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 |
|---|---|---|---|---|---|---|---|---|
exfever_6548
|
Shinsegae is a South Korean retail establishment offering a wide range of consumer goods.
|
{
"evidence": [
"Shinsegae",
"Department store"
],
"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:\nShinsegae is a South Korean retail establishment offering a wide range of consumer goods.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Shinsegae",
"Department store"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6484,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
34584
|
Annie Dillard, who grew up in Pittsburgh, Pennsylvania, attended Hollins College in Virginia, where she not only received bachelor's and master's degree but also met her husband, creative writing professor Richard Henry Wilde Dillard.
|
{
"evidence": [
"Annie Dillard_sentence_18",
"Annie Dillard_sentence_24",
"Annie Dillard_sentence_5",
"R. H. W. Dillard_sentence_12"
],
"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:\nAnnie Dillard, who grew up in Pittsburgh, Pennsylvania, attended Hollins College in Virginia, where she not only received bachelor's and master's degree but also met her husband, creative writing professor Richard Henry Wilde Dillard.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Annie Dillard_sentence_18",
"Annie Dillard_sentence_24",
"Annie Dillard_sentence_5",
"R. H. W. Dillard_sentence_12"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6485,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.893",
"value": "?search="
},
{
"operation": "search",
"time": "6.188",
"value": "Annie Dillard"
},
{
"operation": "Now on",
"time": "7.072",
"value": "Annie Dillard"
},
{
"operation": "Page search",
"time": "14.172",
"value": "grew up"
},
{
"operation": "Page search",
"time": "42.216",
"value": "Hollins"
},
{
"operation": "Highlighting",
"time": "48.436",
"value": "Annie Dillard_sentence_18"
},
{
"operation": "Highlighting",
"time": "90.302",
"value": "Annie Dillard_sentence_24"
},
{
"operation": "hyperlink",
"time": "114.719",
"value": "R. Annie Dillard_sentence_19\n\nH. W. Dillard"
},
{
"operation": "Now on",
"time": "115.223",
"value": "R. H. W. Dillard"
},
{
"operation": "back-button-clicked",
"time": "127.815",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "127.898",
"value": "Annie Dillard"
},
{
"operation": "Highlighting",
"time": "142.155",
"value": "Annie Dillard_sentence_19Annie Dillard_sentence_20"
},
{
"operation": "Highlighting",
"time": "151.065",
"value": "Annie Dillard_sentence_27"
},
{
"operation": "Highlighting deleted",
"time": "170.057",
"value": "Annie Dillard_sentence_27"
},
{
"operation": "Highlighting deleted",
"time": "177.548",
"value": "Annie Dillard_sentence_19Annie Dillard_sentence_20"
},
{
"operation": "hyperlink",
"time": "194.422",
"value": "R. Annie Dillard_sentence_19\n\nH. W. Dillard"
},
{
"operation": "Now on",
"time": "194.751",
"value": "R. H. W. Dillard"
},
{
"operation": "Page search",
"time": "213.118",
"value": "wife"
},
{
"operation": "Page search",
"time": "215.759",
"value": "married"
},
{
"operation": "Page search",
"time": "218.179",
"value": "annue"
},
{
"operation": "Page search",
"time": "219.239",
"value": "annie"
},
{
"operation": "back-button-clicked",
"time": "230.443",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "230.524",
"value": "Annie Dillard"
},
{
"operation": "Highlighting",
"time": "313.329",
"value": "Annie Dillard_sentence_5"
},
{
"operation": "hyperlink",
"time": "342.716",
"value": "R. Annie Dillard_sentence_19\n\nH. W. Dillard"
},
{
"operation": "Now on",
"time": "343.399",
"value": "R. H. W. Dillard"
},
{
"operation": "Highlighting",
"time": "346.959",
"value": "R. H. W. Dillard_sentence_12"
},
{
"operation": "finish",
"time": "371.65",
"value": "finish"
}
]
}
|
88414
|
John Patterson, on a weekend visit to the duke's estate near Exmoor in Devon (a county of England, reaching from the Bristol Channel in the north to the English Channel in the south), meets the duke's granddaughter, Lady Patricia Fairfax, and the two, after a cool beginning based on cultural misunderstandings, fall in love with each other..
|
{
"evidence": [
"I Live in Grosvenor Square_sentence_7",
"Devon_sentence_2",
"I Live in Grosvenor Square_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:\nJohn Patterson, on a weekend visit to the duke's estate near Exmoor in Devon (a county of England, reaching from the Bristol Channel in the north to the English Channel in the south), meets the duke's granddaughter, Lady Patricia Fairfax, and the two, after a cool beginning based on cultural misunderstandings, fall in love with each other..\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"I Live in Grosvenor Square_sentence_7",
"Devon_sentence_2",
"I Live in Grosvenor Square_sentence_8"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6486,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.232",
"value": "?search="
},
{
"operation": "search",
"time": "21.298",
"value": "John Patterson"
},
{
"operation": "Now on",
"time": "22.083",
"value": "John Patterson"
},
{
"operation": "hyperlink",
"time": "40.993",
"value": "John Paterson (disambiguation)"
},
{
"operation": "Now on",
"time": "41.483",
"value": "John Paterson"
},
{
"operation": "search",
"time": "94.341",
"value": "Contains...John Patterson, on a weekend visit to the duke's estate near Exmoo"
},
{
"operation": "Now on",
"time": "95.155",
"value": "undefined"
},
{
"operation": "search",
"time": "128.351",
"value": "I Live in Grosvenor Square"
},
{
"operation": "Now on",
"time": "129.142",
"value": "I Live in Grosvenor Square"
},
{
"operation": "Page search",
"time": "143.87",
"value": "weekend"
},
{
"operation": "Highlighting",
"time": "152.371",
"value": "I Live in Grosvenor Square_sentence_7"
},
{
"operation": "hyperlink",
"time": "157.81",
"value": "Devon"
},
{
"operation": "Now on",
"time": "158.916",
"value": "Devon"
},
{
"operation": "Highlighting",
"time": "163.074",
"value": "Devon_sentence_2"
},
{
"operation": "back-button-clicked",
"time": "168.607",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "168.732",
"value": "I Live in Grosvenor Square"
},
{
"operation": "hyperlink",
"time": "178.034",
"value": "Devon"
},
{
"operation": "Now on",
"time": "178.528",
"value": "Devon"
},
{
"operation": "back-button-clicked",
"time": "182.72",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "182.842",
"value": "I Live in Grosvenor Square"
},
{
"operation": "Highlighting",
"time": "203.297",
"value": "I Live in Grosvenor Square_sentence_8"
},
{
"operation": "finish",
"time": "364.744",
"value": "finish"
}
]
}
|
12235
|
Waqra Willka is a 5,066-metre-high (16,621 ft) mountain in the Andes of Peru, located in the Junín Region, Huancayo Province (a province with an approximate population of 545,615 inhabitants), Chongos Alto District, and is west of Wira Challwa.
|
{
"evidence": [
"Waqra Willka_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:\nWaqra Willka is a 5,066-metre-high (16,621 ft) mountain in the Andes of Peru, located in the Junín Region, Huancayo Province (a province with an approximate population of 545,615 inhabitants), Chongos Alto District, and is west of Wira Challwa.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Waqra Willka_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6487,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.489",
"value": "?search="
},
{
"operation": "search",
"time": "18.578",
"value": "Waqra Willka"
},
{
"operation": "Now on",
"time": "48.132",
"value": "Waqra Willka"
},
{
"operation": "Highlighting",
"time": "60.501",
"value": "Waqra Willka_sentence_0"
},
{
"operation": "Highlighting",
"time": "79.091",
"value": "Waqra Willka_sentence_1"
},
{
"operation": "hyperlink",
"time": "85.617",
"value": "Huancayo Province"
},
{
"operation": "Now on",
"time": "86.597",
"value": "Huancayo Province"
},
{
"operation": "Highlighting",
"time": "96.756",
"value": "Huancayo Province_header_cell_0_9_0"
},
{
"operation": "Highlighting",
"time": "96.757",
"value": "Huancayo Province_title"
},
{
"operation": "Highlighting",
"time": "97.923",
"value": "Huancayo Province_cell_0_9_1"
},
{
"operation": "Highlighting",
"time": "97.93",
"value": "Huancayo Province_header_cell_0_9_0"
},
{
"operation": "Highlighting",
"time": "97.931",
"value": "Huancayo Province_header_cell_0_8_0"
},
{
"operation": "back-button-clicked",
"time": "105.319",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "105.368",
"value": "Waqra Willka"
},
{
"operation": "Highlighting",
"time": "118.667",
"value": "Waqra Willka_sentence_2"
},
{
"operation": "Highlighting",
"time": "129.738",
"value": "Waqra Willka_sentence_2"
},
{
"operation": "finish",
"time": "140.913",
"value": "finish"
}
]
}
|
41028
|
Valter Borges is a pitcher that currently plays in the Ney Work Yankees since 2014.
|
{
"evidence": [
"Valter Borges_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:\nValter Borges is a pitcher that currently plays in the Ney Work Yankees since 2014.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Valter Borges_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6488,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.725",
"value": "?search="
},
{
"operation": "search",
"time": "17.179",
"value": "Valter Borges"
},
{
"operation": "Now on",
"time": "17.846",
"value": "Valter Borges"
},
{
"operation": "search",
"time": "48.002",
"value": "Contains...Valter Borges"
},
{
"operation": "Now on",
"time": "49.653",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "59.957",
"value": "Valter Santos"
},
{
"operation": "Now on",
"time": "60.47",
"value": "Valter Santos"
},
{
"operation": "back-button-clicked",
"time": "66.04",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "66.742",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "94.144",
"value": "Valter Borges"
},
{
"operation": "Now on",
"time": "94.569",
"value": "Valter Borges"
},
{
"operation": "Highlighting",
"time": "96.717",
"value": "Valter Borges_sentence_0"
},
{
"operation": "finish",
"time": "105.241",
"value": "finish"
}
]
}
|
exfever_2715
|
Alicia Amanda Vikander was trained as a ballet dancer at the Royal Swedish Ballet in the largest and capital yet one of the largest cities in terms of area in Sweden.?
|
{
"evidence": [
"Alicia Vikander",
"Stockholm",
"Stockholm Municipality"
],
"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:\nAlicia Amanda Vikander was trained as a ballet dancer at the Royal Swedish Ballet in the largest and capital yet one of the largest cities in terms of area in Sweden.?\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Alicia Vikander",
"Stockholm",
"Stockholm Municipality"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6489,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
31479
|
Rudnaya Pristan is a lead smelting village and considered as one of the worst polluted places in the world that is located at the mouth of the Rudnaya River, on the Pacific coast of Moscow, Russia with a population of 2,107 as of 2010.
|
{
"evidence": [
"Rudnaya Pristan_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:\nRudnaya Pristan is a lead smelting village and considered as one of the worst polluted places in the world that is located at the mouth of the Rudnaya River, on the Pacific coast of Moscow, Russia with a population of 2,107 as of 2010.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Rudnaya Pristan_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6490,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.049",
"value": "?search="
},
{
"operation": "search",
"time": "11.211",
"value": "Rudnaya Pristan"
},
{
"operation": "Now on",
"time": "12.216",
"value": "Rudnaya Pristan"
},
{
"operation": "Highlighting",
"time": "35.856",
"value": "Rudnaya Pristan_sentence_4"
},
{
"operation": "Highlighting",
"time": "63.372",
"value": "Rudnaya Pristan_sentence_7"
},
{
"operation": "Highlighting",
"time": "87.928",
"value": "Rudnaya Pristan_sentence_1"
},
{
"operation": "Highlighting",
"time": "115.743",
"value": "Rudnaya Pristan_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "116.981",
"value": "Rudnaya Pristan_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "116.997",
"value": "Rudnaya Pristan_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "117.005",
"value": "Rudnaya Pristan_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "132.906",
"value": "Rudnaya Pristan_cell_0_1_1"
},
{
"operation": "Highlighting deleted",
"time": "132.921",
"value": "Rudnaya Pristan_header_cell_0_1_0"
},
{
"operation": "Highlighting deleted",
"time": "132.926",
"value": "Rudnaya Pristan_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "138.987",
"value": "Rudnaya Pristan_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "139.001",
"value": "Rudnaya Pristan_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "139.002",
"value": "Rudnaya Pristan_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "146.404",
"value": "Rudnaya Pristan_cell_0_1_1"
},
{
"operation": "Highlighting deleted",
"time": "146.42",
"value": "Rudnaya Pristan_header_cell_0_1_0"
},
{
"operation": "Highlighting deleted",
"time": "146.425",
"value": "Rudnaya Pristan_header_cell_0_0_0"
},
{
"operation": "Page search",
"time": "152.973",
"value": "moscow"
},
{
"operation": "Highlighting",
"time": "158.557",
"value": "Rudnaya Pristan_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "161.873",
"value": "Rudnaya Pristan_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "162.62",
"value": "Rudnaya Pristan_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "163.906",
"value": "Rudnaya Pristan_sentence_7"
},
{
"operation": "finish",
"time": "178.507",
"value": "finish"
}
]
}
|
83287
|
Oudeschoot is located in the province of Friesland, the Netherlands with a total population of 5,000.
