed in three different classes but has never won a state championship.
|
{
"evidence": [
"Landon Cassill_sentence_9"
],
"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:\nLandon Cassill won four International Kart Federation (IKF) championships, he competed in three different classes but has never won a state championship.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Landon Cassill_sentence_9"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4249,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.426",
"value": "?search="
},
{
"operation": "search",
"time": "18.802",
"value": "Landon Cassill"
},
{
"operation": "Now on",
"time": "21.244",
"value": "Landon Cassill"
},
{
"operation": "Highlighting",
"time": "71.889",
"value": "Landon Cassill_sentence_7"
},
{
"operation": "Highlighting",
"time": "77.515",
"value": "Landon Cassill_sentence_8"
},
{
"operation": "Highlighting",
"time": "80.144",
"value": "Landon Cassill_sentence_9"
},
{
"operation": "Highlighting deleted",
"time": "80.824",
"value": "Landon Cassill_sentence_8"
},
{
"operation": "Highlighting deleted",
"time": "81.41",
"value": "Landon Cassill_sentence_7"
},
{
"operation": "finish",
"time": "93.028",
"value": "finish"
}
]
}
|
47163
|
Sumithra Warnakulasuriya (born 25 March 1962) is a former Sri Lankan cricketer, attended Royal College but was not a prefect in school.
|
{
"evidence": [
"Sumithra Warnakulasuriya_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:\nSumithra Warnakulasuriya (born 25 March 1962) is a former Sri Lankan cricketer, attended Royal College but was not a prefect in school.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Sumithra Warnakulasuriya_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4250,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.73",
"value": "?search="
},
{
"operation": "search",
"time": "19.344",
"value": "Sumithra Warnakulasuriya"
},
{
"operation": "Now on",
"time": "20.004",
"value": "Sumithra Warnakulasuriya"
},
{
"operation": "Highlighting",
"time": "24.265",
"value": "Sumithra Warnakulasuriya_sentence_0"
},
{
"operation": "Highlighting",
"time": "30.676",
"value": "Sumithra Warnakulasuriya_sentence_1"
},
{
"operation": "Highlighting",
"time": "33.727",
"value": "Sumithra Warnakulasuriya_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "34.812",
"value": "Sumithra Warnakulasuriya_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "36.232",
"value": "Sumithra Warnakulasuriya_sentence_1"
},
{
"operation": "finish",
"time": "45.041",
"value": "finish"
}
]
}
|
81220
|
Chill point is original market of the Stop & Shop supermarket chain was on the corner of Northern Artery and McGrath Highway but in 2008, it would be dismantled and sold to Daewoo Shipbuilding & Marine Engineering of South Korea and relocated to Mangalia, Romania.
|
{
"evidence": [
"DSME_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:\nChill point is original market of the Stop & Shop supermarket chain was on the corner of Northern Artery and McGrath Highway but in 2008, it would be dismantled and sold to Daewoo Shipbuilding & Marine Engineering of South Korea and relocated to Mangalia, Romania.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"DSME_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4251,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.721",
"value": "?search="
},
{
"operation": "search",
"time": "32.981",
"value": "Chill point"
},
{
"operation": "Now on",
"time": "34.304",
"value": "undefined"
},
{
"operation": "search",
"time": "67.288",
"value": "Stop & Shop"
},
{
"operation": "Now on",
"time": "68.441",
"value": "Stop & Shop"
},
{
"operation": "search",
"time": "406.548",
"value": "Daewoo Shipbuilding & Marine Engineering"
},
{
"operation": "Now on",
"time": "407.541",
"value": "DSME"
},
{
"operation": "search",
"time": "500.645",
"value": "Contains...Chill point"
},
{
"operation": "Now on",
"time": "501.526",
"value": "undefined"
},
{
"operation": "search",
"time": "1742.601",
"value": "Chill point stop & shop"
},
{
"operation": "Now on",
"time": "1744.534",
"value": "undefined"
},
{
"operation": "search",
