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_7971
|
The Formula is an award-winning film.
|
{
"evidence": [
"The Formula (1980 film)",
"G. D. Spradlin",
"George C. Scott"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Formula is an award-winning film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Formula (1980 film)",
"G. D. Spradlin",
"George C. Scott"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7384,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3278
|
Rupert Wyatt is the youngest director who made a blockbuster film in 2011.
|
{
"evidence": [
"Rupert Wyatt",
"Sundance Film Festival"
],
"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:\nRupert Wyatt is the youngest director who made a blockbuster film in 2011.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Rupert Wyatt",
"Sundance Film Festival"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7385,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8161
|
The Odyssey is one of two major ancient Greek epic poems attributed to an ancient Roman author.
|
{
"evidence": [
"Odyssey",
"Homer"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Odyssey is one of two major ancient Greek epic poems attributed to an ancient Roman author.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Odyssey",
"Homer"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7386,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
11550
|
The squadron was activated at Shaw Air Force Base, South Carolina; then was awarded an Air Force Outstanding Unit Award in 1962.
|
{
"evidence": [
"43rd Intelligence Squadron_sentence_12",
"43rd Intelligence Squadron_sentence_13"
],
"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 squadron was activated at Shaw Air Force Base, South Carolina; then was awarded an Air Force Outstanding Unit Award in 1962.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"43rd Intelligence Squadron_sentence_12",
"43rd Intelligence Squadron_sentence_13"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7387,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.504",
"value": "?search="
},
{
"operation": "search",
"time": "18.714",
"value": "Air Force Outstanding Unit Award in 1962"
},
{
"operation": "Now on",
"time": "21.015",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "25.216",
"value": "43rd Intelligence Squadron"
},
{
"operation": "Now on",
"time": "25.965",
"value": "43rd Intelligence Squadron"
},
{
"operation": "Page search",
"time": "39.833",
"value": "Air Force Outstanding Unit Award in 1962"
},
{
"operation": "Highlighting",
"time": "44.153",
"value": "43rd Intelligence Squadron_sentence_13"
},
{
"operation": "Page search",
"time": "57.257",
"value": "shaw"
},
{
"operation": "Highlighting",
"time": "63.869",
"value": "43rd Intelligence Squadron_sentence_12"
},
{
"operation": "Highlighting deleted",
"time": "68.443",
"value": "43rd Intelligence Squadron_sentence_12"
},
{
"operation": "Highlighting",
"time": "69.001",
"value": "43rd Intelligence Squadron_sentence_12"
},
{
"operation": "Highlighting deleted",
"time": "69.681",
"value": "43rd Intelligence Squadron_sentence_13"
},
{
"operation": "Highlighting deleted",
"time": "70.243",
"value": "43rd Intelligence Squadron_sentence_12"
},
{
"operation": "Highlighting",
"time": "70.943",
"value": "43rd Intelligence Squadron_sentence_12"
},
{
"operation": "Highlighting",
"time": "71.561",
"value": "43rd Intelligence Squadron_sentence_13"
},
{
"operation": "finish",
"time": "96.814",
"value": "finish"
}
]
}
|
exfever_2042
|
Sherrybaby is an American drama film screened at the annual film festival organized by the non-profit organization founded by Robert Redford committed to the growth of independent artists.
|
{
"evidence": [
"Sherrybaby",
"Sundance Film Festival",
"Sundance Institute"
],
"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:\nSherrybaby is an American drama film screened at the annual film festival organized by the non-profit organization founded by Robert Redford committed to the growth of independent artists.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Sherrybaby",
"Sundance Film Festival",
"Sundance Institute"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7388,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6559
|
Victor-Marie Hugo was a French poet who was renowned for his poetry collections, such as a collection of poetry that was published in 1856.
|
{
"evidence": [
"Victor Hugo",
"Les Contemplations"
],
"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:\nVictor-Marie Hugo was a French poet who was renowned for his poetry collections, such as a collection of poetry that was published in 1856.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Victor Hugo",
"Les Contemplations"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7389,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_608
|
Doctor Who is an Asian science-fiction television program that depicts the adventures of a Time Lord called the Doctor, who explore the universe using a spacecraft that can travel through time.
|
{
"evidence": [
"Doctor Who",
"TARDIS"
],
"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:\nDoctor Who is an Asian science-fiction television program that depicts the adventures of a Time Lord called the Doctor, who explore the universe using a spacecraft that can travel through time.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Doctor Who",
"TARDIS"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7390,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2982
|
Matt Smith is best known as the eleventh incarnation of the Doctor in the Doctor Who series on the national broadcaster of the United Kingdom.
|
{
"evidence": [
"Matt Smith (actor)",
"BBC"
],
"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:\nMatt Smith is best known as the eleventh incarnation of the Doctor in the Doctor Who series on the national broadcaster of the United Kingdom.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Matt Smith (actor)",
"BBC"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7391,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3127
|
Justin Drew Bieber is a British singer who regained recognition with the release of his debut seven-track EP that was released on November 17, 2009, by Island, RBMG, and Schoolboy Records.
|
{
"evidence": [
"Justin Bieber",
"My World (EP)"
],
"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:\nJustin Drew Bieber is a British singer who regained recognition with the release of his debut seven-track EP that was released on November 17, 2009, by Island, RBMG, and Schoolboy Records.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Justin Bieber",
"My World (EP)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7392,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
13597
|
The roots of the HCSB can be traced to 1984 when Arthur Farstad began a new translation project, then in 1998, Farstad and LifeWay Christian Resources, which publishes the Christian Standard Bible as well as Christian books and commentaries through B&H Publishing, came to an agreement that would allow LifeWay to fund and publish the completed work.
|
{
"evidence": [
"Holman Christian Standard Bible_sentence_3",
"Holman Christian Standard Bible_sentence_4",
"LifeWay Christian Resources_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 roots of the HCSB can be traced to 1984 when Arthur Farstad began a new translation project, then in 1998, Farstad and LifeWay Christian Resources, which publishes the Christian Standard Bible as well as Christian books and commentaries through B&H Publishing, came to an agreement that would allow LifeWay to fund and publish the completed work.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Holman Christian Standard Bible_sentence_3",
"Holman Christian Standard Bible_sentence_4",
"LifeWay Christian Resources_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7393,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.072",
"value": "?search="
},
{
"operation": "search",
"time": "19",
"value": "Contains...The roots of the HCSB can be traced to 1984 when Arthur Farstad began a new translation project"
},
{
"operation": "Now on",
"time": "20.083",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "97.096",
"value": "Translation philosophy Holman Christian Standard Bible_section_1"
},
{
"operation": "Now on",
"time": "98.186",
"value": "Holman Christian Standard Bible#Translation philosophy Holman Christian Standard Bible section 1"
},
{
"operation": "Page search",
"time": "107.021",
"value": "The roots of the HCSB can be traced to 1984 when Arthur Farstad began a new translation project"
},
{
"operation": "Page search",
"time": "142.223",
"value": "1984"
},
{
"operation": "Highlighting",
"time": "147.93",
"value": "Holman Christian Standard Bible_sentence_3"
},
{
"operation": "Highlighting",
"time": "153.248",
"value": "Holman Christian Standard Bible_sentence_4"
},
{
"operation": "hyperlink",
"time": "168.792",
"value": "LifeWay Christian Resources"
},
{
"operation": "Now on",
"time": "169.861",
"value": "LifeWay Christian Resources"
},
{
"operation": "Page search",
"time": "184.43",
"value": "Christian Standard Bible"
},
{
"operation": "Highlighting",
"time": "186.374",
"value": "LifeWay Christian Resources_sentence_3"
},
{
"operation": "back-button-clicked",
"time": "188.085",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "188.36",
"value": "Holman Christian Standard Bible#Translation philosophy Holman Christian Standard Bible section 1"
},
{
"operation": "hyperlink",
"time": "192.813",
"value": "LifeWay Christian Resources"
},
{
"operation": "Now on",
"time": "193.446",
"value": "LifeWay Christian Resources"
},
{
"operation": "back-button-clicked",
"time": "196.204",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "196.429",
"value": "Holman Christian Standard Bible#Translation philosophy Holman Christian Standard Bible section 1"
},
{
"operation": "finish",
"time": "206.462",
"value": "finish"
}
]
}
|
exfever_685
|
Nick Cannon acted in a 2005 American comedy-drama film written by Norman Vance Jr.