|
{
"evidence": [
"Oudeschoot_sentence_0",
"Oudeschoot_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:\nOudeschoot is located in the province of Friesland, the Netherlands with a total population of 5,000.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Oudeschoot_sentence_0",
"Oudeschoot_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6491,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.909",
"value": "?search="
},
{
"operation": "search",
"time": "10.956",
"value": "Oudeschoot"
},
{
"operation": "Now on",
"time": "11.84",
"value": "Oudeschoot"
},
{
"operation": "Highlighting",
"time": "17.136",
"value": "Oudeschoot_sentence_0"
},
{
"operation": "Highlighting",
"time": "19.683",
"value": "Oudeschoot_sentence_1"
},
{
"operation": "finish",
"time": "31.535",
"value": "finish"
}
]
}
|
55869
|
Ludwikowice Kłodzkie was part of Germany between 1871 and 1945 wherein in 1942, the Germans established a forced labor—a vital part of the German economic exploitation of conquered territories that also contributed to the mass extermination of populations in occupied Europe—camp for Jews in the village before transforming it into a subcamp intended for Jewish women.
|
{
"evidence": [
"Ludwikowice Kłodzkie_sentence_4",
"Ludwikowice Kłodzkie_sentence_5",
"Forced labour under German rule during World War II_sentence_2",
"Forced labour under German rule during World War II_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:\nLudwikowice Kłodzkie was part of Germany between 1871 and 1945 wherein in 1942, the Germans established a forced labor—a vital part of the German economic exploitation of conquered territories that also contributed to the mass extermination of populations in occupied Europe—camp for Jews in the village before transforming it into a subcamp intended for Jewish women.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Ludwikowice Kłodzkie_sentence_4",
"Ludwikowice Kłodzkie_sentence_5",
"Forced labour under German rule during World War II_sentence_2",
"Forced labour under German rule during World War II_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6492,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.997",
"value": "?search="
},
{
"operation": "search",
"time": "16.369",
"value": "Ludwikowice Kłodzkie"
},
{
"operation": "Now on",
"time": "17.179",
"value": "Ludwikowice Kłodzkie"
},
{
"operation": "Highlighting",
"time": "26.061",
"value": "Ludwikowice Kłodzkie_sentence_4"
},
{
"operation": "Highlighting",
"time": "42.914",
"value": "Ludwikowice Kłodzkie_sentence_5"
},
{
"operation": "hyperlink",
"time": "50.81",
"value": "forced labour"
},
{
"operation": "Now on",
"time": "53.048",
"value": "Forced labour under German rule during World War II"
},
{
"operation": "Highlighting",
"time": "59.544",
"value": "Forced labour under German rule during World War II_sentence_2"
},
{
"operation": "Highlighting",
"time": "63.197",
"value": "Forced labour under German rule during World War II_sentence_3"
},
{
"operation": "finish",
"time": "126.654",
"value": "finish"
}
]
}
|
exfever_316
|
Jaime Lannister is a fictional character in the A Song of Ice and Fire series portrayed by the Danish actor who had his breakthrough role in Denmark with the 1994 thriller film directed and written by Ole Bornedal.
|
{
"evidence": [
"Jaime Lannister",
"Nikolaj Coster-Waldau",
"Nightwatch (1994 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:\nJaime Lannister is a fictional character in the A Song of Ice and Fire series portrayed by the Danish actor who had his breakthrough role in Denmark with the 1994 thriller film directed and written by Ole Bornedal.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jaime Lannister",
"Nikolaj Coster-Waldau",
"Nightwatch (1994 film)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6493,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
52000
|
Wesley Barresi was named in the Netherlands' One Month International (ODI) squad; he was also named as the substitute player for Poland.
|
{
"evidence": [
"Wesley Barresi_sentence_3",
"Wesley Barresi_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:\nWesley Barresi was named in the Netherlands' One Month International (ODI) squad; he was also named as the substitute player for Poland.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Wesley Barresi_sentence_3",
"Wesley Barresi_sentence_4"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6494,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.732",
"value": "?search="
},
{
"operation": "search",
"time": "9.575",
"value": "Wesley Barresi"
},
{
"operation": "Now on",
"time": "10.542",
"value": "Wesley Barresi"
},
{
"operation": "Highlighting",
"time": "18.023",
"value": "Wesley Barresi_sentence_3"
},
{
"operation": "hyperlink",
"time": "78.424",
"value": "inaugural edition"
},
{
"operation": "Now on",
"time": "79.395",
"value": "2019 Euro T20 Slam"
},
{
"operation": "back-button-clicked",
"time": "102.894",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "103.044",
"value": "Wesley Barresi"
},
{
"operation": "Highlighting",
"time": "109.755",
"value": "Wesley Barresi_sentence_4"
},
{
"operation": "Highlighting",
"time": "114.513",
"value": "Wesley Barresi_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "116.99",
"value": "Wesley Barresi_sentence_5"
},
{
"operation": "finish",
"time": "124.256",
"value": "finish"
}
]
}
|
14879
|
Morris High School Historic District, a national historic district centered on a high school located at Morrisania, includes 51 contributing buildings including the Morris High School and the Trinity Episcopal Church of Morrisania.
|
{
"evidence": [
"Morris High School Historic District_sentence_0",
"Morris High School Historic District_sentence_1",
"Morris High School Historic District_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:\nMorris High School Historic District, a national historic district centered on a high school located at Morrisania, includes 51 contributing buildings including the Morris High School and the Trinity Episcopal Church of Morrisania.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Morris High School Historic District_sentence_0",
"Morris High School Historic District_sentence_1",
"Morris High School Historic District_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6495,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.839",
"value": "undefined"
},
{
"operation": "search",
"time": "14.532",
"value": "Morris High School Historic District"
},
{
"operation": "Now on",
"time": "15.583",
"value": "Morris High School Historic District"
},
{
"operation": "Highlighting",
"time": "19.281",
"value": "Morris High School Historic District_sentence_0"
},
{
"operation": "Highlighting",
"time": "25.399",
"value": "Morris High School Historic District_sentence_1"
},
{
"operation": "Highlighting",
"time": "29.021",
"value": "Morris High School Historic District_sentence_2"
},
{
"operation": "finish",
"time": "49.264",
"value": "finish"
}
]
}
|
52497
|
Vijay Singh, the 2000 champion of the Masters Tournament, headlined the second round with a dominant, seven-under 65 to bolt up to the top of the leaderboard at −9; then Tiger Woods never headlined the five players.
|
{
"evidence": [
"2000 Masters Tournament_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:\nVijay Singh, the 2000 champion of the Masters Tournament, headlined the second round with a dominant, seven-under 65 to bolt up to the top of the leaderboard at −9; then Tiger Woods never headlined the five players.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"2000 Masters Tournament_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6496,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.89",
"value": "?search="
},
{
"operation": "search",
"time": "21.364",
"value": "Vijay Singh (disambiguation)"
},
{
"operation": "Now on",
"time": "22.005",
"value": "Vijay Singh (disambiguation)"
},
{
"operation": "hyperlink",
"time": "32.835",
"value": "Vijay Pal Singh"
},
{
"operation": "Now on",
"time": "33.233",
"value": "Vijay Pal Singh"
},
{
"operation": "search",
"time": "52.14",
"value": "Singh Masters Tournament"
},
{
"operation": "Now on",
"time": "54.486",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "68.34",
"value": "Masters Tournament"
},
{
"operation": "Now on",
"time": "69.979",
"value": "Masters Tournament"
},
{
"operation": "Page search",
"time": "75.214",
"value": "2000"
},
{
"operation": "Page search",
"time": "77.161",
"value": "2000"
},
{
"operation": "search",
"time": "107.091",
"value": "2000 Masters Tournament"
},
{
"operation": "Now on",
"time": "108.63",
"value": "2000 Masters Tournament"
},
{
"operation": "Page search",
"time": "115.167",
"value": "Singh"
},
{
"operation": "Highlighting",
"time": "122.315",
"value": "2000 Masters Tournament_sentence_1"
},
{
"operation": "search",
"time": "193.402",
"value": "2000 Masters Tournament second round"
},
{
"operation": "Now on",
"time": "195.285",
"value": "undefined"
},
{
"operation": "search",
"time": "214.354",
"value": "2000 Masters Tournament"
},
{
"operation": "Now on",
"time": "214.901",
"value": "2000 Masters Tournament"
},
{
"operation": "Page search",
"time": "221.913",
"value": "dominant"
},
{
"operation": "Page search",
"time": "245.312",
"value": "-9"
},
{
"operation": "search",
"time": "329.238",
"value": "Masters Tournament Singh"
},
{
"operation": "Now on",
"time": "329.952",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "337.41",
"value": "PGA Championship"
},
{
"operation": "Now on",
"time": "342.175",
"value": "PGA Championship"
},
{
"operation": "Page search",
"time": "345.572",
"value": "singh"
},
{
"operation": "Highlighting",
"time": "368.262",
"value": "PGA Championship_cell_1_21_1"
},
{
"operation": "Highlighting",
"time": "368.263",
"value": "PGA Championship_title"
},
{
"operation": "Highlighting",
"time": "368.263",
"value": "PGA Championship_section_3"
},
{
"operation": "Highlighting",
"time": "368.265",
"value": "PGA Championship_section_4"
},
{
"operation": "Highlighting",
"time": "368.268",
"value": "PGA Championship_header_cell_1_0_1"
},
{
"operation": "Highlighting",
"time": "370.016",
"value": "PGA Championship_cell_1_21_0"
},
{
"operation": "Highlighting",
"time": "370.022",
"value": "PGA Championship_header_cell_1_0_0"
},
{
"operation": "finish",
"time": "419.361",
"value": "finish"
}
]
}
|
69916
|
The Shadowrun is a fantasy movie about a near-future world where magic has returned to the world and dragons can take human form.
|
{
"evidence": [
"Shadowrun_sentence_2",
"Shadowrun_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:\nThe Shadowrun is a fantasy movie about a near-future world where magic has returned to the world and dragons can take human form.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Shadowrun_sentence_2",
"Shadowrun_sentence_5"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6497,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.341",
"value": "?search="
},
{
"operation": "search",
"time": "16.228",
"value": "Shadowrun"
},
{
"operation": "Now on",
"time": "26.157",
"value": "Shadowrun"
},
{
"operation": "Highlighting",
"time": "113.741",
"value": "Shadowrun_sentence_2"
},
{
"operation": "Page search",
"time": "123.357",
"value": "movie"
},
{
"operation": "search",
"time": "178.516",
"value": "dragons"
},
{
"operation": "Now on",
"time": "189.027",
"value": "Dragon"
},
{
"operation": "search",
"time": "198.358",
"value": "Shadowrun (disambiguation)"
},
{
"operation": "Now on",
"time": "199.483",
"value": "Shadowrun (disambiguation)"
},
{
"operation": "search",
"time": "223.21",
"value": "Shadow Run"
},
{
"operation": "Now on",
"time": "234.572",
"value": "Shadowrun"
},
{
"operation": "Highlighting",
"time": "243.454",
"value": "Shadowrun_sentence_5"
},
{
"operation": "finish",
"time": "254.257",
"value": "finish"
}
]
}
|
56697
|
School Profiles, produced at least once in each academic year including standard data information and summary of school budget, were required to be created by all maintained schools in England, except for maintained nursery schools.
|
{
"evidence": [
"School profile_sentence_5",
"School profile_sentence_3",
"School profile_sentence_7"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSchool Profiles, produced at least once in each academic year including standard data information and summary of school budget, were required to be created by all maintained schools in England, except for maintained nursery schools.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"School profile_sentence_5",
"School profile_sentence_3",
"School profile_sentence_7"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6498,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.736",
"value": "?search="
},
{
"operation": "search",
"time": "10.439",
"value": "School profile"
},
{
"operation": "Now on",
"time": "11.151",
"value": "School profile"
},
{
"operation": "Highlighting",
"time": "31.316",
"value": "School profile_sentence_5"
},
{
"operation": "Page search",
"time": "67.798",
"value": "budget"
},
{
"operation": "Page search",
"time": "75.805",
"value": "data"
},
{
"operation": "Highlighting",
"time": "131.531",
"value": "School profile_sentence_2"
},
{
"operation": "Highlighting",
"time": "134.511",
"value": "School profile_sentence_3"
},
{
"operation": "Page search",
"time": "163.163",
"value": "academic year"
},
{
"operation": "Highlighting",
"time": "168.215",
"value": "School profile_sentence_7"
},
{
"operation": "Highlighting deleted",
"time": "196.259",
"value": "School profile_sentence_2"
},
{
"operation": "hyperlink",
"time": "198.813",
"value": "National Curriculum assessments"
},
{
"operation": "Now on",
"time": "199.593",
"value": "National Curriculum assessment"
},
{
"operation": "Page search",
"time": "203.116",
"value": "budget"
},
{
"operation": "back-button-clicked",
"time": "207.02",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "207.092",
"value": "School profile"
},
{
"operation": "finish",
"time": "213.015",
"value": "finish"
}
]
}
|
exfever_4639
|
Ron Cobb was an American-Australian artist who worked on an Australian science fiction film directed by Robert Zemeckis.
|
{
"evidence": [
"Ron Cobb",
"Back to the Future"
],
"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:\nRon Cobb was an American-Australian artist who worked on an Australian science fiction film directed by Robert Zemeckis.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Ron Cobb",
"Back to the Future"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6499,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
19061
|
Lynn Hornor was a British politician who was the president and manager of a number of coal, oil and gas development, and land companies and served as a member of the advisory West Virginia council of defense during the World War I.