"time": "1769.106",
"value": "Northern Artery and McGrath Highway"
},
{
"operation": "Now on",
"time": "1769.823",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "1794.583",
"value": "Massachusetts Route 38"
},
{
"operation": "Now on",
"time": "1795.223",
"value": "Massachusetts Route 38"
},
{
"operation": "back-button-clicked",
"time": "1815.683",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "1816.182",
"value": "undefined"
},
{
"operation": "search",
"time": "1856.498",
"value": "Daewoo Shipbuilding and Marine Engineering"
},
{
"operation": "Now on",
"time": "1857.07",
"value": "DSME"
},
{
"operation": "hyperlink",
"time": "1880.213",
"value": "Daewoo dissolution and corruption scandal"
},
{
"operation": "Now on",
"time": "1880.656",
"value": "Daewoo dissolution and corruption scandal"
},
{
"operation": "hyperlink",
"time": "1888.494",
"value": "Daewoo Shipbuilding & Marine Engineering"
},
{
"operation": "Now on",
"time": "1888.809",
"value": "Daewoo Shipbuilding & Marine Engineering"
},
{
"operation": "Highlighting",
"time": "1926.318",
"value": "DSME_sentence_0"
},
{
"operation": "finish",
"time": "1938.142",
"value": "finish"
}
]
}
|
exfever_3392
|
The Outcasts is a 2017 American teen film combined with a genre that is designed to make the audience shocked through amusement in a stage that uses live performers, usually actors or actresses, to present the experience of a real or imagined event.
|
{
"evidence": [
"The Outcasts (2017 film)",
"Comedy film",
"Theatre"
],
"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 Outcasts is a 2017 American teen film combined with a genre that is designed to make the audience shocked through amusement in a stage that uses live performers, usually actors or actresses, to present the experience of a real or imagined event.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Outcasts (2017 film)",
"Comedy film",
"Theatre"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4252,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2895
|
Nicholas King Nolte is an American actor whose other film appearances include a 1984 American satirical black comedy-drama series written by W. R. McKinney.
|
{
"evidence": [
"Nick Nolte",
"Teachers (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:\nNicholas King Nolte is an American actor whose other film appearances include a 1984 American satirical black comedy-drama series written by W. R. McKinney.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Nick Nolte",
"Teachers (film)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4253,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
81301
|
Diesel Air Dair 100 is an opposed-piston diesel aircraft engine whose design eliminates the need for a cylinder head and camshafts, but may use either diesel fuel (DERV) or Jet-A1 kerosene (AVTUR).
|
{
"evidence": [
"Diesel Air Dair 100_sentence_0",
"Diesel Air Dair 100_sentence_8",
"Diesel Air Dair 100_sentence_11"
],
"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:\nDiesel Air Dair 100 is an opposed-piston diesel aircraft engine whose design eliminates the need for a cylinder head and camshafts, but may use either diesel fuel (DERV) or Jet-A1 kerosene (AVTUR).\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Diesel Air Dair 100_sentence_0",
"Diesel Air Dair 100_sentence_8",
"Diesel Air Dair 100_sentence_11"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4254,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.867",
"value": "?search="
},
{
"operation": "search",
"time": "19.844",
"value": "Diesel Air Dair 100"
},
{
"operation": "Now on",
"time": "21.065",
"value": "Diesel Air Dair 100"
},
{
"operation": "Highlighting",
"time": "32.512",
"value": "Diesel Air Dair 100_sentence_0"
},
{
"operation": "Highlighting",
"time": "47.719",
"value": "Diesel Air Dair 100_sentence_8"
},
{
"operation": "Highlighting",
"time": "53.857",
"value": "Diesel Air Dair 100_sentence_11"
},
{
"operation": "finish",
"time": "70.377",
"value": "finish"
}
]
}
|
75083
|
The Wilmington and Conway Railroad construction was never completed due to lack of funds.