|
{
"evidence": [
"Nick Cannon",
"Roll Bounce"
],
"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:\nNick Cannon acted in a 2005 American comedy-drama film written by Norman Vance Jr.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Nick Cannon",
"Roll Bounce"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7394,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6670
|
The Lion King is an Australian animated musical drama film released by an American film production studio in which animated films produced by an American animation studio that creates animated features and short films for The Walt Disney Company are also released under the studio banner.?
|
{
"evidence": [
"The Lion King",
"Walt Disney Pictures",
"Walt Disney Animation Studios"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Lion King is an Australian animated musical drama film released by an American film production studio in which animated films produced by an American animation studio that creates animated features and short films for The Walt Disney Company are also released under the studio banner.?\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Lion King",
"Walt Disney Pictures",
"Walt Disney Animation Studios"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7395,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8697
|
Maharaja Sir Duleep Singh was the last Maharaja of the Sikh Empire and the son of the first Maharaja of the Sikh Empire, which ruled the northwest Indian subcontinent in the early half of the 16th century.
|
{
"evidence": [
"Duleep Singh",
"Ranjit Singh"
],
"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:\nMaharaja Sir Duleep Singh was the last Maharaja of the Sikh Empire and the son of the first Maharaja of the Sikh Empire, which ruled the northwest Indian subcontinent in the early half of the 16th century.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Duleep Singh",
"Ranjit Singh"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7396,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5410
|
Mrs Henderson Presents is a 2001 biographical musical film written by American dramatist and screenwriter best known for his 20 stage plays, which have been produced in over 60 countries.
|
{
"evidence": [
"Mrs Henderson Presents",
"Martin Sherman"
],
"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:\nMrs Henderson Presents is a 2001 biographical musical film written by American dramatist and screenwriter best known for his 20 stage plays, which have been produced in over 60 countries.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Mrs Henderson Presents",
"Martin Sherman"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7397,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5095
|
The Crown is a historical drama television series about the reign of Queen Elizabeth II produced by a British film and television production company.
|
{
"evidence": [
"The Crown (TV series)",
"Left Bank Pictures"
],
"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 Crown is a historical drama television series about the reign of Queen Elizabeth II produced by a British film and television production company.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Crown (TV series)",
"Left Bank Pictures"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7398,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
13297
|
Macau Computer Emergency Response Team Coordination Centre's mission is to provide a secure internet for Macau, as well as provide fee-based advice to individuals and organizations.
|
{
"evidence": [
"Macau Computer Emergency Response Team Coordination Centre_sentence_4",
"Macau Computer Emergency Response Team Coordination Centre_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:\nMacau Computer Emergency Response Team Coordination Centre's mission is to provide a secure internet for Macau, as well as provide fee-based advice to individuals and organizations.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Macau Computer Emergency Response Team Coordination Centre_sentence_4",
"Macau Computer Emergency Response Team Coordination Centre_sentence_5"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7399,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.129",
"value": "?search="
},
{
"operation": "search",
"time": "41.573",
"value": "Macau Computer Emergency Response Team Coordination Centre"
},
{
"operation": "Now on",
"time": "42.683",
"value": "Macau Computer Emergency Response Team Coordination Centre"
},
{
"operation": "Highlighting",
"time": "83.414",
"value": "Macau Computer Emergency Response Team Coordination Centre_sentence_2"
},
{
"operation": "Highlighting",
"time": "96.899",
"value": "Macau Computer Emergency Response Team Coordination Centre_sentence_4"
},
{
"operation": "Highlighting",
"time": "105.561",
"value": "Macau Computer Emergency Response Team Coordination Centre_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "114.755",
"value": "Macau Computer Emergency Response Team Coordination Centre_sentence_2"
},
{
"operation": "finish",
"time": "120.594",
"value": "finish"
}
]
}
|
exfever_19
|
Mother Mary Teresa Bojaxhiu is honored in the Catholic Church as Saint Teresa of Calcutta, with origins from an ethnic group native to the Balkan Peninsula.
|
{
"evidence": [
"Mother Teresa",
"Albanians"
],
"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:\nMother Mary Teresa Bojaxhiu is honored in the Catholic Church as Saint Teresa of Calcutta, with origins from an ethnic group native to the Balkan Peninsula.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Mother Teresa",
"Albanians"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7400,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2798
|
Tropic Thunder is a 2008 action-comedy film starring an American actor who worked with a group of young singers who frequently appeared together in teen-oriented coming-of-age films.
|
{
"evidence": [
"Tropic Thunder",
"Robert Downey Jr.",
"Brat Pack (actors)"
],
"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:\nTropic Thunder is a 2008 action-comedy film starring an American actor who worked with a group of young singers who frequently appeared together in teen-oriented coming-of-age films.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Tropic Thunder",
"Robert Downey Jr.",
"Brat Pack (actors)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7401,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3192
|
George W. Romney was an American businessman and a politician of the Grand Old Party, which was founded by abolitionists who opposed the potential expansion of enslavement that involved the enslaved person being made to perform some form of work.
|
{
"evidence": [
"George W. Romney",
"Republican Party (United States)",
"Slavery"
],
"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:\nGeorge W. Romney was an American businessman and a politician of the Grand Old Party, which was founded by abolitionists who opposed the potential expansion of enslavement that involved the enslaved person being made to perform some form of work.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"George W. Romney",
"Republican Party (United States)",
"Slavery"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7402,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_199
|
Macbeth is a 1971 fantasy film co-written by an English theatre critic who was praised by an English playwright and actor, known for his intense critical stance.
|
{
"evidence": [
"Macbeth (1971 film)",
"Kenneth Tynan",
"John Osborne"
],
"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:\nMacbeth is a 1971 fantasy film co-written by an English theatre critic who was praised by an English playwright and actor, known for his intense critical stance.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Macbeth (1971 film)",
"Kenneth Tynan",
"John Osborne"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7403,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
74784
|
Alban Towers is an apartment hotel with many features such as dog walkers, 24-hour maid service, a public dining room, a beauty shop, and a grocery store.
|
{
"evidence": [
"Alban Towers_sentence_14",
"Alban Towers_sentence_15"
],
"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:\nAlban Towers is an apartment hotel with many features such as dog walkers, 24-hour maid service, a public dining room, a beauty shop, and a grocery store.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Alban Towers_sentence_14",
"Alban Towers_sentence_15"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7404,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.171",
"value": "?search="
},
{
"operation": "search",
"time": "245.138",
"value": "Alban Towers"
},
{
"operation": "Now on",
"time": "245.927",
"value": "Alban Towers"
},
{
"operation": "Highlighting",
"time": "264.353",
"value": "Alban Towers_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "279.943",
"value": "Alban Towers_sentence_0"
},
{
"operation": "Highlighting",
"time": "481.277",
"value": "Alban Towers_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "500.661",
"value": "Alban Towers_sentence_5"
},
{
"operation": "Highlighting",
"time": "604.349",
"value": "Alban Towers_sentence_24"
},
{
"operation": "Highlighting deleted",
"time": "893.419",
"value": "Alban Towers_sentence_24"
},
{
"operation": "Highlighting",
"time": "895.499",
"value": "Alban Towers_sentence_14"
},
{
"operation": "Highlighting",
"time": "912.635",
"value": "Alban Towers_sentence_15"
},
{
"operation": "finish",
"time": "1135.995",
"value": "finish"
}
]
}
|
exfever_4657
|
Thirteen is a 2003 American teen drama film directed by an American film director, production designer, and screenwriter who is credited for a 2011 American romantic horror film.
|
{
"evidence": [
"Thirteen (2003 film)",
"Catherine Hardwicke",
"Red Riding Hood (2011 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:\nThirteen is a 2003 American teen drama film directed by an American film director, production designer, and screenwriter who is credited for a 2011 American romantic horror film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Thirteen (2003 film)",
"Catherine Hardwicke",
"Red Riding Hood (2011 film)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7405,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
47846
|
In 1922 banking operation and the ownership were separated of Casse Toscane but the bank also formed a common holding company and one of the largest share holders was Ente Cassa di Risparmio di Firenze which also owned 14% of Aeroporto di Firenze.