|
{
"evidence": [
"Lynn Hornor_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:\nLynn Hornor was a British politician who was the president and manager of a number of coal, oil and gas development, and land companies and served as a member of the advisory West Virginia council of defense during the World War I.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Lynn Hornor_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6500,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.233",
"value": "?search="
},
{
"operation": "search",
"time": "5.64",
"value": "Lynn Hornor"
},
{
"operation": "Now on",
"time": "6.431",
"value": "Lynn Hornor"
},
{
"operation": "Highlighting",
"time": "17.949",
"value": "Lynn Hornor_sentence_0"
},
{
"operation": "finish",
"time": "38.726",
"value": "finish"
}
]
}
|
exfever_2396
|
Daniel Michael DeVito Jr. is an American actor known for his roles in a 1983 comedy-drama film directed by the co-founder of Gracie Films.
|
{
"evidence": [
"Danny DeVito",
"Terms of Endearment",
"James L. Brooks"
],
"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:\nDaniel Michael DeVito Jr. is an American actor known for his roles in a 1983 comedy-drama film directed by the co-founder of Gracie Films.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Danny DeVito",
"Terms of Endearment",
"James L. Brooks"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6501,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1401
|
Medina is one of the holiest cities while the Great Mosque of Damascus was the fifth-holiest site in Islam.
|
{
"evidence": [
"Medina",
"Holiest sites in Islam",
"Umayyad Mosque"
],
"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:\nMedina is one of the holiest cities while the Great Mosque of Damascus was the fifth-holiest site in Islam.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Medina",
"Holiest sites in Islam",
"Umayyad Mosque"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6502,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_187
|
Counterculture in the Western world includes the literary movement started by a group of authors whose work explored and influenced American culture and politics in the post-war era.
|
{
"evidence": [
"Counterculture",
"Beat Generation"
],
"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:\nCounterculture in the Western world includes the literary movement started by a group of authors whose work explored and influenced American culture and politics in the post-war era.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Counterculture",
"Beat Generation"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6503,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6468
|
Iron Fist is an American film series created by Scott Buck for an American television production company responsible for live-action television series that is based on the American comic books and related media that were started by Martin Goodman in 1939.
|
{
"evidence": [
"Iron Fist (TV series)",
"Marvel Television",
"Marvel Comics"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nIron Fist is an American film series created by Scott Buck for an American television production company responsible for live-action television series that is based on the American comic books and related media that were started by Martin Goodman in 1939.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Iron Fist (TV series)",
"Marvel Television",
"Marvel Comics"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6504,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
72030
|
In the 1994 Slovak disclosure referendum took place in Austria (a landlocked country in Central Europe) 95.9% of people voted for it and 4.1% voted against it.
|
{
"evidence": [
"1994 Slovak disclosure referendum_sentence_0"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nIn the 1994 Slovak disclosure referendum took place in Austria (a landlocked country in Central Europe) 95.9% of people voted for it and 4.1% voted against it.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"1994 Slovak disclosure referendum_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6505,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.67",
"value": "?search="
},
{
"operation": "search",
"time": "12.942",
"value": "1994 Slovak disclosure referendum"
},
{
"operation": "Now on",
"time": "14.03",
"value": "1994 Slovak disclosure referendum"
},
{
"operation": "Highlighting",
"time": "17.565",
"value": "1994 Slovak disclosure referendum_sentence_0"
},
{
"operation": "finish",
"time": "30.365",
"value": "finish"
}
]
}
|
exfever_4512
|
Keeping the Faith is a 2000 American romantic comedy film starring an American actor who won a Golden Globe Award that was first awarded by the Hollywood Foreign Press Association in 1944.
|
{
"evidence": [
"Keeping the Faith",
"Edward Norton",
"Golden Globe Award for Best Supporting Actor – Motion Picture"
],
"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:\nKeeping the Faith is a 2000 American romantic comedy film starring an American actor who won a Golden Globe Award that was first awarded by the Hollywood Foreign Press Association in 1944.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Keeping the Faith",
"Edward Norton",
"Golden Globe Award for Best Supporting Actor – Motion Picture"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6506,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6014
|
Gabrielle Monique Union is known for her performance in a 2001 French romantic comedy drama film.
|
{
"evidence": [
"Gabrielle Union",
"The Brothers (2001 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:\nGabrielle Monique Union is known for her performance in a 2001 French romantic comedy drama film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Gabrielle Union",
"The Brothers (2001 film)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6507,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3450
|
Only Lovers Left Alive featured the song Funnel of Love.
|
{
"evidence": [
"Only Lovers Left Alive",
"Jim Jarmusch",
"Independent film"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nOnly Lovers Left Alive featured the song Funnel of Love.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Only Lovers Left Alive",
"Jim Jarmusch",
"Independent film"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6508,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5600
|
Tezaab starred an Indian actor and film producer who received several accolades, including two of the most prominent film award ceremony in India.
|
{
"evidence": [
"Tezaab",
"Anil Kapoor",
"National Film Awards"
],
"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:\nTezaab starred an Indian actor and film producer who received several accolades, including two of the most prominent film award ceremony in India.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Tezaab",
"Anil Kapoor",
"National Film Awards"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6509,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3130
|
The Ellen show was DeGeneres' second attempt at a sitcom, following Ellen on an American multinational commercial broadcast television network.
|
{
"evidence": [
"The Ellen Show",
"American Broadcasting Company"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Ellen show was DeGeneres' second attempt at a sitcom, following Ellen on an American multinational commercial broadcast television network.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Ellen Show",
"American Broadcasting Company"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6510,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
63693
|
The gene CDX2 regulates several essential processes in the development and function of the lower intestinal epithelium, as well as in the vertebrate embryonic development (that starts with the fertilization of an egg cell by a sperm cell) where it becomes active in endodermal cells that are posterior to the developing stomach.
|
{
"evidence": [
"CDX2_sentence_4",
"CDX2_sentence_5",
"CDX2_sentence_6",
"Embryonic development_sentence_4"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe gene CDX2 regulates several essential processes in the development and function of the lower intestinal epithelium, as well as in the vertebrate embryonic development (that starts with the fertilization of an egg cell by a sperm cell) where it becomes active in endodermal cells that are posterior to the developing stomach.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"CDX2_sentence_4",
"CDX2_sentence_5",
"CDX2_sentence_6",
"Embryonic development_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6511,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "3.642",
"value": "?search="
},
{
"operation": "search",
"time": "89.754",
"value": "CDX2"
},
{
"operation": "Now on",
"time": "90.664",
"value": "CDX2"
},
{
"operation": "search",
"time": "101.466",
"value": "CDX2 (gene)"
},
{
"operation": "Now on",
"time": "107.441",
"value": "CDX2"
},
{
"operation": "Page search",
"time": "129.465",
"value": "gene"
},
{
"operation": "hyperlink",
"time": "207.237",
"value": "CDX2 (gene)"
},
{
"operation": "Now on",
"time": "208.109",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "211.242",
"value": "CDX2"
},
{
"operation": "Now on",
"time": "211.442",
"value": "CDX2"
},
{
"operation": "search",
"time": "221.673",
"value": "gene cdx2"
},
{
"operation": "Now on",
"time": "222.698",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "232.858",
"value": "CDX2"
},
{
"operation": "Now on",
"time": "233.216",
"value": "CDX2"
},
{
"operation": "Page search",
"time": "242.664",
"value": "essential"
},
{
"operation": "Highlighting",
"time": "250.493",
"value": "CDX2_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "258.434",
"value": "CDX2_sentence_1"
},
{
"operation": "Highlighting",
"time": "260.078",
"value": "CDX2_sentence_4"
},
{
"operation": "Highlighting",
"time": "291.414",
"value": "CDX2_sentence_5"
},
{
"operation": "hyperlink",
"time": "297.914",
"value": "embryonic development"
},
{
"operation": "Now on",
"time": "312.015",
"value": "Embryonic development"
},
{
"operation": "Highlighting",
"time": "314.168",
"value": "Embryonic development_sentence_4"
},
{
"operation": "back-button-clicked",
"time": "316.593",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "316.625",
"value": "CDX2"
},
{
"operation": "Page search",
"time": "394.081",
"value": "epithelium"
},
{
"operation": "Highlighting",
"time": "407.119",
"value": "CDX2_sentence_6"
},
{
"operation": "hyperlink",
"time": "440.817",
"value": "embryonic development"
},
{
"operation": "Now on",
"time": "441.197",
"value": "Embryonic development"
},
{
"operation": "Highlighting",
"time": "445.71",
"value": "Embryonic development_sentence_4"
},
{
"operation": "finish",
"time": "454.998",
"value": "finish"
}
]
}
|
exfever_729
|
Other major Silicon Valley cities include a city located in the Santa Clara Valley in northwest Santa Clara County.
|
{
"evidence": [
"Silicon Valley",
"Sunnyvale, California"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nOther major Silicon Valley cities include a city located in the Santa Clara Valley in northwest Santa Clara County.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Silicon Valley",
"Sunnyvale, California"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6512,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
75256
|
Robert Eriksson was born in Levanger, Nord-Trøndelag county and was the son of Gjermund Eriksson and Rita Helene Musum.
|
{
"evidence": [
"Robert Eriksson_sentence_8",
"Robert Eriksson_sentence_9"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nRobert Eriksson was born in Levanger, Nord-Trøndelag county and was the son of Gjermund Eriksson and Rita Helene Musum.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Robert Eriksson_sentence_8",
"Robert Eriksson_sentence_9"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6513,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.941",
"value": "?search="
},
{
"operation": "search",
"time": "20.22",
"value": "Robert Eriksson"
},
{
"operation": "Now on",
"time": "21.12",
"value": "Robert Eriksson"
},
{
"operation": "Highlighting",
"time": "61.657",
"value": "Robert Eriksson_sentence_8"
},
{
"operation": "Highlighting",
"time": "91.981",
"value": "Robert Eriksson_sentence_9"
},
{
"operation": "finish",
"time": "140.041",
"value": "finish"
}
]
}
|
exfever_2988
|
Batman Begins is a 2005 superhero film directed by Christopher Nolan Based on the DC Comics character Batman, starring talented artists, including an American actress, who first achieved fame as Joey Potter on an American teen drama television series created by Kevin Williamson.
|
{
"evidence": [
"Batman Begins",
"Katie Holmes",
"Dawson's Creek"
],
"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:\nBatman Begins is a 2005 superhero film directed by Christopher Nolan Based on the DC Comics character Batman, starring talented artists, including an American actress, who first achieved fame as Joey Potter on an American teen drama television series created by Kevin Williamson.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Batman Begins",
"Katie Holmes",
"Dawson's Creek"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6514,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
51971
|
Diego Mancino published "Cose che cambiano tutto" in 2005 (his first album as a solo artist), and recorded "Idee stupide" with best-selling Italian rapper Fabri Fibra in 2006.
|
{
"evidence": [
"Diego Mancino_sentence_8",
"Fabri Fibra_sentence_1",
"Diego Mancino_sentence_7"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nDiego Mancino published \"Cose che cambiano tutto\" in 2005 (his first album as a solo artist), and recorded \"Idee stupide\" with best-selling Italian rapper Fabri Fibra in 2006.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Diego Mancino_sentence_8",
"Fabri Fibra_sentence_1",
"Diego Mancino_sentence_7"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6515,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.474",
"value": "?search="
},
{
"operation": "search",
"time": "13.248",
"value": "Diego Mancino"
},
{
"operation": "Now on",
"time": "14.168",
"value": "Diego Mancino"
},
{
"operation": "Highlighting",
"time": "23.986",
"value": "Diego Mancino_sentence_7"
},
{
"operation": "Highlighting",
"time": "37.231",
"value": "Diego Mancino_sentence_8"
},
{
"operation": "hyperlink",
"time": "38.31",
"value": "Fabri Fibra"
},
{
"operation": "Now on",
"time": "39.58",
"value": "Fabri Fibra"
},
{
"operation": "Highlighting",
"time": "70.103",
"value": "Fabri Fibra_sentence_1"
},
{
"operation": "back-button-clicked",
"time": "109.322",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "109.551",
"value": "Diego Mancino"
},
{
"operation": "Highlighting deleted",
"time": "112.73",
"value": "Diego Mancino_sentence_7"
},
{
"operation": "search",
"time": "116.938",
"value": "Contains...Cose che cambiano tutto"
},
{
"operation": "Now on",
"time": "118.166",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "125.861",
"value": "Diego Mancino"
},
{
"operation": "Now on",
"time": "126.663",
"value": "Diego Mancino"
},
{
"operation": "hyperlink",
"time": "136.849",
"value": "3.2 soloist album Diego Mancino_section_4"
},
{
"operation": "Highlighting",
"time": "162.793",
"value": "Diego Mancino_sentence_7"
},
{
"operation": "finish",
"time": "176.113",
"value": "finish"
}
]
}
|
28879
|
Small rhombidodecacron is a star polyhedron type or nonconvex isohedral polyhedron having 60 faces, 120 edges, and 42 vertices.