|
{
"evidence": [
"Wilmington and Conway Railroad_sentence_1",
"Wilmington and Conway Railroad_sentence_0"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Wilmington and Conway Railroad construction was never completed due to lack of funds.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Wilmington and Conway Railroad_sentence_1",
"Wilmington and Conway Railroad_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4255,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "3.321",
"value": "undefined"
},
{
"operation": "search",
"time": "36.367",
"value": "The Wilmington and Conway Railroad"
},
{
"operation": "Now on",
"time": "40.392",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "42.87",
"value": "Wilmington and Conway Railroad"
},
{
"operation": "Now on",
"time": "43.834",
"value": "Wilmington and Conway Railroad"
},
{
"operation": "Highlighting",
"time": "62.799",
"value": "Wilmington and Conway Railroad_sentence_1"
},
{
"operation": "Highlighting",
"time": "70.182",
"value": "Wilmington and Conway Railroad_sentence_0"
},
{
"operation": "finish",
"time": "90.109",
"value": "finish"
}
]
}
|
36983
|
Sheena Easton's discography has a total of more than 20 studio albums and 50 live albums, a collection of audio recordings issued as a collection on compact disc (CD), vinyl, audiotape, or another medium.
|
{
"evidence": [
"Sheena Easton discography_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:\nSheena Easton's discography has a total of more than 20 studio albums and 50 live albums, a collection of audio recordings issued as a collection on compact disc (CD), vinyl, audiotape, or another medium.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Sheena Easton discography_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4256,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.859",
"value": "?search="
},
{
"operation": "search",
"time": "11.024",
"value": "Sheena Easton discography"
},
{
"operation": "Now on",
"time": "11.997",
"value": "Sheena Easton discography"
},
{
"operation": "Page search",
"time": "46.688",
"value": "album"
},
{
"operation": "Highlighting",
"time": "58.684",
"value": "Sheena Easton discography_sentence_0"
},
{
"operation": "finish",
"time": "185.616",
"value": "finish"
}
]
}
|
94372
|
In April 1521, Ferdinand Magellan accompanied Duarte de Menezes from Lisbon to India as the next governor of Portuguese India, a colonial state of the Portuguese Empire founded six years after discovering a sea route to the Indian Subcontinent by the Kingdom of Portugal.
|
{
"evidence": [
"Duarte de Menezes_sentence_8",
"Duarte de Menezes_sentence_7",
"Duarte de Menezes_sentence_6",
"Portuguese India_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:\nIn April 1521, Ferdinand Magellan accompanied Duarte de Menezes from Lisbon to India as the next governor of Portuguese India, a colonial state of the Portuguese Empire founded six years after discovering a sea route to the Indian Subcontinent by the Kingdom of Portugal.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Duarte de Menezes_sentence_8",
"Duarte de Menezes_sentence_7",
"Duarte de Menezes_sentence_6",
"Portuguese India_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4257,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.492",
"value": "undefined"
},
{
"operation": "search",
"time": "13.195",
"value": "Ferdinand Magellan accompanied Duarte de Menezes from Lisbon to India as the next governor of Portuguese India, a colonial state of the Portuguese Empire founded six years after discovering a sea route to the Indian Subcontinent by the Kingdom of Portugal."
},
{
"operation": "Now on",
"time": "16.802",
"value": "undefined"
},
{
"operation": "search",
"time": "64.542",
"value": "Ferdinand Magellan accompanied Duarte de Menezes from Lisbon to India"
},
{
"operation": "Now on",
"time": "65.346",
"value": "undefined"
},
{
"operation": "search",
"time": "88.017",
"value": "Duarte de Menezes"
},
{
"operation": "Now on",
"time": "88.868",
"value": "Duarte de Menezes"
},
{
"operation": "Page search",
"time": "98.076",
"value": "ferdinand"
},
{
"operation": "Page search",
"time": "137.877",
"value": "governor"
},
{
"operation": "Page search",
"time": "161.288",
"value": "1521"
},
{
"operation": "Highlighting",
"time": "177.349",
"value": "Duarte de Menezes_sentence_7"
},
{
"operation": "Highlighting",
"time": "178.617",
"value": "Duarte de Menezes_sentence_8"
},
{
"operation": "Highlighting deleted",
"time": "181.321",
"value": "Duarte de Menezes_sentence_7"
},
{
"operation": "Highlighting",
"time": "185.173",
"value": "Duarte de Menezes_sentence_7"
},
{
"operation": "Page search",
"time": "203.221",
"value": "governor"
},
{
"operation": "Highlighting",
"time": "212.281",
"value": "Duarte de Menezes_sentence_6"
},
{
"operation": "hyperlink",
"time": "214.265",
"value": "Portuguese India"
},
{
"operation": "Now on",
"time": "214.998",
"value": "Portuguese India"
},
{
"operation": "Page search",
"time": "228.274",
"value": "colonial"
},
{
"operation": "Highlighting",
"time": "230.538",
"value": "Portuguese India_sentence_0"
},
{
"operation": "back-button-clicked",
"time": "238.281",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "238.37",
"value": "Duarte de Menezes"
},
{
"operation": "finish",
"time": "264.228",
"value": "finish"
}
]
}
|
exfever_4133
|
Eric Trump is the second son of an American politician, a media personality, and a businessman.