|
{
"evidence": [
"Banca CR Firenze_sentence_5",
"Banca CR Firenze_sentence_6"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nIn 1922 banking operation and the ownership were separated of Casse Toscane but the bank also formed a common holding company and one of the largest share holders was Ente Cassa di Risparmio di Firenze which also owned 14% of Aeroporto di Firenze.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Banca CR Firenze_sentence_5",
"Banca CR Firenze_sentence_6"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7406,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.13",
"value": "?search="
},
{
"operation": "search",
"time": "19.151",
"value": "Contains...In 1922 banking operation and the ownership were separated of Casse Toscane"
},
{
"operation": "Now on",
"time": "20.608",
"value": "undefined"
},
{
"operation": "search",
"time": "39.606",
"value": "Banca CR Firenze"
},
{
"operation": "Now on",
"time": "40.471",
"value": "Banca CR Firenze"
},
{
"operation": "Page search",
"time": "250.28",
"value": "casse toscane"
},
{
"operation": "Highlighting",
"time": "255.067",
"value": "Banca CR Firenze_sentence_6"
},
{
"operation": "Highlighting deleted",
"time": "307.883",
"value": "Banca CR Firenze_sentence_6"
},
{
"operation": "Highlighting",
"time": "308.436",
"value": "Banca CR Firenze_sentence_5"
},
{
"operation": "Highlighting",
"time": "331.488",
"value": "Banca CR Firenze_sentence_6"
},
{
"operation": "Highlighting",
"time": "335.131",
"value": "Banca CR Firenze_sentence_7"
},
{
"operation": "hyperlink",
"time": "364.889",
"value": "Ente Cassa di Risparmio di Firenze"
},
{
"operation": "Now on",
"time": "365.672",
"value": "Ente Cassa di Risparmio di Firenze"
},
{
"operation": "Highlighting",
"time": "368.412",
"value": "Ente Cassa di Risparmio di Firenze_sentence_2"
},
{
"operation": "Highlighting",
"time": "368.413",
"value": "Ente Cassa di Risparmio di Firenze_title"
},
{
"operation": "back-button-clicked",
"time": "370.159",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "370.227",
"value": "Banca CR Firenze"
},
{
"operation": "finish",
"time": "385.986",
"value": "finish"
}
]
}
|
exfever_7659
|
The Wrath of the Titans stars include an Estonian actor.
|
{
"evidence": [
"Wrath of the Titans",
"Danny Huston"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Wrath of the Titans stars include an Estonian actor.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Wrath of the Titans",
"Danny Huston"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7407,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
51425
|
The story written by Cho Jeongrae (a South Korean film director born October 15, 1973) tries to describe and reveal a few generations-lasting conflicts between the proprietors and peasants and provided further insight into the politically controversial ideological issue over the '40s in South Korea.
|
{
"evidence": [
"The Taebaek Mountains_sentence_1",
"The Taebaek Mountains_sentence_2",
"The Taebaek Mountains_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:\nThe story written by Cho Jeongrae (a South Korean film director born October 15, 1973) tries to describe and reveal a few generations-lasting conflicts between the proprietors and peasants and provided further insight into the politically controversial ideological issue over the '40s in South Korea.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"The Taebaek Mountains_sentence_1",
"The Taebaek Mountains_sentence_2",
"The Taebaek Mountains_sentence_4"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7408,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.934",
"value": "?search="
},
{
"operation": "search",
"time": "55.704",
"value": "Cho Jeongrae"
},
{
"operation": "Now on",
"time": "56.836",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "73.862",
"value": "The Taebaek Mountains"
},
{
"operation": "Now on",
"time": "74.893",
"value": "The Taebaek Mountains"
},
{
"operation": "Highlighting",
"time": "125.483",
"value": "The Taebaek Mountains_sentence_1"
},
{
"operation": "Highlighting",
"time": "139.45",
"value": "The Taebaek Mountains_sentence_2"
},
{
"operation": "Highlighting",
"time": "203.175",
"value": "The Taebaek Mountains_sentence_4"
},
{
"operation": "Highlighting",
"time": "222.413",
"value": "The Taebaek Mountains_header_cell_0_7_0"
},
{
"operation": "Highlighting",
"time": "225.944",
"value": "The Taebaek Mountains_cell_0_7_1"
},
{
"operation": "Highlighting",
"time": "225.968",
"value": "The Taebaek Mountains_header_cell_0_7_0"
},
{
"operation": "Highlighting",
"time": "225.968",
"value": "The Taebaek Mountains_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "229.331",
"value": "The Taebaek Mountains_cell_0_7_1"
},
{
"operation": "Highlighting deleted",
"time": "229.34",
"value": "The Taebaek Mountains_header_cell_0_7_0"
},
{
"operation": "Highlighting deleted",
"time": "229.342",
"value": "The Taebaek Mountains_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "232.17",
"value": "The Taebaek Mountains_cell_0_7_1"
},
{
"operation": "Highlighting",
"time": "232.181",
"value": "The Taebaek Mountains_header_cell_0_7_0"
},
{
"operation": "Highlighting",
"time": "232.181",
"value": "The Taebaek Mountains_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "240.999",
"value": "The Taebaek Mountains_cell_0_7_1"
},
{
"operation": "Highlighting deleted",
"time": "241.016",
"value": "The Taebaek Mountains_header_cell_0_7_0"
},
{
"operation": "Highlighting deleted",
"time": "241.018",
"value": "The Taebaek Mountains_header_cell_0_0_0"
},
{
"operation": "search",
"time": "469.256",
"value": "Cho Jeongrae"
},
{
"operation": "Now on",
"time": "470.473",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "491.715",
"value": "cho jeong jae"
},
{
"operation": "Now on",
"time": "493.454",
"value": "undefined"
},
{
"operation": "search",
"time": "529.743",
"value": "Cho Jeong-rae"
},
{
"operation": "Now on",
"time": "530.797",
"value": "undefined"
},
{
"operation": "search",
"time": "741.159",
"value": "Cho Jeong-rae"
},
{
"operation": "Now on",
"time": "741.913",
"value": "undefined"
},
{
"operation": "finish",
"time": "777.391",
"value": "finish"
}
]
}
|
86531
|
Adler offered a three-speed gearbox bicycle in the 1930s, attempts to develop gearbox bicycles was for downhill racing but Pinion never launched their gear system.
|
{
"evidence": [
"Gearbox bicycle_sentence_7"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAdler offered a three-speed gearbox bicycle in the 1930s, attempts to develop gearbox bicycles was for downhill racing but Pinion never launched their gear system.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Gearbox bicycle_sentence_7"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7409,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.872",
"value": "?search="
},
{
"operation": "search",
"time": "50.629",
"value": "attempts to develop gearbox bicycles was for downhill racing"
},
{
"operation": "Now on",
"time": "52.094",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "53.498",
"value": "Gearbox bicycle"
},
{
"operation": "Now on",
"time": "54.073",
"value": "Gearbox bicycle"
},
{
"operation": "Page search",
"time": "63.044",
"value": "ADLER"
},
{
"operation": "Highlighting",
"time": "65.778",
"value": "Gearbox bicycle_sentence_4"
},
{
"operation": "Highlighting",
"time": "67.413",
"value": "Gearbox bicycle_sentence_5"
},
{
"operation": "Highlighting",
"time": "83.754",
"value": "Gearbox bicycle_sentence_7"
},
{
"operation": "Highlighting deleted",
"time": "84.895",
"value": "Gearbox bicycle_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "85.345",
"value": "Gearbox bicycle_sentence_5"
},
{
"operation": "finish",
"time": "90.568",
"value": "finish"
}
]
}
|
92131
|
Glenn Braica went to St. Agnes High School where he met Norm Roberts and became great friends.