|
{
"evidence": [
"Small rhombidodecahedron_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:\nSmall rhombidodecacron is a star polyhedron type or nonconvex isohedral polyhedron having 60 faces, 120 edges, and 42 vertices.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Small rhombidodecahedron_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6516,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.093",
"value": "?search="
},
{
"operation": "search",
"time": "29.926",
"value": "Small rhombidodecahedron"
},
{
"operation": "Now on",
"time": "30.951",
"value": "Small rhombidodecahedron"
},
{
"operation": "Page search",
"time": "64.33",
"value": "polyhedron"
},
{
"operation": "Page search",
"time": "102.844",
"value": "face"
},
{
"operation": "Highlighting",
"time": "127.993",
"value": "Small rhombidodecahedron_sentence_1"
},
{
"operation": "finish",
"time": "277.008",
"value": "finish"
}
]
}
|
exfever_6775
|
"Wild Ones" is a song by Canadian rapper Flo Rida from his fourth studio album, Wild Ones, released on July 3, 2012.
|
{
"evidence": [
"Wild Ones (song)",
"Wild Ones (Flo Rida album)"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\n\"Wild Ones\" is a song by Canadian rapper Flo Rida from his fourth studio album, Wild Ones, released on July 3, 2012.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Wild Ones (song)",
"Wild Ones (Flo Rida album)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6517,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
4756
|
Gene Feist was born in Brooklyn to a librarian mother and bar-owner father, and grew up with a love of reading that made him a target of teasing when he was young.
|
{
"evidence": [
"Gene Feist_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:\nGene Feist was born in Brooklyn to a librarian mother and bar-owner father, and grew up with a love of reading that made him a target of teasing when he was young.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Gene Feist_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6518,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "19.352",
"value": "Gene Feist"
},
{
"operation": "Highlighting",
"time": "25.11",
"value": "Gene Feist_sentence_2"
},
{
"operation": "finish",
"time": "141.052",
"value": "finish"
}
]
}
|
67928
|
Käferberg is mostly woodland and a popular recreational area with picnic sites that is also the location of restaurants overlooking the city.
|
{
"evidence": [
"Käferberg_sentence_10",
"Käferberg_sentence_9"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nKäferberg is mostly woodland and a popular recreational area with picnic sites that is also the location of restaurants overlooking the city.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Käferberg_sentence_10",
"Käferberg_sentence_9"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6519,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.689",
"value": "?search="
},
{
"operation": "search",
"time": "3.858",
"value": "Käferberg"
},
{
"operation": "Now on",
"time": "6.011",
"value": "Käferberg"
},
{
"operation": "Highlighting",
"time": "11.939",
"value": "Käferberg_sentence_2"
},
{
"operation": "Highlighting",
"time": "14.048",
"value": "Käferberg_sentence_0"
},
{
"operation": "Highlighting",
"time": "14.576",
"value": "Käferberg_sentence_1"
},
{
"operation": "Highlighting",
"time": "23.187",
"value": "Käferberg_sentence_10"
},
{
"operation": "Highlighting",
"time": "31.466",
"value": "Käferberg_sentence_9"
},
{
"operation": "finish",
"time": "38.643",
"value": "finish"
}
]
}
|
94148
|
Goworów, a village in the administrative district of Gmina Międzylesie, within Kłodzko County, Lower Silesian Voivodeship, in south-western Poland, has a population of 330.
|
{
"evidence": [
"Goworów_sentence_0",
"Goworów_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:\nGoworów, a village in the administrative district of Gmina Międzylesie, within Kłodzko County, Lower Silesian Voivodeship, in south-western Poland, has a population of 330.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Goworów_sentence_0",
"Goworów_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6520,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.901",
"value": "?search="
},
{
"operation": "search",
"time": "37.579",
"value": "Goworów"
},
{
"operation": "Now on",
"time": "38.646",
"value": "Goworów"
},
{
"operation": "Highlighting",
"time": "48.193",
"value": "Goworów_sentence_0"
},
{
"operation": "Highlighting",
"time": "73.719",
"value": "Goworów_sentence_3"
},
{
"operation": "finish",
"time": "94.114",
"value": "finish"
}
]
}
|
12053
|
Academy at Ivy Ridge ( boarding school in Ogdensburg, New York) is a private school affiliated with the World Wide Association of Specialty Programs.
|
{
"evidence": [
"Academy at Ivy Ridge_sentence_0",
"Academy at Ivy Ridge_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:\nAcademy at Ivy Ridge ( boarding school in Ogdensburg, New York) is a private school affiliated with the World Wide Association of Specialty Programs.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Academy at Ivy Ridge_sentence_0",
"Academy at Ivy Ridge_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6521,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.518",
"value": "?search="
},
{
"operation": "search",
"time": "8.145",
"value": "Academy at Ivy Ridge"
},
{
"operation": "Now on",
"time": "8.898",
"value": "Academy at Ivy Ridge"
},
{
"operation": "Highlighting",
"time": "14.947",
"value": "Academy at Ivy Ridge_sentence_0"
},
{
"operation": "Highlighting",
"time": "36.447",
"value": "Academy at Ivy Ridge_sentence_2"
},
{
"operation": "finish",
"time": "97.141",
"value": "finish"
}
]
}
|
49663
|
Although El Escorial is a storehouse of art, it does not include any works by masters like Titian, El Greco, or Alonso Cano.
|
{
"evidence": [
"El Escorial_sentence_48"
],
"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:\nAlthough El Escorial is a storehouse of art, it does not include any works by masters like Titian, El Greco, or Alonso Cano.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"El Escorial_sentence_48"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6522,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.676",
"value": "?search="
},
{
"operation": "search",
"time": "10.052",
"value": "El Escorial"
},
{
"operation": "Now on",
"time": "11.468",
"value": "El Escorial"
},
{
"operation": "Page search",
"time": "21.507",
"value": "art"
},
{
"operation": "Highlighting",
"time": "36.077",
"value": "El Escorial_sentence_47"
},
{
"operation": "Highlighting",
"time": "44.515",
"value": "El Escorial_sentence_60"
},
{
"operation": "Highlighting",
"time": "44.515",
"value": "El Escorial_section_1"
},
{
"operation": "Highlighting",
"time": "44.515",
"value": "El Escorial_section_2"
},
{
"operation": "Page search",
"time": "58.202",
"value": "el grec"
},
{
"operation": "Highlighting",
"time": "67.241",
"value": "El Escorial_sentence_48"
},
{
"operation": "finish",
"time": "78.564",
"value": "finish"
}
]
}
|
exfever_1135
|
"Wild Ones" is a song from the fourth studio album of the same name by a Mexican rapper who has sold over 80 million records worldwide, making him one of the best-selling music artists.
|
{
"evidence": [
"Wild Ones (song)",
"Flo Rida"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\n\"Wild Ones\" is a song from the fourth studio album of the same name by a Mexican rapper who has sold over 80 million records worldwide, making him one of the best-selling music artists.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Wild Ones (song)",
"Flo Rida"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6523,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
77155
|
Haffner og Haagaas was a Norwegian series of textbooks in mathematics published in numerous editions between 1925 and 1979 and the series was originally edited by Theodor Haagaas and Einar Haffner, for whom it was named.
|
{
"evidence": [
"Haffner og Haagaas_sentence_0",
"Haffner og Haagaas_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:\nHaffner og Haagaas was a Norwegian series of textbooks in mathematics published in numerous editions between 1925 and 1979 and the series was originally edited by Theodor Haagaas and Einar Haffner, for whom it was named.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Haffner og Haagaas_sentence_0",
"Haffner og Haagaas_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6524,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.755",
"value": "?search="
},
{
"operation": "search",
"time": "11.632",
"value": "Haffner og Haagaas"
},
{
"operation": "Now on",
"time": "12.312",
"value": "Haffner og Haagaas"
},
{
"operation": "Highlighting",
"time": "20.001",
"value": "Haffner og Haagaas_sentence_0"
},
{
"operation": "Highlighting",
"time": "27.965",
"value": "Haffner og Haagaas_sentence_1"
},
{
"operation": "finish",
"time": "38.717",
"value": "finish"
}
]
}
|
27349
|
SOD3 is a gene that encodes a member of the superoxide dismutase protein family and protects the brain, lungs, and other tissues from oxidative stress (a stress that is associated with increased production of oxidizing species or a significant decrease in the effectiveness of antioxidant defenses).
|
{
"evidence": [
"SOD3_sentence_1",
"SOD3_sentence_3",
"Oxidative stress_sentence_9"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSOD3 is a gene that encodes a member of the superoxide dismutase protein family and protects the brain, lungs, and other tissues from oxidative stress (a stress that is associated with increased production of oxidizing species or a significant decrease in the effectiveness of antioxidant defenses).\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"SOD3_sentence_1",
"SOD3_sentence_3",
"Oxidative stress_sentence_9"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6525,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.155",
"value": "?search="
},
{
"operation": "search",
"time": "24.849",
"value": "SOD3"
},
{
"operation": "Now on",
"time": "25.833",
"value": "SOD3"
},
{
"operation": "Highlighting",
"time": "48.69",
"value": "SOD3_sentence_1"
},
{
"operation": "Highlighting",
"time": "68.99",
"value": "SOD3_sentence_3"
},
{
"operation": "hyperlink",
"time": "71.947",
"value": "oxidative stress"
},
{
"operation": "Now on",
"time": "73.272",
"value": "Oxidative stress"
},
{
"operation": "Highlighting",
"time": "142.586",
"value": "Oxidative stress_sentence_9"
},
{
"operation": "finish",
"time": "233.1",
"value": "finish"
}
]
}
|
36831
|
The album, the second and final album by The Arrows released in 1985 which has a title that is a line from the last song titled "Hampton Avenue", has a more serious tone than the previous one.
|
{
"evidence": [
"The Lines Are Open_sentence_0",
"The Lines Are Open_sentence_2",
"The Lines Are Open_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:\nThe album, the second and final album by The Arrows released in 1985 which has a title that is a line from the last song titled \"Hampton Avenue\", has a more serious tone than the previous one.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"The Lines Are Open_sentence_0",
"The Lines Are Open_sentence_2",
"The Lines Are Open_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6526,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.143",
"value": "?search="
},
{
"operation": "search",
"time": "17.659",
"value": "second and final album by The Arrows"
},
{
"operation": "Now on",
"time": "20.088",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "22.447",
"value": "The Lines Are Open"
},
{
"operation": "Now on",
"time": "22.786",
"value": "The Lines Are Open"
},
{
"operation": "Highlighting",
"time": "27.838",
"value": "The Lines Are Open_sentence_0"
},
{
"operation": "Highlighting",
"time": "33.345",
"value": "The Lines Are Open_sentence_2"
},
{
"operation": "Highlighting",
"time": "41.427",
"value": "The Lines Are Open_sentence_3"
},
{
"operation": "finish",
"time": "64.312",
"value": "finish"
}
]
}
|
exfever_1217
|
Halle Berry's debut film was Boomerang.
|
{
"evidence": [
"Boomerang (1992 film)",
"Halle Berry"
],
"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:\nHalle Berry's debut film was Boomerang.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Boomerang (1992 film)",
"Halle Berry"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6527,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2975
|
Ryan Murphy's Ratched is the last series of Sharon Vonne Stone.
|
{
"evidence": [
"Sharon Stone",
"Primetime Emmy Award"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nRyan Murphy's Ratched is the last series of Sharon Vonne Stone.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Sharon Stone",
"Primetime Emmy Award"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6528,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
71690
|
The Bombmaker was originally written as a series and features over five cast members.
|
{
"evidence": [
"The Bombmaker_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 Bombmaker was originally written as a series and features over five cast members.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"The Bombmaker_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6529,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.167",
"value": "?search="
},
{
"operation": "search",
"time": "15.421",
"value": "The Bombmaker"
},
{
"operation": "Now on",
"time": "17.86",
"value": "The Bombmaker"
},
{
"operation": "Highlighting",
"time": "37.165",
"value": "The Bombmaker_sentence_2"
},
{
"operation": "finish",
"time": "45.66",
"value": "finish"
}
]
}
|
18703
|
In 2001 and 2015 the Galagedara Polling Division claimed that UNP would win which accurately matched the country's results, as well as the Kandy electoral district results, which is one of 22 electoral districts of Sri Lanka created by the 1978 Constitution.
|
{
"evidence": [
"Galagedara Polling Division_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 2001 and 2015 the Galagedara Polling Division claimed that UNP would win which accurately matched the country's results, as well as the Kandy electoral district results, which is one of 22 electoral districts of Sri Lanka created by the 1978 Constitution.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Galagedara Polling Division_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6530,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.466",
"value": "?search="
},
{
"operation": "search",
"time": "56.832",
"value": "2001 and 2015 the Galagedara Polling Division"
},
{
"operation": "Now on",
"time": "58.941",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "63.847",
"value": "Galagedara Polling Division"
},
{
"operation": "Now on",
"time": "65.641",
"value": "Galagedara Polling Division"
},
{
"operation": "Highlighting",
"time": "129.932",
"value": "Galagedara Polling Division_sentence_0"
},
{
"operation": "Page search",
"time": "134.88",
"value": "unp"
},
{
"operation": "Highlighting",
"time": "164.639",
"value": "Galagedara Polling Division_sentence_3"
},
{
"operation": "Highlighting",
"time": "164.643",
"value": "Galagedara Polling Division_section_10"
},
{
"operation": "Highlighting",
"time": "164.645",
"value": "Galagedara Polling Division_section_11"
},
{
"operation": "Highlighting deleted",
"time": "189.279",
"value": "Galagedara Polling Division_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "189.286",
"value": "Galagedara Polling Division_section_10"
},
{
"operation": "Highlighting deleted",
"time": "189.291",
"value": "Galagedara Polling Division_section_11"
},
{
"operation": "Highlighting",
"time": "240.638",
"value": "Galagedara Polling Division_sentence_3"
},
{
"operation": "Highlighting",
"time": "240.642",
"value": "Galagedara Polling Division_section_10"
},
{
"operation": "Highlighting",
"time": "240.643",
"value": "Galagedara Polling Division_section_11"
},
{
"operation": "Highlighting deleted",
"time": "244.738",
"value": "Galagedara Polling Division_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "244.744",
"value": "Galagedara Polling Division_section_10"
},
{
"operation": "Highlighting deleted",
"time": "244.748",
"value": "Galagedara Polling Division_section_11"
},
{
"operation": "finish",
"time": "254.339",
"value": "finish"
}
]
}
|
64526
|
The Shops at Willow Lawn is a shopping center outside Richmond, Virginia where the Barksdale Theatre is currently housed.