|
{
"evidence": [
"Eric Trump",
"Donald Trump"
],
"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:\nEric Trump is the second son of an American politician, a media personality, and a businessman.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Eric Trump",
"Donald Trump"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4258,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
62819
|
BLRT Grupp is a shipbuilding company headquartered in Tallin, the capital, primate and the most populous city of Estonia that is located on the shore of the Gulf of Finland of the Baltic Sea.
|
{
"evidence": [
"BLRT Grupp_sentence_0",
"Tallinn_sentence_2",
"Tallinn_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:\nBLRT Grupp is a shipbuilding company headquartered in Tallin, the capital, primate and the most populous city of Estonia that is located on the shore of the Gulf of Finland of the Baltic Sea.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"BLRT Grupp_sentence_0",
"Tallinn_sentence_2",
"Tallinn_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4259,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.064",
"value": "?search="
},
{
"operation": "search",
"time": "13.922",
"value": "BLRT Grupp"
},
{
"operation": "Now on",
"time": "14.824",
"value": "BLRT Grupp"
},
{
"operation": "Highlighting",
"time": "17.838",
"value": "BLRT Grupp_sentence_0"
},
{
"operation": "hyperlink",
"time": "25.991",
"value": "Tallinn"
},
{
"operation": "Now on",
"time": "27.679",
"value": "Tallinn"
},
{
"operation": "Highlighting",
"time": "32.208",
"value": "Tallinn_sentence_2"
},
{
"operation": "Highlighting",
"time": "51.867",
"value": "Tallinn_sentence_3"
},
{
"operation": "finish",
"time": "60.376",
"value": "finish"
}
]
}
|
46265
|
Semra Bheropura is a village that offers a lot of jobs.
|
{
"evidence": [
"Semra Bheropura_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:\nSemra Bheropura is a village that offers a lot of jobs.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Semra Bheropura_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4260,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.02",
"value": "?search="
},
{
"operation": "search",
"time": "8.608",
"value": "Semra Bheropura"
},
{
"operation": "Now on",
"time": "9.523",
"value": "Semra Bheropura"
},
{
"operation": "Highlighting",
"time": "27.096",
"value": "Semra Bheropura_sentence_0"
},
{
"operation": "finish",
"time": "48.281",
"value": "finish"
}
]
}
|
exfever_5768
|
Amsterdam is known for its beautiful canals, quirky architecture, and lively nightlife.
|
{
"evidence": [
"Audrey Hepburn",
"Sonia Gaskell"
],
"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:\nAmsterdam is known for its beautiful canals, quirky architecture, and lively nightlife.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Audrey Hepburn",
"Sonia Gaskell"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4261,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6197
|
Amanda Leigh Moore is an Australian singer, songwriter, and actress whose self-titled second studio album was released on June 19, 2001, by an American record label owned by Sony Music Entertainment.
|
{
"evidence": [
"Mandy Moore",
"Mandy Moore (album)",
"Epic Records"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAmanda Leigh Moore is an Australian singer, songwriter, and actress whose self-titled second studio album was released on June 19, 2001, by an American record label owned by Sony Music Entertainment.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Mandy Moore",
"Mandy Moore (album)",
"Epic Records"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4262,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7678
|
Every cell consists of a cytoplasm enclosed within a membrane, which contains many biomolecules such as biopolymers or macromolecules, composed of organic molecules.