|
{
"evidence": [
"Glenn Braica_sentence_7"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nGlenn Braica went to St. Agnes High School where he met Norm Roberts and became great friends.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Glenn Braica_sentence_7"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7410,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.778",
"value": "?search="
},
{
"operation": "search",
"time": "13.369",
"value": "Contains...glenna braica"
},
{
"operation": "Now on",
"time": "14.114",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "16.824",
"value": "glenea branca"
},
{
"operation": "Now on",
"time": "17.45",
"value": "undefined"
},
{
"operation": "search",
"time": "28.122",
"value": "Norm Roberts"
},
{
"operation": "Now on",
"time": "28.732",
"value": "Norm Roberts"
},
{
"operation": "Page search",
"time": "34.713",
"value": "agnes"
},
{
"operation": "search",
"time": "50.175",
"value": "glenn braica agnes"
},
{
"operation": "Now on",
"time": "50.838",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "52.528",
"value": "Glenn Braica"
},
{
"operation": "Now on",
"time": "53.007",
"value": "Glenn Braica"
},
{
"operation": "Highlighting",
"time": "59.185",
"value": "Glenn Braica_sentence_5"
},
{
"operation": "Highlighting",
"time": "62.094",
"value": "Glenn Braica_sentence_7"
},
{
"operation": "Highlighting deleted",
"time": "63.191",
"value": "Glenn Braica_sentence_5"
},
{
"operation": "Highlighting",
"time": "245.365",
"value": "Glenn Braica_sentence_0Glenn Braica_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "245.884",
"value": "Glenn Braica_sentence_0Glenn Braica_sentence_1"
},
{
"operation": "finish",
"time": "380.961",
"value": "finish"
}
]
}
|
14454
|
French-trained Violette Verdy joined the ballet company New York City Ballet under choreographer George Balanchine.
|
{
"evidence": [
"Violette Verdy_sentence_0",
"Violette Verdy_sentence_20",
"Violette Verdy_sentence_21"
],
"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:\nFrench-trained Violette Verdy joined the ballet company New York City Ballet under choreographer George Balanchine.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Violette Verdy_sentence_0",
"Violette Verdy_sentence_20",
"Violette Verdy_sentence_21"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7411,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.184",
"value": "?search="
},
{
"operation": "search",
"time": "80.116",
"value": "violette verdy"
},
{
"operation": "Now on",
"time": "81.221",
"value": "Violette Verdy"
},
{
"operation": "Highlighting",
"time": "88.457",
"value": "Violette Verdy_sentence_0"
},
{
"operation": "Highlighting",
"time": "102.926",
"value": "Violette Verdy_sentence_20"
},
{
"operation": "Highlighting",
"time": "106.636",
"value": "Violette Verdy_sentence_21"
},
{
"operation": "finish",
"time": "113.108",
"value": "finish"
}
]
}
|
exfever_3619
|
Amsterdam is the capital and most populous city of the country located in Northwestern America with overseas territories in the Caribbean.
|
{
"evidence": [
"Amsterdam",
"Netherlands"
],
"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:\nAmsterdam is the capital and most populous city of the country located in Northwestern America with overseas territories in the Caribbean.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Amsterdam",
"Netherlands"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7412,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3212
|
Norovirus is usually spread through a particular route of transmission wherein pathogens in fecal particles pass from one person to the mouth of another person.
|
{
"evidence": [
"Norovirus",
"Fecal–oral route"
],
"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:\nNorovirus is usually spread through a particular route of transmission wherein pathogens in fecal particles pass from one person to the mouth of another person.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Norovirus",
"Fecal–oral route"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7413,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8086
|
Stardust is a 2007 romantic adventure film whose genre belongs to the genres with fantastic themes.
|
{
"evidence": [
"Stardust (2007 film)",
"Fantasy 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:\nStardust is a 2007 romantic adventure film whose genre belongs to the genres with fantastic themes.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Stardust (2007 film)",
"Fantasy film"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7414,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2885
|
Tyrion Lannister is one of a few prominent characters in the fifth and only novel in the epic fantasy series A Song of Ice and Fire which was published during the eight-season run of the HBO adaptation of an American fantasy drama television series created by David Benioff and D. B. Weiss.
|
{
"evidence": [
"Tyrion Lannister",
"A Dance with Dragons",
"Game of Thrones"
],
"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:\nTyrion Lannister is one of a few prominent characters in the fifth and only novel in the epic fantasy series A Song of Ice and Fire which was published during the eight-season run of the HBO adaptation of an American fantasy drama television series created by David Benioff and D. B. Weiss.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Tyrion Lannister",
"A Dance with Dragons",
"Game of Thrones"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7415,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
11465
|
Rachpal Singh Gill was an Indian engineer who worked on projects such as the Ranjit Sagar Dam, also known as the Thein Dam.
|
{
"evidence": [
"Rachpal Singh Gill_sentence_1",
"Ranjit Sagar Dam_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:\nRachpal Singh Gill was an Indian engineer who worked on projects such as the Ranjit Sagar Dam, also known as the Thein Dam.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Rachpal Singh Gill_sentence_1",
"Ranjit Sagar Dam_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7416,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.517",
"value": "?search="
},
{
"operation": "search",
"time": "11.217",
"value": "Rachpal Singh Gill"
},
{
"operation": "Now on",
"time": "12.085",
"value": "Rachpal Singh Gill"
},
{
"operation": "Highlighting",
"time": "22.995",
"value": "Rachpal Singh Gill_sentence_1"
},
{
"operation": "hyperlink",
"time": "26.686",
"value": "Ranjit Sagar Dam"
},
{
"operation": "Now on",
"time": "27.23",
"value": "Ranjit Sagar Dam"
},
{
"operation": "Highlighting",
"time": "29.559",
"value": "Ranjit Sagar Dam_sentence_0"
},
{
"operation": "back-button-clicked",
"time": "37.925",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "37.991",
"value": "Rachpal Singh Gill"
},
{
"operation": "finish",
"time": "60.845",
"value": "finish"
}
]
}
|
exfever_4999
|
Myles Kennedy was asked to join the band Alter Bridge by an American musician and songwriter who received a Grammy Award for a song by the band Creed.
|
{
"evidence": [
"Myles Kennedy",
"Mark Tremonti",
"With Arms Wide Open"
],
"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:\nMyles Kennedy was asked to join the band Alter Bridge by an American musician and songwriter who received a Grammy Award for a song by the band Creed.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Myles Kennedy",
"Mark Tremonti",
"With Arms Wide Open"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7417,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5618
|
Sir Richard Starkey is a French musician who occasionally sang lead vocals with the group, usually for one song on each album, including a song by the English rock band the Beatles from their seventh studio album that topped the Record Retailer chart in the UK for seven weeks and the US Billboard Top LPs list for six weeks.
|
{
"evidence": [
"Ringo Starr",
"Yellow Submarine (song)",
"Revolver (Beatles 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:\nSir Richard Starkey is a French musician who occasionally sang lead vocals with the group, usually for one song on each album, including a song by the English rock band the Beatles from their seventh studio album that topped the Record Retailer chart in the UK for seven weeks and the US Billboard Top LPs list for six weeks.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Ringo Starr",
"Yellow Submarine (song)",
"Revolver (Beatles album)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7418,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
18666
|
Ayla Aksu is a Turkish-American tennis player who first represented Turkey in 2010 and has a career high WTA doubles ranking of 199.
|
{
"evidence": [
"Ayla Aksu_sentence_0",
"Ayla Aksu_sentence_1",
"Ayla Aksu_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:\nAyla Aksu is a Turkish-American tennis player who first represented Turkey in 2010 and has a career high WTA doubles ranking of 199.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Ayla Aksu_sentence_0",
"Ayla Aksu_sentence_1",
"Ayla Aksu_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7419,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.232",
"value": "?search="
},
{
"operation": "search",
"time": "12.004",
"value": "Ayla Aksu"
},
{
"operation": "Now on",
"time": "13.372",
"value": "Ayla Aksu"
},
{
"operation": "Highlighting",
"time": "17.972",
"value": "Ayla Aksu_sentence_0"
},
{
"operation": "Highlighting",
"time": "29.459",
"value": "Ayla Aksu_sentence_1"
},
{
"operation": "Highlighting",
"time": "50.895",
"value": "Ayla Aksu_sentence_3"
},
{
"operation": "finish",
"time": "91.278",
"value": "finish"
}
]
}
|
77141
|
Carl Frederik Bricka, son of a carpenter, was born in Copenhagen, Denmark.