|
{
"evidence": [
"The Shops at Willow Lawn_sentence_0",
"The Shops at Willow Lawn_sentence_19",
"The Shops at Willow Lawn_sentence_20"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Shops at Willow Lawn is a shopping center outside Richmond, Virginia where the Barksdale Theatre is currently housed.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"The Shops at Willow Lawn_sentence_0",
"The Shops at Willow Lawn_sentence_19",
"The Shops at Willow Lawn_sentence_20"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6531,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.496",
"value": "?search="
},
{
"operation": "search",
"time": "24.367",
"value": "The Shops at Willow Lawn"
},
{
"operation": "Now on",
"time": "27.834",
"value": "The Shops at Willow Lawn"
},
{
"operation": "Highlighting",
"time": "30.891",
"value": "The Shops at Willow Lawn_sentence_0"
},
{
"operation": "Highlighting",
"time": "49.304",
"value": "The Shops at Willow Lawn_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "51.606",
"value": "The Shops at Willow Lawn_sentence_5"
},
{
"operation": "Page search",
"time": "64.515",
"value": "Barksdale Theatre"
},
{
"operation": "Page search",
"time": "64.81",
"value": "Barksdale Theatre"
},
{
"operation": "Page search",
"time": "65.074",
"value": "Barksdale Theatre"
},
{
"operation": "Page search",
"time": "65.29",
"value": "Barksdale Theatre"
},
{
"operation": "Highlighting",
"time": "68.846",
"value": "The Shops at Willow Lawn_sentence_19"
},
{
"operation": "Highlighting",
"time": "83.826",
"value": "The Shops at Willow Lawn_sentence_20"
},
{
"operation": "finish",
"time": "113.613",
"value": "finish"
}
]
}
|
76638
|
SB Wyvenhoe was converted to a motor ship in 1923 and was rebuilt in steel in 1947.
|
{
"evidence": [
"SB Wyvenhoe_sentence_4",
"SB Wyvenhoe_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:\nSB Wyvenhoe was converted to a motor ship in 1923 and was rebuilt in steel in 1947.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"SB Wyvenhoe_sentence_4",
"SB Wyvenhoe_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6532,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.523",
"value": "?search="
},
{
"operation": "search",
"time": "7.09",
"value": "SB Wyvenhoe"
},
{
"operation": "Now on",
"time": "7.633",
"value": "SB Wyvenhoe"
},
{
"operation": "Highlighting",
"time": "24.421",
"value": "SB Wyvenhoe_sentence_4"
},
{
"operation": "Highlighting",
"time": "27.515",
"value": "SB Wyvenhoe_sentence_5"
},
{
"operation": "finish",
"time": "51.152",
"value": "finish"
}
]
}
|
exfever_7908
|
Coronary artery disease is the most common cardiovascular disease, which includes what is commonly known as a heart attack, which occurs when blood flow decreases or stops to the coronary artery of the heart, causing damage to the stomach muscle.
|
{
"evidence": [
"Coronary artery disease",
"Myocardial infarction"
],
"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:\nCoronary artery disease is the most common cardiovascular disease, which includes what is commonly known as a heart attack, which occurs when blood flow decreases or stops to the coronary artery of the heart, causing damage to the stomach muscle.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Coronary artery disease",
"Myocardial infarction"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6533,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_691
|
Kate Walsh is an American actress best known for her role as Dr. Addison Montgomery in the American medical drama television series that premiered on the American Broadcasting Company.
|
{
"evidence": [
"Kate Walsh (actress)",
"Grey's Anatomy"
],
"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:\nKate Walsh is an American actress best known for her role as Dr. Addison Montgomery in the American medical drama television series that premiered on the American Broadcasting Company.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Kate Walsh (actress)",
"Grey's Anatomy"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6534,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3491
|
The Blacklist is an American crime thriller television series starring known for playing Ryan Matthews on the CW American teen drama series, developed by Rob Thomas, Gabe Sachs, and Jeff Judah.
|
{
"evidence": [
"The Blacklist (TV series)",
"Ryan Eggold",
"90210 (TV series)"
],
"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 Blacklist is an American crime thriller television series starring known for playing Ryan Matthews on the CW American teen drama series, developed by Rob Thomas, Gabe Sachs, and Jeff Judah.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Blacklist (TV series)",
"Ryan Eggold",
"90210 (TV series)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6535,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
72686
|
Live à Paris is the third live album featuring primarily French-language songs by Canadian singer Celine Dion, released on 21 October 1996 by Columbia Records (an American record label owned by Sony Music Entertainment).
|
{
"evidence": [
"Live à Paris_sentence_1",
"Live à Paris_sentence_2",
"Columbia Records_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:\nLive à Paris is the third live album featuring primarily French-language songs by Canadian singer Celine Dion, released on 21 October 1996 by Columbia Records (an American record label owned by Sony Music Entertainment).\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Live à Paris_sentence_1",
"Live à Paris_sentence_2",
"Columbia Records_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6536,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.765",
"value": "?search="
},
{
"operation": "search",
"time": "15.995",
"value": "Live à Paris"
},
{
"operation": "Now on",
"time": "16.716",
"value": "Live à Paris"
},
{
"operation": "Highlighting",
"time": "20.242",
"value": "Live à Paris_sentence_1"
},
{
"operation": "Highlighting",
"time": "32.21",
"value": "Live à Paris_sentence_2"
},
{
"operation": "hyperlink",
"time": "37.73",
"value": "Columbia Records"
},
{
"operation": "Now on",
"time": "39.662",
"value": "Columbia Records"
},
{
"operation": "Highlighting",
"time": "41.148",
"value": "Columbia Records_sentence_3"
},
{
"operation": "finish",
"time": "129.385",
"value": "finish"
}
]
}
|
exfever_660
|
Maria Yuryevna Sharapova is a Russian former world No. 1 tennis player who was ranked world No. 1 in singles by the principal organizing body of women's professional tennis founded in June 1973 by an American former world No. 1 tennis player who was a member of the victorious United States team in seven Federation Cups.
|
{
"evidence": [
"Maria Sharapova",
"Women's Tennis Association",
"Billie Jean King"
],
"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:\nMaria Yuryevna Sharapova is a Russian former world No. 1 tennis player who was ranked world No. 1 in singles by the principal organizing body of women's professional tennis founded in June 1973 by an American former world No. 1 tennis player who was a member of the victorious United States team in seven Federation Cups.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Maria Sharapova",
"Women's Tennis Association",
"Billie Jean King"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6537,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
94379
|
The 1920 Donegal County Council election elected 45 councilors from ten electoral divisions and Sinn Féin won a majority of the seats.
|
{
"evidence": [
"1920 Donegal County Council election_sentence_1",
"1920 Donegal County Council 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:\nThe 1920 Donegal County Council election elected 45 councilors from ten electoral divisions and Sinn Féin won a majority of the seats.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"1920 Donegal County Council election_sentence_1",
"1920 Donegal County Council election_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6538,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.591",
"value": "?search="
},
{
"operation": "search",
"time": "32.255",
"value": "1920 Donegal County Council election"
},
{
"operation": "Now on",
"time": "33.551",
"value": "1920 Donegal County Council election"
},
{
"operation": "Highlighting",
"time": "47.38",
"value": "1920 Donegal County Council election_sentence_1"
},
{
"operation": "Highlighting",
"time": "69.526",
"value": "1920 Donegal County Council election_sentence_2"
},
{
"operation": "finish",
"time": "94.952",
"value": "finish"
}
]
}
|
87246
|
George Neil Jenkins was appointed Head of the new Department of Oral Physiology before retiring in 1982.
|
{
"evidence": [
"George Neil Jenkins_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:\nGeorge Neil Jenkins was appointed Head of the new Department of Oral Physiology before retiring in 1982.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"George Neil Jenkins_sentence_6"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6539,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.637",
"value": "?search="
},
{
"operation": "search",
"time": "11.55",
"value": "George Neil Jenkins"
},
{
"operation": "Now on",
"time": "12.673",
"value": "George Neil Jenkins"
},
{
"operation": "Page search",
"time": "223.798",
"value": "head"
},
{
"operation": "Highlighting",
"time": "226.676",
"value": "George Neil Jenkins_sentence_5"
},
{
"operation": "Page search",
"time": "239.902",
"value": "1982"
},
{
"operation": "Page search",
"time": "244.926",
"value": "retire"
},
{
"operation": "Highlighting",
"time": "255.5",
"value": "George Neil Jenkins_sentence_6"
},
{
"operation": "Highlighting deleted",
"time": "258.128",
"value": "George Neil Jenkins_sentence_5"
},
{
"operation": "finish",
"time": "266.958",
"value": "finish"
}
]
}
|
47789
|
As described in a film movies, Cordelia Darwin (Inescourt), spinster sister of Egyptologist Michael Darwin (Clark) who resides in the desert, is a believer in reincarnation and Elinor Wayne (Hall), ward of the Darwins, becomes the prey of Egyptian nobleman Aboul Pasha (Jones).
|
{
"evidence": [
"An Arabian Knight_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:\nAs described in a film movies, Cordelia Darwin (Inescourt), spinster sister of Egyptologist Michael Darwin (Clark) who resides in the desert, is a believer in reincarnation and Elinor Wayne (Hall), ward of the Darwins, becomes the prey of Egyptian nobleman Aboul Pasha (Jones).\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"An Arabian Knight_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6540,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.311",
"value": "?search="
},
{
"operation": "search",
"time": "22.769",
"value": "Cordelia Darwin"
},
{
"operation": "Now on",
"time": "24.35",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "60.331",
"value": "An Arabian Knight"
},
{
"operation": "Now on",
"time": "61.41",
"value": "An Arabian Knight"
},
{
"operation": "Page search",
"time": "72.254",
"value": "cordelia"
},
{
"operation": "Highlighting",
"time": "78.465",
"value": "An Arabian Knight_sentence_2"
},
{
"operation": "hyperlink",
"time": "101.748",
"value": "film magazine"
},
{
"operation": "Now on",
"time": "106.169",
"value": "List of film periodicals"
},
{
"operation": "back-button-clicked",
"time": "108.625",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "109.67",
"value": "An Arabian Knight"
},
{
"operation": "finish",
"time": "117.127",
"value": "finish"
}
]
}
|
64005
|
Made with tomatoes as the primary ingredient, tomato soup may be served hot or cold in a bowl, and may be made in a variety of ways.
|
{
"evidence": [
"Tomato soup_sentence_0",
"Tomato soup_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:\nMade with tomatoes as the primary ingredient, tomato soup may be served hot or cold in a bowl, and may be made in a variety of ways.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Tomato soup_sentence_0",
"Tomato soup_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6541,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.511",
"value": "?search="
},
{
"operation": "search",
"time": "70.927",
"value": "tomato soup"
},
{
"operation": "Now on",
"time": "72.378",
"value": "Tomato soup"
},
{
"operation": "Highlighting",
"time": "76.955",
"value": "Tomato soup_sentence_0"
},
{
"operation": "Highlighting",
"time": "78.731",
"value": "Tomato soup_sentence_1"
},
{
"operation": "finish",
"time": "92.989",
"value": "finish"
}
]
}
|
38636
|
A Sinclair user admitted the ZX-81, which was developed by Sinclair Research before launching in 1981, should be recognized as the first graphics adventure while another Sinclair user provided positive reviews for the game.
|
{
"evidence": [
"ZX81_sentence_213",
"ZX81_sentence_0",
"ZX81_sentence_1",
"ZX81_sentence_269",
"ZX81_sentence_270",
"ZX81_sentence_273"
],
"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:\nA Sinclair user admitted the ZX-81, which was developed by Sinclair Research before launching in 1981, should be recognized as the first graphics adventure while another Sinclair user provided positive reviews for the game.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"ZX81_sentence_213",
"ZX81_sentence_0",
"ZX81_sentence_1",
"ZX81_sentence_269",
"ZX81_sentence_270",
"ZX81_sentence_273"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6542,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.127",
"value": "?search="
},
{
"operation": "search",
"time": "15.088",
"value": "Zx-81"
},
{
"operation": "Now on",
"time": "16.563",
"value": "ZX81"
},
{
"operation": "Highlighting",
"time": "118.017",
"value": "ZX81_sentence_213"
},
{
"operation": "Highlighting",
"time": "186.383",
"value": "ZX81_sentence_0"
},
{
"operation": "Highlighting",
"time": "189.06",
"value": "ZX81_sentence_1"
},
{
"operation": "Highlighting",
"time": "309.304",
"value": "ZX81_sentence_15ZX81_sentence_16"
},
{
"operation": "Highlighting",
"time": "333.754",
"value": "ZX81_sentence_269"
},
{
"operation": "Highlighting",
"time": "336.386",
"value": "ZX81_sentence_270"
},
{
"operation": "Highlighting",
"time": "348.491",
"value": "ZX81_sentence_273"
},
{
"operation": "finish",
"time": "403.898",
"value": "finish"
}
]
}
|
90111
|
Charles Darling Parks was married on December 4, 1889, to Eleanor Sophia, and in 1910, he bought Tarrywile Mansion (which is a large municipal park in the city of Danbury, Connecticut, and is consists of 722 acres) from Dr. William C. Wiles.