|
{
"evidence": [
"Cell (biology)",
"Nucleic acid",
"Nucleotide"
],
"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:\nEvery cell consists of a cytoplasm enclosed within a membrane, which contains many biomolecules such as biopolymers or macromolecules, composed of organic molecules.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Cell (biology)",
"Nucleic acid",
"Nucleotide"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4263,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2997
|
Oz the Great and Powerful is a 2013 American fantasy adventure film directed by an American filmmaker best known for directing the Spider-Man trilogy.
|
{
"evidence": [
"Oz the Great and Powerful",
"Sam Raimi"
],
"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:\nOz the Great and Powerful is a 2013 American fantasy adventure film directed by an American filmmaker best known for directing the Spider-Man trilogy.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Oz the Great and Powerful",
"Sam Raimi"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4264,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
68419
|
Italy Records is an independent record label founded in Detroit, Kansas in 1997, by Dave Buick.
|
{
"evidence": [
"Italy Records_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:\nItaly Records is an independent record label founded in Detroit, Kansas in 1997, by Dave Buick.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Italy Records_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4265,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.443",
"value": "?search="
},
{
"operation": "search",
"time": "8.444",
"value": "Italy Records"
},
{
"operation": "Now on",
"time": "11.035",
"value": "Italy Records"
},
{
"operation": "Highlighting",
"time": "14.79",
"value": "Italy Records_sentence_0"
},
{
"operation": "finish",
"time": "21.298",
"value": "finish"
}
]
}
|
4418
|
Dustpur is a town located in the state of New York City in the United States.
|
{
"evidence": [
"Dostpur_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:\nDustpur is a town located in the state of New York City in the United States.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Dostpur_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4266,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "38.232",
"value": "Dustpur"
},
{
"operation": "hyperlink",
"time": "44.509",
"value": "Düstur"
},
{
"operation": "back-button-clicked",
"time": "76.992",
"value": "back-button-clicked"
},
{
"operation": "search",
"time": "103.001",
"value": "Dostpur"
},
{
"operation": "Highlighting",
"time": "106.935",
"value": "Dostpur_sentence_0"
},
{
"operation": "finish",
"time": "116.981",
"value": "finish"
}
]
}
|
exfever_3563
|
The Boys from Brazil is a British-American science fiction thriller film starring an English actor and director who was one of a trio of male actors who dominated the American stage of the mid-20th century.
|
{
"evidence": [
"The Boys from Brazil (film)",
"Laurence Olivier"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Boys from Brazil is a British-American science fiction thriller film starring an English actor and director who was one of a trio of male actors who dominated the American stage of the mid-20th century.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Boys from Brazil (film)",
"Laurence Olivier"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4267,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
50780
|
There are many graphic novels and comics featuring body swaps, including Crosswind by Gail Simone, a series that began in 2017, with a Chicago hitman and Seattle housewife switching bodies because of a man with the power to transfer souls.
|
{
"evidence": [
"Gail Simone_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:\nThere are many graphic novels and comics featuring body swaps, including Crosswind by Gail Simone, a series that began in 2017, with a Chicago hitman and Seattle housewife switching bodies because of a man with the power to transfer souls.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Gail Simone_sentence_4"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4268,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.995",
"value": "?search="
},
{
"operation": "search",
"time": "29.811",
"value": "graphics novels featuring body swaps"
},
{
"operation": "Now on",
"time": "31.198",
"value": "undefined"
},
{
"operation": "search",
"time": "43.839",
"value": "crosswind"
},
{
"operation": "Now on",
"time": "44.573",
"value": "Crosswind"
},
{
"operation": "hyperlink",
"time": "50.199",
"value": "Crosswinds (disambiguation)"
},
{
"operation": "Now on",
"time": "50.797",
"value": "Crosswinds (disambiguation)"
},
{
"operation": "search",
"time": "64.519",
"value": "Gail Simone"
},
{
"operation": "Now on",
"time": "65.715",
"value": "Gail Simone"
},
{
"operation": "Page search",
"time": "115.216",
"value": "crosswind"
},
{
"operation": "Highlighting",
"time": "131.611",
"value": "Gail Simone_sentence_4"
},
{
"operation": "hyperlink",
"time": "132.597",
"value": "Image Comics"
},
{
"operation": "Now on",
"time": "134.775",
"value": "Image Comics"
},
{
"operation": "Page search",
"time": "146.369",
"value": "crosswind"
},
{
"operation": "back-button-clicked",
"time": "164.344",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "164.451",
"value": "Gail Simone"
},
{
"operation": "finish",
"time": "194.376",
"value": "finish"
}
]
}
|
86959
|
Thomas William Moseley died in Scranton, Pennsylvania on March 10, 1880 as was referred to as Gen. Mosley.