|
{
"evidence": [
"Carl Frederik Bricka_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:\nCarl Frederik Bricka, son of a carpenter, was born in Copenhagen, Denmark.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Carl Frederik Bricka_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7420,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.727",
"value": "?search="
},
{
"operation": "search",
"time": "14.208",
"value": "Carl Frederik Bricka"
},
{
"operation": "Now on",
"time": "15.786",
"value": "Carl Frederik Bricka"
},
{
"operation": "Highlighting",
"time": "20.225",
"value": "Carl Frederik Bricka_sentence_2"
},
{
"operation": "finish",
"time": "108.368",
"value": "finish"
}
]
}
|
exfever_4999
|
Myles Kennedy was asked to join the band Alter Bridge by an American musician and songwriter who received a Grammy Award for a song by the band Creed.
|
{
"evidence": [
"Myles Kennedy",
"Mark Tremonti",
"With Arms Wide Open"
],
"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:\nMyles Kennedy was asked to join the band Alter Bridge by an American musician and songwriter who received a Grammy Award for a song by the band Creed.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Myles Kennedy",
"Mark Tremonti",
"With Arms Wide Open"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7421,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
31876
|
Tokyo Metropolitan University was relocated to 1-1-1 Minami-Osawa, Hachioji in 1991 and the university would not sign the student exchange agreement with University of Vienna in 1997.
|
{
"evidence": [
"Tokyo Metropolitan University_sentence_12"
],
"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:\nTokyo Metropolitan University was relocated to 1-1-1 Minami-Osawa, Hachioji in 1991 and the university would not sign the student exchange agreement with University of Vienna in 1997.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Tokyo Metropolitan University_sentence_12"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7422,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.774",
"value": "?search="
},
{
"operation": "search",
"time": "21.568",
"value": "Tokyo Metropolitan University"
},
{
"operation": "Now on",
"time": "22.553",
"value": "Tokyo Metropolitan University"
},
{
"operation": "Highlighting",
"time": "53.514",
"value": "Tokyo Metropolitan University_sentence_12"
},
{
"operation": "finish",
"time": "225.546",
"value": "finish"
}
]
}
|
exfever_2488
|
Sarrainodu is a 2017 Indian Telugu-language action film written and directed by Boyapati Srinu and produced by Geetha Arts, which is owned by an Indian film producer and distributor in Telugu cinema.
|
{
"evidence": [
"Sarrainodu",
"Allu Aravind"
],
"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:\nSarrainodu is a 2017 Indian Telugu-language action film written and directed by Boyapati Srinu and produced by Geetha Arts, which is owned by an Indian film producer and distributor in Telugu cinema.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Sarrainodu",
"Allu Aravind"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7423,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_655
|
Gorillaz won the Grammy Award for Best Alternative Music Album for their album, Humanz.
|
{
"evidence": [
"Humanz",
"Grace Jones",
"Lorde"
],
"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:\nGorillaz won the Grammy Award for Best Alternative Music Album for their album, Humanz.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Humanz",
"Grace Jones",
"Lorde"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7424,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
86443
|
On February 19, 1981, Gore accosted Ying Ling and brandished his auxiliary police badge to lure the teenager into his truck, after which he drove her to her own home, then once there, he encountered Taiwanese native Hsiang Ling and kidnapped both women.
|
{
"evidence": [
"David Alan Gore_sentence_21",
"David Alan Gore_sentence_22"
],
"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:\nOn February 19, 1981, Gore accosted Ying Ling and brandished his auxiliary police badge to lure the teenager into his truck, after which he drove her to her own home, then once there, he encountered Taiwanese native Hsiang Ling and kidnapped both women.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"David Alan Gore_sentence_21",
"David Alan Gore_sentence_22"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7425,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.22",
"value": "?search="
},
{
"operation": "search",
"time": "20.348",
"value": "ying ling"
},
{
"operation": "Now on",
"time": "22.756",
"value": "undefined"
},
{
"operation": "search",
"time": "48.096",
"value": "hsiang ling"
},
{
"operation": "Now on",
"time": "49.124",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "60.605",
"value": "David Alan Gore"
},
{
"operation": "Now on",
"time": "61.383",
"value": "David Alan Gore"
},
{
"operation": "hyperlink",
"time": "75.521",
"value": "2.1 Hsiang Huang Ling and Ying Hua Ling David Alan Gore_section_2"
},
{
"operation": "Highlighting",
"time": "86.199",
"value": "David Alan Gore_sentence_21"
},
{
"operation": "Highlighting",
"time": "97.865",
"value": "David Alan Gore_sentence_22"
},
{
"operation": "finish",
"time": "497.336",
"value": "finish"
}
]
}
|
48137
|
In July 1857, John Paul Somers (1791–1862) stood as a Liberal candidate but was defeated by the opposing Liberal Matthew Sadleir and Somers was finally returned to Parliament at the 1865 general election.
|
{
"evidence": [
"John Patrick Somers_sentence_6",
"John Patrick Somers_sentence_8"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nIn July 1857, John Paul Somers (1791–1862) stood as a Liberal candidate but was defeated by the opposing Liberal Matthew Sadleir and Somers was finally returned to Parliament at the 1865 general election.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"John Patrick Somers_sentence_6",
"John Patrick Somers_sentence_8"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7426,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.749",
"value": "?search="
},
{
"operation": "search",
"time": "13.502",
"value": "John Paul Somers"
},
{
"operation": "Now on",
"time": "15.716",
"value": "undefined"
},
{
"operation": "search",
"time": "186.669",
"value": "865 general election"
},
{
"operation": "Now on",
"time": "188.638",
"value": "undefined"
},
{
"operation": "search",
"time": "192.676",
"value": "1865 general election"
},
{
"operation": "Now on",
"time": "193.165",
"value": "List of elections in 1865"
},
{
"operation": "hyperlink",
"time": "205.715",
"value": "1865 United Kingdom general election"
},
{
"operation": "Now on",
"time": "206.386",
"value": "1865 United Kingdom general election"
},
{
"operation": "search",
"time": "255.469",
"value": "1857 parliament general election"
},
{
"operation": "Now on",
"time": "256.579",
"value": "undefined"
},
{
"operation": "search",
"time": "278.845",
"value": "1857 general election (UK)"
},
{
"operation": "Now on",
"time": "279.609",
"value": "1857 United Kingdom general election"
},
{
"operation": "search",
"time": "309.452",
"value": "John Paul Somers"
},
{
"operation": "Now on",
"time": "310.015",
"value": "undefined"
},
{
"operation": "search",
"time": "463.439",
"value": "Matthew Sadleir"
},
{
"operation": "Now on",
"time": "464.853",
"value": "undefined"
},
{
"operation": "search",
"time": "521.213",
"value": "John Paul Somers (1791–1862) stood as a Liberal candidate"
},
{
"operation": "Now on",
"time": "524.335",
"value": "undefined"
},
{
"operation": "search",
"time": "539.593",
"value": "Somers was finally returned to Parliament"
},
{
"operation": "Now on",
"time": "541.488",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "545.222",
"value": "John Patrick Somers"
},
{
"operation": "Now on",
"time": "545.543",
"value": "John Patrick Somers"
},
{
"operation": "Page search",
"time": "548.304",
"value": "Somers was finally returned to Parliament"
},
{
"operation": "Highlighting",
"time": "568.138",
"value": "John Patrick Somers_sentence_6"
},
{
"operation": "Highlighting",
"time": "580.515",
"value": "John Patrick Somers_sentence_8"
},
{
"operation": "finish",
"time": "627.76",
"value": "finish"
}
]
}
|
exfever_7778
|
Paul Thomas Anderson is an Indian film director who directed There Will Be Blood, about an oil prospector during the oil production in California which began in the late 19th century.
|
{
"evidence": [
"Paul Thomas Anderson",
"History of oil in California through 1930"
],
"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:\nPaul Thomas Anderson is an Indian film director who directed There Will Be Blood, about an oil prospector during the oil production in California which began in the late 19th century.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Paul Thomas Anderson",
"History of oil in California through 1930"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7427,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2914
|
Sean John Combs is an American rapper, songwriter, record executive, and entrepreneur who is also the founder of an American record label founded in 1993.