|
{
"evidence": [
"Charles Darling Parks_sentence_26",
"Charles Darling Parks_sentence_28",
"Tarrywile Park_sentence_0",
"Tarrywile Park_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:\nCharles Darling Parks was married on December 4, 1889, to Eleanor Sophia, and in 1910, he bought Tarrywile Mansion (which is a large municipal park in the city of Danbury, Connecticut, and is consists of 722 acres) from Dr. William C. Wiles.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Charles Darling Parks_sentence_26",
"Charles Darling Parks_sentence_28",
"Tarrywile Park_sentence_0",
"Tarrywile Park_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6543,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.235",
"value": "?search="
},
{
"operation": "search",
"time": "6.397",
"value": "Charles Darling Parks"
},
{
"operation": "Now on",
"time": "7.037",
"value": "Charles Darling Parks"
},
{
"operation": "Highlighting",
"time": "10.921",
"value": "Charles Darling Parks_sentence_26"
},
{
"operation": "Highlighting",
"time": "49.885",
"value": "Charles Darling Parks_sentence_28"
},
{
"operation": "hyperlink",
"time": "69.629",
"value": "Tarrywile Mansion"
},
{
"operation": "Now on",
"time": "70.297",
"value": "Tarrywile Park"
},
{
"operation": "Highlighting",
"time": "72.12",
"value": "Tarrywile Park_sentence_0"
},
{
"operation": "Highlighting",
"time": "77.157",
"value": "Tarrywile Park_sentence_1"
},
{
"operation": "back-button-clicked",
"time": "81.642",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "81.719",
"value": "Charles Darling Parks"
},
{
"operation": "finish",
"time": "222.763",
"value": "finish"
}
]
}
|
58017
|
Ditrigona furvicosta, a moth in the family Drepanidae that was described by George Hampson in 1911, has forewings that are white with a conspicuous buff costa.
|
{
"evidence": [
"Ditrigona furvicosta_sentence_0",
"Ditrigona furvicosta_sentence_1",
"Ditrigona furvicosta_sentence_4"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nDitrigona furvicosta, a moth in the family Drepanidae that was described by George Hampson in 1911, has forewings that are white with a conspicuous buff costa.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Ditrigona furvicosta_sentence_0",
"Ditrigona furvicosta_sentence_1",
"Ditrigona furvicosta_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6544,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.738",
"value": "?search="
},
{
"operation": "search",
"time": "11.933",
"value": "Ditrigona furvicosta"
},
{
"operation": "Now on",
"time": "12.895",
"value": "Ditrigona furvicosta"
},
{
"operation": "Highlighting",
"time": "14.441",
"value": "Ditrigona furvicosta_sentence_0"
},
{
"operation": "Highlighting",
"time": "17.316",
"value": "Ditrigona furvicosta_sentence_1"
},
{
"operation": "Highlighting",
"time": "20.597",
"value": "Ditrigona furvicosta_sentence_4"
},
{
"operation": "finish",
"time": "30.474",
"value": "finish"
}
]
}
|
33990
|
RAD23B is a protein encoded by the RAD23B gene and is the is the initial damage recognition factor in global genomic nucleotide excision repair as well as the assembly of the other core NER factors
|
{
"evidence": [
"RAD23B_sentence_7",
"RAD23B_sentence_5",
"RAD23B_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:\nRAD23B is a protein encoded by the RAD23B gene and is the is the initial damage recognition factor in global genomic nucleotide excision repair as well as the assembly of the other core NER factors\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"RAD23B_sentence_7",
"RAD23B_sentence_5",
"RAD23B_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6545,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.302",
"value": "?search="
},
{
"operation": "search",
"time": "12.274",
"value": "RAD23B"
},
{
"operation": "Now on",
"time": "13.07",
"value": "RAD23B"
},
{
"operation": "Highlighting",
"time": "263.746",
"value": "RAD23B_sentence_7"
},
{
"operation": "Highlighting",
"time": "271.412",
"value": "RAD23B_sentence_5"
},
{
"operation": "Highlighting",
"time": "283.213",
"value": "RAD23B_sentence_0"
},
{
"operation": "finish",
"time": "365.554",
"value": "finish"
}
]
}
|
52138
|
Alice Lorraine, the daughter of Sir Roland Lorraine, throws herself in the river to avoid marrying a drunk named Chapman but is rescued.
|
{
"evidence": [
"Alice Lorraine_sentence_4",
"Alice Lorraine_sentence_11",
"Alice Lorraine_sentence_9"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAlice Lorraine, the daughter of Sir Roland Lorraine, throws herself in the river to avoid marrying a drunk named Chapman but is rescued.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Alice Lorraine_sentence_4",
"Alice Lorraine_sentence_11",
"Alice Lorraine_sentence_9"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6546,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.401",
"value": "?search="
},
{
"operation": "search",
"time": "10.569",
"value": "Alice Lorraine"
},
{
"operation": "Now on",
"time": "11.283",
"value": "Alice Lorraine"
},
{
"operation": "Highlighting",
"time": "38.47",
"value": "Alice Lorraine_sentence_4"
},
{
"operation": "Highlighting",
"time": "83.929",
"value": "Alice Lorraine_sentence_11"
},
{
"operation": "Highlighting",
"time": "85.988",
"value": "Alice Lorraine_sentence_9"
},
{
"operation": "finish",
"time": "173.293",
"value": "finish"
}
]
}
|
exfever_4720
|
Spring is the season between winter and summer when the weather becomes warmer and plants start to grow again.
|
{
"evidence": [
"Memorial Day",
"Summer",
"Autumn"
],
"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:\nSpring is the season between winter and summer when the weather becomes warmer and plants start to grow again.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Memorial Day",
"Summer",
"Autumn"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6547,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5714
|
Buzz Aldrin is a Canadian former astronaut born in a borough in Essex County, New Jersey, United States.
|
{
"evidence": [
"Buzz Aldrin",
"Glen Ridge, New Jersey"
],
"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:\nBuzz Aldrin is a Canadian former astronaut born in a borough in Essex County, New Jersey, United States.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Buzz Aldrin",
"Glen Ridge, New Jersey"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6548,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_645
|
Goliyon Ki Raasleela Ram-Leela is a 2013 Indian Hindi-language tragic romance film starring an Indian actor who works in Hindi films.
|
{
"evidence": [
"Goliyon Ki Raasleela Ram-Leela",
"Ranveer Singh"
],
"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:\nGoliyon Ki Raasleela Ram-Leela is a 2013 Indian Hindi-language tragic romance film starring an Indian actor who works in Hindi films.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Goliyon Ki Raasleela Ram-Leela",
"Ranveer Singh"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6549,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
34556
|
New Indies Style is a modern 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",
"New Indies Style_sentence_32",
"New Indies Style_sentence_34"
],
"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:\nNew Indies Style is a modern architectural style that employs the use of 'double facade' which protects the facade from heavy rainfall and strong sunlight.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"New Indies Style_sentence_0",
"New Indies Style_sentence_32",
"New Indies Style_sentence_34"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6550,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.953",
"value": "?search="
},
{
"operation": "search",
"time": "7.278",
"value": "New Indies Style"
},
{
"operation": "Now on",
"time": "7.999",
"value": "New Indies Style"
},
{
"operation": "Highlighting",
"time": "15.199",
"value": "New Indies Style_sentence_0"
},
{
"operation": "Page search",
"time": "89.206",
"value": "double"
},
{
"operation": "Page search",
"time": "96.405",
"value": "facade"
},
{
"operation": "Highlighting",
"time": "104.103",
"value": "New Indies Style_sentence_32"
},
{
"operation": "Highlighting",
"time": "107.205",
"value": "New Indies Style_sentence_34"
},
{
"operation": "finish",
"time": "156.905",
"value": "finish"
}
]
}
|
24545
|
John Wheeley Gough Gutch was born at Bristol in 1809, the son of John Mathew Gutch, and was educated as a surgeon at the infirmary there and he became a member of the Royal College of Surgeons.
|
{
"evidence": [
"John Wheeley Gough Gutch_sentence_2",
"John Wheeley Gough Gutch_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:\nJohn Wheeley Gough Gutch was born at Bristol in 1809, the son of John Mathew Gutch, and was educated as a surgeon at the infirmary there and he became a member of the Royal College of Surgeons.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"John Wheeley Gough Gutch_sentence_2",
"John Wheeley Gough Gutch_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6551,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.668",
"value": "?search="
},
{
"operation": "search",
"time": "4.444",
"value": "John Wheeley Gough Gutch"
},
{
"operation": "Now on",
"time": "5.065",
"value": "John Wheeley Gough Gutch"
},
{
"operation": "Highlighting",
"time": "13.449",
"value": "John Wheeley Gough Gutch_sentence_2"
},
{
"operation": "Highlighting",
"time": "29.852",
"value": "John Wheeley Gough Gutch_sentence_3"
},
{
"operation": "finish",
"time": "34.927",
"value": "finish"
}
]
}
|
94092
|
Tournexia is from the Plantae kingdom and a member of the Asteraceae family.
|
{
"evidence": [
"Asteraceae_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:\nTournexia is from the Plantae kingdom and a member of the Asteraceae family.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Asteraceae_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6552,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.015",
"value": "?search="
},
{
"operation": "search",
"time": "17.257",
"value": "Contains...Tournexia"
},
{
"operation": "Now on",
"time": "18.117",
"value": "undefined"
},
{
"operation": "search",
"time": "24.257",
"value": "Contains...Tournexia"
},
{
"operation": "Now on",
"time": "24.726",
"value": "undefined"
},
{
"operation": "search",
"time": "29.68",
"value": "turnexia"
},
{
"operation": "Now on",
"time": "30.81",
"value": "undefined"
},
{
"operation": "search",
"time": "43.553",
"value": "tuneria"
},
{
"operation": "Now on",
"time": "44.203",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "48.527",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "48.643",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "52.078",
"value": "turneri"
},
{
"operation": "Now on",
"time": "52.764",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "55.747",
"value": "Chrysoritis"
},
{
"operation": "Now on",
"time": "56.617",
"value": "Chrysoritis"
},
{
"operation": "Page search",
"time": "68.772",
"value": "to"
},
{
"operation": "Page search",
"time": "78.234",
"value": "tornuri"
},
{
"operation": "Page search",
"time": "80.966",
"value": "uri"
},
{
"operation": "hyperlink",
"time": "102.763",
"value": "Chrysoritis turneri"
},
{
"operation": "Now on",
"time": "103.766",
"value": "Chrysoritis turneri"
},
{
"operation": "search",
"time": "123.55",
"value": "Asteraceae"
},
{
"operation": "Now on",
"time": "124.851",
"value": "Asteraceae"
},
{
"operation": "Page search",
"time": "138.865",
"value": "turn"
},
{
"operation": "Page search",
"time": "148",
"value": "exia"
},
{
"operation": "Highlighting",
"time": "161.997",
"value": "Asteraceae_sentence_0"
},
{
"operation": "finish",
"time": "165.81",
"value": "finish"
}
]
}
|
85879
|
The maximum size of adult Japanese bobtail squid is 2.5 cm in mantle length (ML), and its body consists of large fins and a short and dome-shaped mantle surrounded by an iridescent belt.
|
{
"evidence": [
"Sepiolina nipponensis_sentence_2",
"Sepiolina nipponensis_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:\nThe maximum size of adult Japanese bobtail squid is 2.5 cm in mantle length (ML), and its body consists of large fins and a short and dome-shaped mantle surrounded by an iridescent belt.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Sepiolina nipponensis_sentence_2",
"Sepiolina nipponensis_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6553,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.84",
"value": "?search="
},
{
"operation": "search",
"time": "11.41",
"value": "Japanese Bobtail Squid"
},
{
"operation": "Now on",
"time": "11.955",
"value": "Sepiolina nipponensis"
},
{
"operation": "Highlighting",
"time": "15.586",
"value": "Sepiolina nipponensis_sentence_2"
},
{
"operation": "Highlighting",
"time": "21.608",
"value": "Sepiolina nipponensis_sentence_3"
},
{
"operation": "finish",
"time": "78.246",
"value": "finish"
}
]
}
|
exfever_2731
|
Radiohead recorded OK Computer in a landlocked county in the far west of the government statistical region of South East England, borders a county of historic origin, a ceremonial county, and a non-metropolitan county without a county council to the south.
|
{
"evidence": [
"OK Computer",
"Oxfordshire",
"Berkshire"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nRadiohead recorded OK Computer in a landlocked county in the far west of the government statistical region of South East England, borders a county of historic origin, a ceremonial county, and a non-metropolitan county without a county council to the south.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"OK Computer",
"Oxfordshire",
"Berkshire"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6554,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6410
|
Con Man is a Candian comedy web series directed by Alan Tudyk, who was also one of the stars of the 2002 Western drama television series directed by Joss Whedon.