|
{
"evidence": [
"Thomas William Moseley_sentence_5",
"Thomas William Moseley_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:\nThomas William Moseley died in Scranton, Pennsylvania on March 10, 1880 as was referred to as Gen. Mosley.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Thomas William Moseley_sentence_5",
"Thomas William Moseley_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4269,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.853",
"value": "?search="
},
{
"operation": "search",
"time": "28.211",
"value": "Thomas William Moseley"
},
{
"operation": "Now on",
"time": "28.938",
"value": "Thomas William Moseley"
},
{
"operation": "Highlighting",
"time": "158.09",
"value": "Thomas William Moseley_sentence_5"
},
{
"operation": "Highlighting",
"time": "170.105",
"value": "Thomas William Moseley_sentence_6"
},
{
"operation": "Highlighting",
"time": "287.016",
"value": "Thomas William Moseley_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "287.632",
"value": "Thomas William Moseley_sentence_0"
},
{
"operation": "finish",
"time": "296.752",
"value": "finish"
}
]
}
|
exfever_4435
|
Django Unchained is an American revisionist Northern film directed by Quentin Tarantino, starring an American actor who has played Ajax in The Warriors.
|
{
"evidence": [
"Django Unchained",
"James Remar"
],
"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:\nDjango Unchained is an American revisionist Northern film directed by Quentin Tarantino, starring an American actor who has played Ajax in The Warriors.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Django Unchained",
"James Remar"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4270,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7149
|
Venice is the most beautiful city in northeastern Italy.
|
{
"evidence": [
"Venice",
"Veneto"
],
"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:\nVenice is the most beautiful city in northeastern Italy.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Venice",
"Veneto"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4271,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
58943
|
There were seven more races after the Dutch Grand Prix in the 1971 World Championship of Drivers.
|
{
"evidence": [
"1971 Dutch Grand Prix_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:\nThere were seven more races after the Dutch Grand Prix in the 1971 World Championship of Drivers.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"1971 Dutch Grand Prix_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4272,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.077",
"value": "?search="
},
{
"operation": "search",
"time": "35.133",
"value": "1971 world championship of drivers"
},
{
"operation": "Now on",
"time": "38.158",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "52.631",
"value": "1971 Italian Grand Prix"
},
{
"operation": "Now on",
"time": "53.82",
"value": "1971 Italian Grand Prix"
},
{
"operation": "Page search",
"time": "63.537",
"value": "1971 world championship of drivers"
},
{
"operation": "Highlighting",
"time": "66.792",
"value": "1971 Italian Grand Prix_sentence_1"
},
{
"operation": "Highlighting",
"time": "66.793",
"value": "1971 Italian Grand Prix_title"
},
{
"operation": "search",
"time": "88.239",
"value": "1971 dutch grand prix"
},
{
"operation": "Now on",
"time": "89.785",
"value": "1971 Dutch Grand Prix"
},
{
"operation": "Highlighting",
"time": "93.215",
"value": "1971 Dutch Grand Prix_sentence_1"
},
{
"operation": "finish",
"time": "109.778",
"value": "finish"
}
]
}
|
exfever_7620
|
Stars Dance is an EDM and electropop album, incorporating elements of the genre of electronic dance music that is generally characterized by a variety of rhythms played together to make a piece of music off-beat.