|
{
"evidence": [
"Sean Combs",
"Bad Boy Records"
],
"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:\nSean John Combs is an American rapper, songwriter, record executive, and entrepreneur who is also the founder of an American record label founded in 1993.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Sean Combs",
"Bad Boy Records"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7428,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8660
|
That '70s Show is an Australian television period sitcom that aired on Fox, with an American actor, model, producer, and entrepreneur as one of the cast.
|
{
"evidence": [
"Point Place",
"Ashton Kutcher"
],
"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:\nThat '70s Show is an Australian television period sitcom that aired on Fox, with an American actor, model, producer, and entrepreneur as one of the cast.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Point Place",
"Ashton Kutcher"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7429,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
33999
|
Operation Buster–Jangle was a series of seven nuclear weapons tests conducted by the United States in late 1951 at the Nevada Test Site which is a United States Department of Energy reservation located in southeastern Nye County, Utah.
|
{
"evidence": [
"Nevada Test Site_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:\nOperation Buster–Jangle was a series of seven nuclear weapons tests conducted by the United States in late 1951 at the Nevada Test Site which is a United States Department of Energy reservation located in southeastern Nye County, Utah.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Nevada Test Site_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7430,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.207",
"value": "?search="
},
{
"operation": "search",
"time": "114.413",
"value": "Operation Buster–Jangle"
},
{
"operation": "Now on",
"time": "115.204",
"value": "Operation Buster–Jangle"
},
{
"operation": "Highlighting",
"time": "130.491",
"value": "Operation Buster–Jangle_sentence_0"
},
{
"operation": "Highlighting",
"time": "130.493",
"value": "Operation Buster–Jangle_title"
},
{
"operation": "hyperlink",
"time": "134.862",
"value": "Nevada Test Site"
},
{
"operation": "Now on",
"time": "135.999",
"value": "Nevada Test Site"
},
{
"operation": "Highlighting",
"time": "143.78",
"value": "Nevada Test Site_sentence_0"
},
{
"operation": "finish",
"time": "165.11",
"value": "finish"
}
]
}
|
45541
|
Bob Allison had a mediocre debut and retired the next year.
|
{
"evidence": [
"Bob Allison_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:\nBob Allison had a mediocre debut and retired the next year.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Bob Allison_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7431,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.718",
"value": "?search="
},
{
"operation": "search",
"time": "10.453",
"value": "Bob Allison"
},
{
"operation": "Now on",
"time": "11.221",
"value": "Bob Allison"
},
{
"operation": "Highlighting",
"time": "18.139",
"value": "Bob Allison_sentence_1"
},
{
"operation": "finish",
"time": "30.658",
"value": "finish"
}
]
}
|
58713
|
The 2011 Sicilia Classic held between October 3-9, was a professional tennis tournament played on clay courts which was held annually in Palermo, Italy.
|
{
"evidence": [
"2011 Sicilia Classic_sentence_2",
"2011 Sicilia Classic_sentence_0",
"Sicilia Classic_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 2011 Sicilia Classic held between October 3-9, was a professional tennis tournament played on clay courts which was held annually in Palermo, Italy.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"2011 Sicilia Classic_sentence_2",
"2011 Sicilia Classic_sentence_0",
"Sicilia Classic_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7432,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.176",
"value": "?search="
},
{
"operation": "search",
"time": "13.415",
"value": "2011 Sicilia Classic"
},
{
"operation": "Now on",
"time": "14.153",
"value": "2011 Sicilia Classic"
},
{
"operation": "Highlighting",
"time": "19.274",
"value": "2011 Sicilia Classic_sentence_2"
},
{
"operation": "Highlighting",
"time": "21.619",
"value": "2011 Sicilia Classic_sentence_0"
},
{
"operation": "hyperlink",
"time": "38.428",
"value": "Sicilia Classic"
},
{
"operation": "Now on",
"time": "39.319",
"value": "Sicilia Classic"
},
{
"operation": "Highlighting",
"time": "47.285",
"value": "Sicilia Classic_sentence_2"
},
{
"operation": "finish",
"time": "88.96",
"value": "finish"
}
]
}
|
86745
|
Great dirhombicosidodecahedron is the only non-degenerate uniform polyhedron with more than six faces meeting at a vertex, that has 124 faces, 24 edges, and 60 vertices.
|
{
"evidence": [
"Great dirhombicosidodecahedron_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:\nGreat dirhombicosidodecahedron is the only non-degenerate uniform polyhedron with more than six faces meeting at a vertex, that has 124 faces, 24 edges, and 60 vertices.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Great dirhombicosidodecahedron_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7433,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.506",
"value": "?search="
},
{
"operation": "Now on",
"time": "9.999",
"value": "?search="
},
{
"operation": "Now on",
"time": "19.385",
"value": "?search="
},
{
"operation": "search",
"time": "27.856",
"value": "Great dirhombicosidodecahedron"
},
{
"operation": "Now on",
"time": "29.674",
"value": "Great dirhombicosidodecahedron"
},
{
"operation": "search",
"time": "38.543",
"value": "non-degen"
},
{
"operation": "Now on",
"time": "39.598",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "40.611",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "40.674",
"value": "Great dirhombicosidodecahedron"
},
{
"operation": "Highlighting",
"time": "46.258",
"value": "Great dirhombicosidodecahedron_sentence_2"
},
{
"operation": "Highlighting",
"time": "84.513",
"value": "Great dirhombicosidodecahedron_sentence_1"
},
{
"operation": "Highlighting",
"time": "135.503",
"value": "Great dirhombicosidodecahedron_sentence_1"
},
{
"operation": "finish",
"time": "162.7",
"value": "finish"
}
]
}
|
exfever_2322
|
Black Widow is the second fictional character published by Marvel Comics.
|
{
"evidence": [
"Black Widow (Natasha Romanova)",
"Don Rico",
"Arthur Peddy"
],
"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:\nBlack Widow is the second fictional character published by Marvel Comics.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Black Widow (Natasha Romanova)",
"Don Rico",
"Arthur Peddy"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7434,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2534
|
The Offspring is an American rock band from a city in northern Orange County, Australia.
|
{
"evidence": [
"The Offspring",
"Garden Grove, California"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Offspring is an American rock band from a city in northern Orange County, Australia.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Offspring",
"Garden Grove, California"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7435,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
74723
|
Thendara station is served by trains heading south to Utica beginning around the month of May each year and trains continue along the 57 mile route along the Moose River in Adirondack Park.
|
{
"evidence": [
"Thendara station_sentence_1",
"Thendara station_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:\nThendara station is served by trains heading south to Utica beginning around the month of May each year and trains continue along the 57 mile route along the Moose River in Adirondack Park.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Thendara station_sentence_1",
"Thendara station_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7436,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.074",
"value": "?search="
},
{
"operation": "search",
"time": "13.603",
"value": "Thendara station"
},
{
"operation": "Now on",
"time": "14.394",
"value": "Thendara station"
},
{
"operation": "Highlighting",
"time": "25.993",
"value": "Thendara station_sentence_1"
},
{
"operation": "Highlighting",
"time": "36.615",
"value": "Thendara station_sentence_2"
},
{
"operation": "finish",
"time": "151.255",
"value": "finish"
}
]
}
|
exfever_5934
|
Selena Marie Gomez appeared in a 2010 American made-for-television comedy-drama fantasy film.
|
{
"evidence": [
"Selena Gomez",
"Wizards of Waverly Place: The Movie"
],
"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:\nSelena Marie Gomez appeared in a 2010 American made-for-television comedy-drama fantasy film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Selena Gomez",
"Wizards of Waverly Place: The Movie"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7437,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_242
|
Nat Faxon is an American actor, comedian, director, and screenwriter who starred in the epic series Married on a pay television channel.