|
{
"evidence": [
"Con Man (web series)",
"Firefly (TV 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:\nCon Man is a Candian comedy web series directed by Alan Tudyk, who was also one of the stars of the 2002 Western drama television series directed by Joss Whedon.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Con Man (web series)",
"Firefly (TV series)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6555,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
51105
|
Le comte Ory is a Spanish comic opera that was written by Gioachino Rossini on 20 August 1828 and was first performed in Salle Le Peletier, Paris, France.
|
{
"evidence": [
"Le comte Ory_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:\nLe comte Ory is a Spanish comic opera that was written by Gioachino Rossini on 20 August 1828 and was first performed in Salle Le Peletier, Paris, France.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Le comte Ory_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6556,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.419",
"value": "?search="
},
{
"operation": "search",
"time": "37.175",
"value": "Le Comte Ory"
},
{
"operation": "Now on",
"time": "39.049",
"value": "Le Comte Ory"
},
{
"operation": "Highlighting",
"time": "61.627",
"value": "Le comte Ory_sentence_0"
},
{
"operation": "Highlighting",
"time": "88.188",
"value": "Le comte Ory_cell_0_3_1"
},
{
"operation": "Highlighting",
"time": "88.193",
"value": "Le comte Ory_header_cell_0_3_0"
},
{
"operation": "Highlighting",
"time": "88.194",
"value": "Le comte Ory_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "254.194",
"value": "Le comte Ory_cell_0_3_1"
},
{
"operation": "Highlighting deleted",
"time": "254.199",
"value": "Le comte Ory_header_cell_0_3_0"
},
{
"operation": "Highlighting deleted",
"time": "254.202",
"value": "Le comte Ory_header_cell_0_0_0"
},
{
"operation": "finish",
"time": "287.314",
"value": "finish"
}
]
}
|
71525
|
"HAM" is a song from a collaborative album released in January 2011 by American rappers Jay-Z and Kanye West, with the help of producer Lexus "Lex Luger" Lewis,
|
{
"evidence": [
"H•A•M_sentence_1",
"H•A•M_sentence_2",
"H•A•M_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:\n\"HAM\" is a song from a collaborative album released in January 2011 by American rappers Jay-Z and Kanye West, with the help of producer Lexus \"Lex Luger\" Lewis,\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"H•A•M_sentence_1",
"H•A•M_sentence_2",
"H•A•M_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6557,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.818",
"value": "?search="
},
{
"operation": "search",
"time": "13.229",
"value": "ham"
},
{
"operation": "Now on",
"time": "14.153",
"value": "Ham"
},
{
"operation": "hyperlink",
"time": "70.391",
"value": "Ham (disambiguation)"
},
{
"operation": "Now on",
"time": "71.289",
"value": "Ham (disambiguation)"
},
{
"operation": "hyperlink",
"time": "162.246",
"value": "H A M"
},
{
"operation": "Now on",
"time": "162.947",
"value": "H•A•M"
},
{
"operation": "Highlighting",
"time": "166.832",
"value": "H•A•M_sentence_1"
},
{
"operation": "Highlighting",
"time": "167.756",
"value": "H•A•M_sentence_2"
},
{
"operation": "Highlighting",
"time": "170.573",
"value": "H•A•M_sentence_3"
},
{
"operation": "finish",
"time": "181.695",
"value": "finish"
}
]
}
|
exfever_6353
|
Steve Jobs was the founder and CEO of an American technology company that specialized in computer workstations intended for higher education and business use.
|
{
"evidence": [
"Steve Jobs",
"NeXT"
],
"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:\nSteve Jobs was the founder and CEO of an American technology company that specialized in computer workstations intended for higher education and business use.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Steve Jobs",
"NeXT"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6558,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
13195
|
Frank Westmore, born in Maywood, Texas, apprenticed at Paramount Pictures (an American film studio and subsidiary of ViacomCBS) with his brother Wally.
|
{
"evidence": [
"Frank Westmore_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:\nFrank Westmore, born in Maywood, Texas, apprenticed at Paramount Pictures (an American film studio and subsidiary of ViacomCBS) with his brother Wally.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Frank Westmore_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6559,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.087",
"value": "?search="
},
{
"operation": "search",
"time": "16.546",
"value": "Frank Westmore"
},
{
"operation": "Now on",
"time": "17.586",
"value": "Frank Westmore"
},
{
"operation": "Highlighting",
"time": "50.509",
"value": "Frank Westmore_sentence_1"
},
{
"operation": "hyperlink",
"time": "66.937",
"value": "Paramount Pictures"
},
{
"operation": "Now on",
"time": "69.864",
"value": "Paramount Pictures"
},
{
"operation": "finish",
"time": "79.166",
"value": "finish"
}
]
}
|
77322
|
Ayr is a historic and registration county in south-west Ireland and sub-region of Strathclyde with four districts, namely, Cumnock and Doon Valley, Cunninghame, Kilmarnock and Loudoun, and Kyle and Carrick.
|
{
"evidence": [
"Ayr_sentence_1",
"Ayrshire_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:\nAyr is a historic and registration county in south-west Ireland and sub-region of Strathclyde with four districts, namely, Cumnock and Doon Valley, Cunninghame, Kilmarnock and Loudoun, and Kyle and Carrick.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Ayr_sentence_1",
"Ayrshire_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6560,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.001",
"value": "?search="
},
{
"operation": "search",
"time": "0.013",
"value": "Ayr"
},
{
"operation": "Now on",
"time": "0.015",
"value": "Ayr"
},
{
"operation": "Highlighting",
"time": "0.027",
"value": "Ayr_sentence_1"
},
{
"operation": "Highlighting",
"time": "0.041",
"value": "Ayr_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "0.05",
"value": "Ayr_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "0.059",
"value": "Ayr_sentence_2"
},
{
"operation": "Highlighting",
"time": "0.059",
"value": "Ayr_sentence_1"
},
{
"operation": "Highlighting",
"time": "0.068",
"value": "Ayr_sentence_2"
},
{
"operation": "hyperlink",
"time": "0.087",
"value": "Ayr (disambiguation)"
},
{
"operation": "Now on",
"time": "0.088",
"value": "Ayr (disambiguation)"
},
{
"operation": "hyperlink",
"time": "0.098",
"value": "County of Ayr"
},
{
"operation": "Now on",
"time": "0.099",
"value": "County of Ayr"
},
{
"operation": "Highlighting",
"time": "0.122",
"value": "Ayrshire_sentence_1"
},
{
"operation": "hyperlink",
"time": "0.127",
"value": "County of Ayr"
},
{
"operation": "Now on",
"time": "0.128",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "0.131",
"value": "Ayrshire"
},
{
"operation": "Now on",
"time": "0.132",
"value": "Ayrshire"
},
{
"operation": "hyperlink",
"time": "0.179",
"value": "Ayr"
},
{
"operation": "Now on",
"time": "0.18",
"value": "Ayr"
},
{
"operation": "Highlighting",
"time": "0.183",
"value": "Ayr_sentence_1"
},
{
"operation": "Highlighting",
"time": "0.191",
"value": "Ayr_sentence_1"
},
{
"operation": "hyperlink",
"time": "0.209",
"value": "Ayr (disambiguation)"
},
{
"operation": "Now on",
"time": "0.209",
"value": "Ayr (disambiguation)"
},
{
"operation": "hyperlink",
"time": "0.216",
"value": "County of Ayr"
},
{
"operation": "Now on",
"time": "0.217",
"value": "County of Ayr"
},
{
"operation": "Highlighting",
"time": "0.218",
"value": "Ayrshire_sentence_1"
},
{
"operation": "finish",
"time": "0.227",
"value": "finish"
},
{
"operation": "Now on",
"time": "1622150485.045",
"value": "Ayr"
},
{
"operation": "finish",
"time": "1622150486.999",
"value": "finish"
}
]
}
|
exfever_2734
|
Salman Khan is an Indian actor who has received awards that honor the film industry of India by an Indian English-language fortnightly magazine published by Worldwide Media.
|
{
"evidence": [
"Salman Khan",
"Filmfare Awards",
"Filmfare"
],
"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:\nSalman Khan is an Indian actor who has received awards that honor the film industry of India by an Indian English-language fortnightly magazine published by Worldwide Media.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Salman Khan",
"Filmfare Awards",
"Filmfare"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6561,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8923
|
My Summer of Love film explores the romantic relationship between Mona portrayed by Natalie Press, and Tamsin played by a British actress. who is the recipient of several accolades, including a Golden Globe Award.
|
{
"evidence": [
"My Summer of Love",
"Emily Blunt"
],
"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:\nMy Summer of Love film explores the romantic relationship between Mona portrayed by Natalie Press, and Tamsin played by a British actress. who is the recipient of several accolades, including a Golden Globe Award.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"My Summer of Love",
"Emily Blunt"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6562,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6076
|
TD Garden is the first multi-purpose arena in Boston.
|
{
"evidence": [
"TD Garden",
"Massachusetts"
],
"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:\nTD Garden is the first multi-purpose arena in Boston.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"TD Garden",
"Massachusetts"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6563,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6561
|
Felicity Jones is an English actress who appeared in the 2008 production of The Chalk Garden at a 251-seat, not-for-profit theatre in Oxford Street, London, England.
|
{
"evidence": [
"Felicity Jones",
"Donmar Warehouse"
],
"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:\nFelicity Jones is an English actress who appeared in the 2008 production of The Chalk Garden at a 251-seat, not-for-profit theatre in Oxford Street, London, England.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Felicity Jones",
"Donmar Warehouse"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6564,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5492
|
The Fosters is a family drama series about a school vice-principal and a warranted law employee of a police force.
|
{
"evidence": [
"The Fosters (2013 TV series)",
"Police officer"
],
"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 Fosters is a family drama series about a school vice-principal and a warranted law employee of a police force.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Fosters (2013 TV series)",
"Police officer"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6565,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8996
|
Andrew Jackson was born in the colonial Carolinas in the decade before the American Revolutionary War, became a frontier lawyer, and married the United States' 7th President, who died just days after his election and before his inauguration in 1828.
|
{
"evidence": [
"Andrew Jackson",
"Rachel Jackson"
],
"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:\nAndrew Jackson was born in the colonial Carolinas in the decade before the American Revolutionary War, became a frontier lawyer, and married the United States' 7th President, who died just days after his election and before his inauguration in 1828.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Andrew Jackson",
"Rachel Jackson"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6566,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
49104
|
One source of input to the thalamic reticular nucleus is the cerebral cortex, which was found to consist of 52 different areas by Korbinian Brodmann.
|
{
"evidence": [
"Korbinian Brodmann_sentence_0",
"Thalamic reticular nucleus_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:\nOne source of input to the thalamic reticular nucleus is the cerebral cortex, which was found to consist of 52 different areas by Korbinian Brodmann.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Korbinian Brodmann_sentence_0",
"Thalamic reticular nucleus_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6567,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.104",
"value": "?search="
},
{
"operation": "search",
"time": "18.386",
"value": "Korbinian Brodmann"
},
{
"operation": "Now on",
"time": "18.927",
"value": "Korbinian Brodmann"
},
{
"operation": "Highlighting",
"time": "21.717",
"value": "Korbinian Brodmann_sentence_0"
},
{
"operation": "hyperlink",
"time": "35.315",
"value": "cerebral cortex"
},
{
"operation": "Now on",
"time": "36.552",
"value": "Cerebral cortex"
},
{
"operation": "Page search",
"time": "50.508",
"value": "halamic reticular nucleus"
},
{
"operation": "hyperlink",
"time": "76.688",
"value": "thalamic reticular nucleus"
},
{
"operation": "Now on",
"time": "77.103",
"value": "Thalamic reticular nucleus"
},
{
"operation": "Page search",
"time": "85.379",
"value": "cerebral cortex"
},
{
"operation": "Highlighting",
"time": "90.749",
"value": "Thalamic reticular nucleus_sentence_5"
},
{
"operation": "finish",
"time": "109.389",
"value": "finish"
}
]
}
|
51272
|
The Williamsburg Railroad was chartered by the South Carolina General Assembly, he name was changed to the Central Railroad of South Carolina and was opened in 1882.
|
{
"evidence": [
"Williamsburg Railroad_sentence_1",
"Williamsburg Railroad_sentence_2",
"Williamsburg Railroad_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:\nThe Williamsburg Railroad was chartered by the South Carolina General Assembly, he name was changed to the Central Railroad of South Carolina and was opened in 1882.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Williamsburg Railroad_sentence_1",
"Williamsburg Railroad_sentence_2",
"Williamsburg Railroad_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6568,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1",
"value": "?search="
},
{
"operation": "search",
"time": "12.559",
"value": "Williamsburg Railroad"
},
{
"operation": "Now on",
"time": "13.426",
"value": "Williamsburg Railroad"
},
{
"operation": "Highlighting",
"time": "23.69",
"value": "Williamsburg Railroad_sentence_1"
},
{
"operation": "Highlighting",
"time": "32.073",
"value": "Williamsburg Railroad_sentence_2"
},
{
"operation": "Highlighting",
"time": "34.121",
"value": "Williamsburg Railroad_sentence_3"
},
{
"operation": "finish",
"time": "57.747",
"value": "finish"
}
]
}
|
exfever_2702
|
Kendrick Lamar is the highest-paid rapper in the United States.