|
{
"evidence": [
"Stars Dance",
"Dubstep",
"Syncopation"
],
"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:\nStars Dance is an EDM and electropop album, incorporating elements of the genre of electronic dance music that is generally characterized by a variety of rhythms played together to make a piece of music off-beat.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Stars Dance",
"Dubstep",
"Syncopation"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4273,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
22128
|
Federico Plummer (born neither on April 10, 1929 nor on April 4, 2004) made his professional debut, a sixth-round knockout of Sam Langford on May 23, 1947; then he won his first six fights before losing to Mike Ross in April 1948.
|
{
"evidence": [
"Federico Plummer_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:\nFederico Plummer (born neither on April 10, 1929 nor on April 4, 2004) made his professional debut, a sixth-round knockout of Sam Langford on May 23, 1947; then he won his first six fights before losing to Mike Ross in April 1948.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Federico Plummer_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4274,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.211",
"value": "?search="
},
{
"operation": "search",
"time": "8.474",
"value": "Federico Plummer"
},
{
"operation": "Now on",
"time": "9.416",
"value": "Federico Plummer"
},
{
"operation": "Highlighting",
"time": "15.724",
"value": "Federico Plummer_sentence_0"
},
{
"operation": "finish",
"time": "27.831",
"value": "finish"
}
]
}
|
386
|
Albert Fishlow served as deputy assistant secretary of state for inter-American affairs; then, in 1999, he received the National Order of the Southern Cross award from Brazil's government.
|
{
"evidence": [
"Albert Fishlow_sentence_4",
"Albert Fishlow_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:\nAlbert Fishlow served as deputy assistant secretary of state for inter-American affairs; then, in 1999, he received the National Order of the Southern Cross award from Brazil's government.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Albert Fishlow_sentence_4",
"Albert Fishlow_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4275,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "65.048",
"value": "Albert Fishlow"
},
{
"operation": "Highlighting",
"time": "164.515",
"value": "Albert Fishlow_sentence_4"
},
{
"operation": "Highlighting",
"time": "170.639",
"value": "Albert Fishlow_sentence_5"
},
{
"operation": "finish",
"time": "179.81",
"value": "finish"
}
]
}
|
exfever_1307
|
Annelies Marie Frank is one of the most discussed Jewish victims of the genocide of European Jews during a global war that lasted from 1939 to 1945.
|
{
"evidence": [
"Anne Frank",
"The Holocaust",
"World War II"
],
"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:\nAnnelies Marie Frank is one of the most discussed Jewish victims of the genocide of European Jews during a global war that lasted from 1939 to 1945.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Anne Frank",
"The Holocaust",
"World War II"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4276,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6589
|
Android was the most commonly known operating system in the world.
|
{
"evidence": [
"Android (operating system)",
"Linux kernel",
"Monolithic kernel"
],
"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:\nAndroid was the most commonly known operating system in the world.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Android (operating system)",
"Linux kernel",
"Monolithic kernel"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4277,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
35448
|
Glutathione oxidase is an enzyme from the family of oxidoreductases that catalyzes the chemical reaction.
|
{
"evidence": [
"Glutathione oxidase_sentence_0",
"Glutathione oxidase_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:\nGlutathione oxidase is an enzyme from the family of oxidoreductases that catalyzes the chemical reaction.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Glutathione oxidase_sentence_0",
"Glutathione oxidase_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4278,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.696",
"value": "?search="
},
{
"operation": "search",
"time": "41.754",
"value": "Glutathione oxidase"
},
{
"operation": "Now on",
"time": "42.562",
"value": "Glutathione oxidase"
},
{
"operation": "Highlighting",
"time": "85.694",
"value": "Glutathione oxidase_sentence_0"
},
{
"operation": "Highlighting",
"time": "92.68",
"value": "Glutathione oxidase_sentence_2"
},
{
"operation": "hyperlink",
"time": "103.324",
"value": "enzyme"
},
{
"operation": "Now on",
"time": "104.116",
"value": "Enzyme"
},
{
"operation": "back-button-clicked",
"time": "105.505",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "105.552",
"value": "Glutathione oxidase"
},
{
"operation": "finish",
"time": "115.091",
"value": "finish"
}
]
}
|
exfever_2959
|
The Planet of the Apes film is set in a historical place that made the film look like it was from 3978 A.D.