|
{
"evidence": [
"Nat Faxon",
"FX (TV channel)"
],
"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:\nNat Faxon is an American actor, comedian, director, and screenwriter who starred in the epic series Married on a pay television channel.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Nat Faxon",
"FX (TV channel)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7438,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
29593
|
Carbon peapods whose molecules are amorphous carbon can only be artificially produced although C60 fullerene impurities are formed the fullerenes within a nanotube can be stabilized at a diameter difference of 0.34 nm or less
|
{
"evidence": [
"Carbon peapod_sentence_8"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nCarbon peapods whose molecules are amorphous carbon can only be artificially produced although C60 fullerene impurities are formed the fullerenes within a nanotube can be stabilized at a diameter difference of 0.34 nm or less\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Carbon peapod_sentence_8"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7439,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.803",
"value": "?search="
},
{
"operation": "search",
"time": "17.23",
"value": "Contains...Carbon peapods"
},
{
"operation": "Now on",
"time": "18.08",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "20.455",
"value": "Carbon peapod"
},
{
"operation": "Now on",
"time": "20.975",
"value": "Carbon peapod"
},
{
"operation": "Page search",
"time": "37.843",
"value": "molecules"
},
{
"operation": "Highlighting",
"time": "59.687",
"value": "Carbon peapod_sentence_15"
},
{
"operation": "Highlighting",
"time": "59.689",
"value": "Carbon peapod_section_2"
},
{
"operation": "Highlighting",
"time": "125.721",
"value": "Carbon peapod_sentence_26"
},
{
"operation": "Highlighting",
"time": "125.722",
"value": "Carbon peapod_section_3"
},
{
"operation": "Highlighting deleted",
"time": "130.136",
"value": "Carbon peapod_sentence_26"
},
{
"operation": "Highlighting deleted",
"time": "130.139",
"value": "Carbon peapod_section_3"
},
{
"operation": "Page search",
"time": "146.455",
"value": "fullerene impurities"
},
{
"operation": "Highlighting",
"time": "157.092",
"value": "Carbon peapod_sentence_9"
},
{
"operation": "Highlighting",
"time": "165.931",
"value": "Carbon peapod_sentence_10"
},
{
"operation": "Highlighting",
"time": "178.651",
"value": "Carbon peapod_sentence_8"
},
{
"operation": "Highlighting deleted",
"time": "184.317",
"value": "Carbon peapod_sentence_9"
},
{
"operation": "Highlighting deleted",
"time": "184.997",
"value": "Carbon peapod_sentence_10"
},
{
"operation": "Highlighting deleted",
"time": "186.857",
"value": "Carbon peapod_sentence_15"
},
{
"operation": "Highlighting deleted",
"time": "186.859",
"value": "Carbon peapod_section_2"
},
{
"operation": "finish",
"time": "199.301",
"value": "finish"
}
]
}
|
exfever_5892
|
Ronald Belford "Bon" Scott was posthumously inducted into the Rock and Roll Hall of Fame as a member of AC/DC.
|
{
"evidence": [
"Bon Scott",
"Angus, Scotland"
],
"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:\nRonald Belford \"Bon\" Scott was posthumously inducted into the Rock and Roll Hall of Fame as a member of AC/DC.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Bon Scott",
"Angus, Scotland"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7440,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
50968
|
China's Zhang Nan and Zhao Yunlei ranked 1st in the qualifying round of the mixed doubles event of the 2016 Summer Olympics which was held May 4, 2015 and May 1, 2016.
|
{
"evidence": [
"Badminton at the 2016 Summer Olympics – Qualification_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:\nChina's Zhang Nan and Zhao Yunlei ranked 1st in the qualifying round of the mixed doubles event of the 2016 Summer Olympics which was held May 4, 2015 and May 1, 2016.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Badminton at the 2016 Summer Olympics – Qualification_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7441,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.23",
"value": "?search="
},
{
"operation": "search",
"time": "21.811",
"value": "2016 Summer Olympics"
},
{
"operation": "Now on",
"time": "26.181",
"value": "2016 Summer Olympics"
},
{
"operation": "hyperlink",
"time": "55.555",
"value": "3 The Games 2016 Summer Olympics_section_11"
},
{
"operation": "search",
"time": "117.237",
"value": "China at the 2016 Summer Olympics"
},
{
"operation": "Now on",
"time": "177.002",
"value": "China at the 2016 Summer Olympics"
},
{
"operation": "hyperlink",
"time": "297.88",
"value": "Tennis at the 2016 Summer Olympics"
},
{
"operation": "Now on",
"time": "300.251",
"value": "Tennis at the 2016 Summer Olympics"
},
{
"operation": "hyperlink",
"time": "305.024",
"value": "2 Qualification Tennis at the 2016 Summer Olympics_section_1"
},
{
"operation": "hyperlink",
"time": "326.326",
"value": "Tennis at the 2016 Summer Olympics – Mixed Doubles"
},
{
"operation": "Now on",
"time": "327.523",
"value": "Tennis at the 2016 Summer Olympics – Mixed doubles"
},
{
"operation": "back-button-clicked",
"time": "354.127",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "354.198",
"value": "Tennis at the 2016 Summer Olympics#Qualification Tennis at the 2016 Summer Olympics section 1"
},
{
"operation": "hyperlink",
"time": "433.512",
"value": "Tennis at the 2016 Summer Olympics – Qualification"
},
{
"operation": "Now on",
"time": "440.166",
"value": "Tennis at the 2016 Summer Olympics – Qualification"
},
{
"operation": "search",
"time": "573.066",
"value": "insource"
},
{
"operation": "Now on",
"time": "575.547",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "583.531",
"value": "Competition format Badminton at the 2016 Summer Olympics – Mixed doubles_section_0"
},
{
"operation": "Now on",
"time": "584.879",
"value": "Badminton at the 2016 Summer Olympics – Mixed doubles#Competition format Badminton at the 2016 Summer Olympics .E2.80.93 Mixed doubles section 0"
},
{
"operation": "hyperlink",
"time": "610.581",
"value": "Badminton at the 2016 Summer Olympics"
},
{
"operation": "Now on",
"time": "612.2",
"value": "Badminton at the 2016 Summer Olympics"
},
{
"operation": "hyperlink",
"time": "638.31",
"value": "5.5 Mixed doubles Badminton at the 2016 Summer Olympics_section_13"
},
{
"operation": "hyperlink",
"time": "641.413",
"value": "Badminton at the 2016 Summer Olympics – Mixed doubles"
},
{
"operation": "Now on",
"time": "642.367",
"value": "Badminton at the 2016 Summer Olympics – Mixed doubles"
},
{
"operation": "back-button-clicked",
"time": "648.626",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "648.695",
"value": "Badminton at the 2016 Summer Olympics#Mixed doubles Badminton at the 2016 Summer Olympics section 13"
},
{
"operation": "Highlighting",
"time": "664.207",
"value": "Badminton at the 2016 Summer Olympics_sentence_6"
},
{
"operation": "Highlighting",
"time": "664.208",
"value": "Badminton at the 2016 Summer Olympics_title"
},
{
"operation": "Highlighting",
"time": "664.209",
"value": "Badminton at the 2016 Summer Olympics_section_0"
},
{
"operation": "hyperlink",
"time": "664.846",
"value": "Badminton at the 2016 Summer Olympics – Qualification"
},
{
"operation": "Now on",
"time": "667.558",
"value": "Badminton at the 2016 Summer Olympics – Qualification"
},
{
"operation": "Highlighting",
"time": "685.175",
"value": "Badminton at the 2016 Summer Olympics – Qualification_cell_5_1_2"
},
{
"operation": "Highlighting",
"time": "685.177",
"value": "Badminton at the 2016 Summer Olympics – Qualification_section_2"
},
{
"operation": "Highlighting",
"time": "685.177",
"value": "Badminton at the 2016 Summer Olympics – Qualification_section_7"
},
{
"operation": "Highlighting",
"time": "685.178",
"value": "Badminton at the 2016 Summer Olympics – Qualification_header_cell_5_0_2"
},
{
"operation": "Highlighting deleted",
"time": "687.679",