|
{
"evidence": [
"James Blake (musician)",
"The Colour in Anything"
],
"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:\nKendrick Lamar is the highest-paid rapper in the United States.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"James Blake (musician)",
"The Colour in Anything"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6569,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3717
|
Citalopram, sold under the brand name Celexa among others is a medication used to treat a major depressive disorder, some anxiety disorders, some chronic pain conditions, and to help manage some addictions.
|
{
"evidence": [
"Citalopram",
"Antidepressant"
],
"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:\nCitalopram, sold under the brand name Celexa among others is a medication used to treat a major depressive disorder, some anxiety disorders, some chronic pain conditions, and to help manage some addictions.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Citalopram",
"Antidepressant"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6570,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
11985
|
Duliajan is an industrial town in the district of Dibrugarh in Nepal with a total population of 28,626, with a warm and temperate climate and is particularly known for its oil-related industry.
|
{
"evidence": [
"Duliajan_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:\nDuliajan is an industrial town in the district of Dibrugarh in Nepal with a total population of 28,626, with a warm and temperate climate and is particularly known for its oil-related industry.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Duliajan_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 6571,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.692",
"value": "?search="
},
{
"operation": "search",
"time": "13.185",
"value": "Duliajan"
},
{
"operation": "Now on",
"time": "14.374",
"value": "Duliajan"
},
{
"operation": "Page search",
"time": "49.12",
"value": "warm"
},
{
"operation": "Highlighting",
"time": "65.37",
"value": "Duliajan_sentence_0"
},
{
"operation": "Now on",
"time": "123.627",
"value": "Duliajan"
},
{
"operation": "finish",
"time": "138.569",
"value": "finish"
}
]
}
|
38092
|
The United States Board on Geographic Names named the stream in 1933 after Charles Moorman, who in 1735 patented 400 acres (1.6 km) of land in what was then Goochland County, at the junction of the Mechum and (now) Moorman rivers, a 14.3-mile-long (23.0 km) tributary of the South Fork of the Rivanna River in central Virginia in the United States.
|
{
"evidence": [
"Moormans River_sentence_3",
"Moormans River_sentence_4",
"Moormans River_sentence_0"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe United States Board on Geographic Names named the stream in 1933 after Charles Moorman, who in 1735 patented 400 acres (1.6 km) of land in what was then Goochland County, at the junction of the Mechum and (now) Moorman rivers, a 14.3-mile-long (23.0 km) tributary of the South Fork of the Rivanna River in central Virginia in the United States.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Moormans River_sentence_3",
"Moormans River_sentence_4",
"Moormans River_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6572,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.22",
"value": "?search="
},
{
"operation": "search",
"time": "39.146",
"value": "Contains...Charles Moorman"
},
{
"operation": "Now on",
"time": "40.875",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "53.553",
"value": "Charles Harwood Moorman"
},
{
"operation": "Now on",
"time": "54.599",
"value": "Charles Harwood Moorman"
},
{
"operation": "search",
"time": "90.58",
"value": "Moormans River"
},
{
"operation": "Now on",
"time": "91.851",
"value": "Moormans River"
},
{
"operation": "Highlighting",
"time": "110.142",
"value": "Moormans River_sentence_3"
},
{
"operation": "Highlighting",
"time": "117.741",
"value": "Moormans River_sentence_4"
},
{
"operation": "Highlighting",
"time": "133.2",
"value": "Moormans River_sentence_0"
},
{
"operation": "finish",
"time": "179.313",
"value": "finish"
}
]
}
|
exfever_3291
|
Ellen Lee DeGeneres is an American television host and comedian that starred in the sitcom Ellen and hosted the variety comedy talk show, taped in Studio 11 at NBC Studios in a city in the southeastern end of the San Fernando Valley.
|
{
"evidence": [
"Ellen DeGeneres",
"The Ellen DeGeneres Show",
"Burbank, California"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nEllen Lee DeGeneres is an American television host and comedian that starred in the sitcom Ellen and hosted the variety comedy talk show, taped in Studio 11 at NBC Studios in a city in the southeastern end of the San Fernando Valley.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Ellen DeGeneres",
"The Ellen DeGeneres Show",
"Burbank, California"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6573,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8936
|
Walter Whitman was part of the transition between a philosophical movement that developed in the late 1820s and 1830s in New England and realism.
|
{
"evidence": [
"Walt Whitman",
"Transcendentalism"
],
"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:\nWalter Whitman was part of the transition between a philosophical movement that developed in the late 1820s and 1830s in New England and realism.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Walt Whitman",
"Transcendentalism"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6574,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6478
|
Frederick Trump traveled to the Yukon Territory and made his fortune by operating a restaurant and a brothel for miners during the migration of an estimated 100,000 prospectors to the region of the Yukon Territory in northwestern Canada.
|
{
"evidence": [
"Frederick Trump",
"Klondike Gold Rush",
"Klondike, Yukon"
],
"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:\nFrederick Trump traveled to the Yukon Territory and made his fortune by operating a restaurant and a brothel for miners during the migration of an estimated 100,000 prospectors to the region of the Yukon Territory in northwestern Canada.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Frederick Trump",
"Klondike Gold Rush",
"Klondike, Yukon"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6575,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
70745
|
One of former American SharpTone Records artists who are no longer signed with the company is metal-core band Attila from Georgia, whose most successful album, About That Life, was produced by Joey Sturgis, in 2013 (before their time with Sharptone) and debuted on the Billboard 200 chart at number 22.
|
{
"evidence": [
"Attila (metalcore band)_sentence_3",
"Attila (metalcore band)_sentence_0",
"Attila (metalcore band)_sentence_64",
"Attila (metalcore band)_sentence_73"
],
"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:\nOne of former American SharpTone Records artists who are no longer signed with the company is metal-core band Attila from Georgia, whose most successful album, About That Life, was produced by Joey Sturgis, in 2013 (before their time with Sharptone) and debuted on the Billboard 200 chart at number 22.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Attila (metalcore band)_sentence_3",
"Attila (metalcore band)_sentence_0",
"Attila (metalcore band)_sentence_64",
"Attila (metalcore band)_sentence_73"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6576,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.497",
"value": "?search="
},
{
"operation": "search",
"time": "11.991",
"value": "Attila"
},
{
"operation": "Now on",
"time": "14.227",
"value": "Attila"
},
{
"operation": "hyperlink",
"time": "75.716",
"value": "Atilla (disambiguation)"
},
{
"operation": "Now on",
"time": "76.707",
"value": "Atilla (disambiguation)"
},
{
"operation": "search",
"time": "91.485",
"value": "Atilla band"
},
{
"operation": "Now on",
"time": "93.386",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "94.915",
"value": "Attila (metalcore band)"
},
{
"operation": "Now on",
"time": "100.477",
"value": "Attila (metalcore band)"
},
{
"operation": "Highlighting",
"time": "102.421",
"value": "Attila (metalcore band)_sentence_3"
},
{
"operation": "search",
"time": "128.057",
"value": "American Sharptone Records"
},
{
"operation": "Now on",
"time": "134.994",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "138.955",
"value": "SharpTone Records"
},
{
"operation": "Now on",
"time": "140.139",
"value": "SharpTone Records"
},
{
"operation": "Page search",
"time": "152.303",
"value": "Atilla"
},
{
"operation": "hyperlink",
"time": "183.202",
"value": "Attila"
},
{
"operation": "Now on",
"time": "183.947",
"value": "Attila (metalcore band)"
},
{
"operation": "Highlighting",
"time": "209.379",
"value": "Attila (metalcore band)_sentence_0"
},
{
"operation": "Page search",
"time": "236.301",
"value": "Sharptone"
},
{
"operation": "Highlighting",
"time": "242.914",
"value": "Attila (metalcore band)_sentence_64"
},
{
"operation": "Highlighting",
"time": "251.33",
"value": "Attila (metalcore band)_sentence_73"
},
{
"operation": "finish",
"time": "267.985",
"value": "finish"
}
]
}
|
exfever_8792
|
Precious also was considered for the BAFTA awards in several categories.
|
{
"evidence": [
"Precious (film)",
"Gabourey Sidibe"
],
"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:\nPrecious also was considered for the BAFTA awards in several categories.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Precious (film)",
"Gabourey Sidibe"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6577,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3528
|
Odin came from an old Scandinavian mythology which is the body of a folklore genre consisting of narratives that play.
|
{
"evidence": [
"Odin",
"Norse mythology",
"Mythology"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nOdin came from an old Scandinavian mythology which is the body of a folklore genre consisting of narratives that play.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Odin",
"Norse mythology",
"Mythology"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6578,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
47389
|
Zuo Shusheng is an internationally-known Chinese soccer player who spent both his playing and coaching career working with Tianjin Teda FC, which is based in Tianjin at the Olympic Center Stadium.
|
{
"evidence": [
"Zuo Shusheng_sentence_1",
"Zuo Shusheng_sentence_2",
"Zuo Shusheng_sentence_3",
"Tianjin TEDA F.C._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:\nZuo Shusheng is an internationally-known Chinese soccer player who spent both his playing and coaching career working with Tianjin Teda FC, which is based in Tianjin at the Olympic Center Stadium.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Zuo Shusheng_sentence_1",
"Zuo Shusheng_sentence_2",
"Zuo Shusheng_sentence_3",
"Tianjin TEDA F.C._sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6579,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.706",
"value": "?search="
},
{
"operation": "search",
"time": "8.326",
"value": "Zuo Shusheng"
},
{
"operation": "Now on",
"time": "9.053",
"value": "Zuo Shusheng"
},
{
"operation": "Highlighting",
"time": "13.228",
"value": "Zuo Shusheng_sentence_1"
},
{
"operation": "Highlighting",
"time": "23.999",
"value": "Zuo Shusheng_sentence_2"
},
{
"operation": "Highlighting",
"time": "25.194",
"value": "Zuo Shusheng_sentence_3"
},
{
"operation": "hyperlink",
"time": "42.651",
"value": "Tianjin Teda F.C."
},
{
"operation": "Now on",
"time": "44.853",
"value": "Tianjin TEDA F.C."
},
{
"operation": "Highlighting",
"time": "50.822",
"value": "Tianjin TEDA F.C._sentence_1"
},
{
"operation": "finish",
"time": "59.775",
"value": "finish"
}
]
}
|
77889
|
Hessie Donahue declined to spar with Sullivan Stapleton in a vaudeville act until the curtain came down.
|
{
"evidence": [
"Hessie Donahue_sentence_3",
"Hessie Donahue_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:\nHessie Donahue declined to spar with Sullivan Stapleton in a vaudeville act until the curtain came down.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Hessie Donahue_sentence_3",
"Hessie Donahue_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6580,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.806",
"value": "undefined"
},
{
"operation": "search",
"time": "11.395",
"value": "Hessie Donahue"
},
{
"operation": "Now on",
"time": "12.215",
"value": "Hessie Donahue"
},
{
"operation": "Page search",
"time": "23.16",
"value": "sullivan"
},
{
"operation": "Page search",
"time": "31.551",
"value": "sullivan staple"
},
{
"operation": "Highlighting",
"time": "45.328",
"value": "Hessie Donahue_sentence_3"
},
{
"operation": "Highlighting",
"time": "55.329",
"value": "Hessie Donahue_sentence_0"
},
{
"operation": "finish",
"time": "182.276",
"value": "finish"
}
]
}
|
50466
|
Oomalama is the debut album released on 29 September 1992 under Atlantic Records by Scottish pop rock band Eugenius which received a B+ rating from Entertainment Weekly.
|
{
"evidence": [
"Oomalama_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:\nOomalama is the debut album released on 29 September 1992 under Atlantic Records by Scottish pop rock band Eugenius which received a B+ rating from Entertainment Weekly.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Oomalama_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6581,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.384",
"value": "?search="
},
{
"operation": "search",
"time": "154.6",
"value": "Oomalama"
},
{
"operation": "Now on",
"time": "219.599",
"value": "?search="
},
{
"operation": "search",
"time": "224.93",
"value": "Oomalama"
},
{
"operation": "Now on",
"time": "226.274",
"value": "Oomalama"
},
{
"operation": "Highlighting",
"time": "552.047",
"value": "Oomalama_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "675.512",
"value": "Oomalama_sentence_0"
},
{
"operation": "Highlighting",
"time": "730.388",
"value": "Oomalama_sentence_0"
},
{
"operation": "finish",
"time": "832.481",
"value": "finish"
}
]
}
|
exfever_3832
|
The United States Naval Academy is a federal service academy in Annapolis, located in a state in the Mid-Atlantic region of the United States.
|
{
"evidence": [
"United States Naval Academy",
"Maryland"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe United States Naval Academy is a federal service academy in Annapolis, located in a state in the Mid-Atlantic region of the United States.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"United States Naval Academy",
"Maryland"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 6582,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1949
|
Heather Joan Graham won the Best Supporting Actress Award in the film Six Degrees of Separation.
|
{
"evidence": [
"Heather Graham",
"License to Drive",
"Neil Tolkin"
],
"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:\nHeather Joan Graham won the Best Supporting Actress Award in the film Six Degrees of Separation.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Heather Graham",
"License to Drive",
"Neil Tolkin"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 6583,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.