|
{
"evidence": [
"Planet of the Apes (1968 film)",
"Kim Hunter"
],
"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 Planet of the Apes film is set in a historical place that made the film look like it was from 3978 A.D.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Planet of the Apes (1968 film)",
"Kim Hunter"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4279,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
18891
|
In The Wonderful Widow of Eighteen Springs (which became one of Cage's most frequently performed works), the vocal line uses four pitches.
|
{
"evidence": [
"The Wonderful Widow of Eighteen Springs_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:\nIn The Wonderful Widow of Eighteen Springs (which became one of Cage's most frequently performed works), the vocal line uses four pitches.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"The Wonderful Widow of Eighteen Springs_sentence_7"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4280,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.845",
"value": "?search="
},
{
"operation": "search",
"time": "15.714",
"value": "The Wonderful Widow of Eighteen Springs"
},
{
"operation": "Now on",
"time": "16.366",
"value": "The Wonderful Widow of Eighteen Springs"
},
{
"operation": "Highlighting",
"time": "95.367",
"value": "The Wonderful Widow of Eighteen Springs_sentence_0"
},
{
"operation": "Highlighting",
"time": "115.438",
"value": "The Wonderful Widow of Eighteen Springs_sentence_7"
},
{
"operation": "Highlighting deleted",
"time": "124.236",
"value": "The Wonderful Widow of Eighteen Springs_sentence_0"
},
{
"operation": "finish",
"time": "127.335",
"value": "finish"
}
]
}
|
exfever_5302
|
Mad Men was the first American TV series produced by Lionsgate Television.
|
{
"evidence": [
"Mad Men",
"Cable television",
"Broadcast programming"
],
"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:\nMad Men was the first American TV series produced by Lionsgate Television.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Mad Men",
"Cable television",
"Broadcast programming"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4281,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
31033
|
Ethnoscape deals with perspectival constructs related to the location of communities and their history, politics, and linguistics, the scientific study of language..
|
{
"evidence": [
"Ethnoscape_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:\nEthnoscape deals with perspectival constructs related to the location of communities and their history, politics, and linguistics, the scientific study of language..\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Ethnoscape_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4282,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.091",
"value": "?search="
},
{
"operation": "search",
"time": "16.01",
"value": "Ethnoscape"
},
{
"operation": "Now on",
"time": "16.937",
"value": "Ethnoscape"
},
{
"operation": "Page search",
"time": "28.52",
"value": "perspectival"
},
{
"operation": "Page search",
"time": "61.687",
"value": "language"
},
{
"operation": "Highlighting",
"time": "77.474",
"value": "Ethnoscape_sentence_1"
},
{
"operation": "finish",
"time": "158.632",
"value": "finish"
}
]
}
|
6351
|
Pedro Pais de Almeida, who was not associated with Abreu Advogados, turned down the position of President of Union Internationale des Avocats (UIA).
|
{
"evidence": [
"Pedro Pais de Almeida_sentence_4",
"Pedro Pais de Almeida_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:\nPedro Pais de Almeida, who was not associated with Abreu Advogados, turned down the position of President of Union Internationale des Avocats (UIA).\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Pedro Pais de Almeida_sentence_4",
"Pedro Pais de Almeida_sentence_6"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4283,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.794",
"value": "?search="
},
{
"operation": "search",
"time": "34.09",
"value": "Pedro Pais de Almeida"
},
{
"operation": "Now on",
"time": "34.878",
"value": "Pedro Pais de Almeida"
},
{
"operation": "Highlighting",
"time": "48.087",
"value": "Pedro Pais de Almeida_sentence_4"
},
{
"operation": "Highlighting",
"time": "56.513",
"value": "Pedro Pais de Almeida_sentence_6"
},
{
"operation": "finish",
"time": "84.623",
"value": "finish"
}
]
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.