"value": "Badminton at the 2016 Summer Olympics – Qualification_cell_5_1_2"
},
{
"operation": "Highlighting deleted",
"time": "687.686",
"value": "Badminton at the 2016 Summer Olympics – Qualification_section_2"
},
{
"operation": "Highlighting deleted",
"time": "687.688",
"value": "Badminton at the 2016 Summer Olympics – Qualification_section_7"
},
{
"operation": "Highlighting deleted",
"time": "687.689",
"value": "Badminton at the 2016 Summer Olympics – Qualification_header_cell_5_0_2"
},
{
"operation": "Highlighting",
"time": "693.171",
"value": "Badminton at the 2016 Summer Olympics – Qualification_cell_5_1_2"
},
{
"operation": "Highlighting",
"time": "693.174",
"value": "Badminton at the 2016 Summer Olympics – Qualification_section_2"
},
{
"operation": "Highlighting",
"time": "693.174",
"value": "Badminton at the 2016 Summer Olympics – Qualification_section_7"
},
{
"operation": "Highlighting",
"time": "693.175",
"value": "Badminton at the 2016 Summer Olympics – Qualification_header_cell_5_0_2"
},
{
"operation": "Highlighting",
"time": "694.669",
"value": "Badminton at the 2016 Summer Olympics – Qualification_cell_5_1_3"
},
{
"operation": "Highlighting deleted",
"time": "694.855",
"value": "Badminton at the 2016 Summer Olympics – Qualification_cell_5_1_3"
},
{
"operation": "Highlighting",
"time": "696.95",
"value": "Badminton at the 2016 Summer Olympics – Qualification_cell_5_1_3"
},
{
"operation": "Highlighting",
"time": "697.595",
"value": "Badminton at the 2016 Summer Olympics – Qualification_cell_5_1_4"
},
{
"operation": "Highlighting",
"time": "697.599",
"value": "Badminton at the 2016 Summer Olympics – Qualification_header_cell_5_0_4"
},
{
"operation": "Highlighting",
"time": "699.136",
"value": "Badminton at the 2016 Summer Olympics – Qualification_cell_5_1_0"
},
{
"operation": "Highlighting",
"time": "699.139",
"value": "Badminton at the 2016 Summer Olympics – Qualification_header_cell_5_0_0"
},
{
"operation": "Highlighting deleted",
"time": "700.182",
"value": "Badminton at the 2016 Summer Olympics – Qualification_cell_5_1_0"
},
{
"operation": "Highlighting deleted",
"time": "700.185",
"value": "Badminton at the 2016 Summer Olympics – Qualification_header_cell_5_0_0"
},
{
"operation": "Highlighting",
"time": "700.767",
"value": "Badminton at the 2016 Summer Olympics – Qualification_cell_5_1_1"
},
{
"operation": "Highlighting",
"time": "700.772",
"value": "Badminton at the 2016 Summer Olympics – Qualification_header_cell_5_0_1"
},
{
"operation": "Highlighting",
"time": "713.204",
"value": "Badminton at the 2016 Summer Olympics – Qualification_sentence_1"
},
{
"operation": "Highlighting",
"time": "756.43",
"value": "Badminton at the 2016 Summer Olympics – Qualification_sentence_1"
},
{
"operation": "finish",
"time": "815.462",
"value": "finish"
}
]
}
|
62786
|
The Hatchard League, originally called the Sheffield & District Alliance, was suspended for the duration of the First World War, then disbanded altogether in 1923, but was re-introduced after the Second World War.
|
{
"evidence": [
"Hatchard League_sentence_1",
"Hatchard League_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 Hatchard League, originally called the Sheffield & District Alliance, was suspended for the duration of the First World War, then disbanded altogether in 1923, but was re-introduced after the Second World War.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Hatchard League_sentence_1",
"Hatchard League_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7442,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.917",
"value": "?search="
},
{
"operation": "search",
"time": "17.92",
"value": "Hatchard LEague"
},
{
"operation": "Now on",
"time": "18.867",
"value": "Hatchard League"
},
{
"operation": "Highlighting",
"time": "87.046",
"value": "Hatchard League_sentence_1"
},
{
"operation": "Highlighting",
"time": "97.893",
"value": "Hatchard League_sentence_3"
},
{
"operation": "finish",
"time": "115.149",
"value": "finish"
}
]
}
|
49773
|
The Melbourne–Adelaide rail corridor is an 1,435 mm (4 ft 8 ⁄2 in) single track standard-gauge railway corridor that runs between Perth and Adelaide, South Australia.
|
{
"evidence": [
"Melbourne–Adelaide rail corridor_sentence_0"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Melbourne–Adelaide rail corridor is an 1,435 mm (4 ft 8 ⁄2 in) single track standard-gauge railway corridor that runs between Perth and Adelaide, South Australia.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Melbourne–Adelaide rail corridor_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7443,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.232",
"value": "?search="
},
{
"operation": "search",
"time": "20.621",
"value": "Melbourne–Adelaide rail corridor"
},
{
"operation": "Now on",
"time": "21.375",
"value": "Melbourne–Adelaide rail corridor"
},
{
"operation": "Highlighting",
"time": "30.499",
"value": "Melbourne–Adelaide rail corridor_cell_0_4_1"
},
{
"operation": "Highlighting",
"time": "30.506",
"value": "Melbourne–Adelaide rail corridor_header_cell_0_4_0"
},
{
"operation": "Highlighting",
"time": "30.506",
"value": "Melbourne–Adelaide rail corridor_header_cell_0_3_0"
},
{
"operation": "hyperlink",
"time": "47.67",
"value": "standard gauge"
},
{
"operation": "Now on",
"time": "50.331",
"value": "Standard-gauge railway"
},
{
"operation": "Page search",
"time": "59.497",
"value": "single"
},
{
"operation": "back-button-clicked",
"time": "63.751",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "63.859",
"value": "Melbourne–Adelaide rail corridor"
},
{
"operation": "Page search",
"time": "70.447",
"value": "single"
},
{
"operation": "Highlighting",
"time": "83.328",
"value": "Melbourne–Adelaide rail corridor_sentence_4"
},
{
"operation": "Highlighting",
"time": "83.33",
"value": "Melbourne–Adelaide rail corridor_section_0"
},
{
"operation": "Highlighting",
"time": "96.338",
"value": "Melbourne–Adelaide rail corridor_sentence_8"
},
{
"operation": "Highlighting",
"time": "96.34",
"value": "Melbourne–Adelaide rail corridor_section_2"
},
{
"operation": "Highlighting deleted",
"time": "97.827",
"value": "Melbourne–Adelaide rail corridor_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "97.83",
"value": "Melbourne–Adelaide rail corridor_section_0"
},
{
"operation": "Highlighting",
"time": "184.437",
"value": "Melbourne–Adelaide rail corridor_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "185.635",
"value": "Melbourne–Adelaide rail corridor_sentence_8"
},
{
"operation": "Highlighting deleted",
"time": "185.639",
"value": "Melbourne–Adelaide rail corridor_section_2"
},
{
"operation": "Highlighting deleted",
"time": "187.152",
"value": "Melbourne–Adelaide rail corridor_cell_0_4_1"
},
{
"operation": "Highlighting deleted",
"time": "187.158",
"value": "Melbourne–Adelaide rail corridor_header_cell_0_4_0"
},
{
"operation": "Highlighting deleted",
"time": "187.16",
"value": "Melbourne–Adelaide rail corridor_header_cell_0_3_0"
},
{
"operation": "finish",
"time": "196.055",
"value": "finish"
}
]
}
|
75597
|
Within the basic structure of PEPPSI, R can be a methyl, an alkyl that comes from methane.
|
{
"evidence": [
"PEPPSI_sentence_4",
"Methyl group_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:\nWithin the basic structure of PEPPSI, R can be a methyl, an alkyl that comes from methane.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"PEPPSI_sentence_4",
"Methyl group_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7444,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.105",
"value": "?search="
},
{
"operation": "search",
"time": "9.563",
"value": "PEPPSI"
},
{
"operation": "Now on",
"time": "10.273",
"value": "PEPPSI"
},
{
"operation": "Highlighting",
"time": "138.552",
"value": "PEPPSI_sentence_4"
},
{
"operation": "hyperlink",
"time": "144.533",
"value": "methyl"
},
{
"operation": "Now on",
"time": "145.472",
"value": "Methyl group"
},
{
"operation": "Highlighting",
"time": "147.814",
"value": "Methyl group_sentence_1"
},
{
"operation": "finish",
"time": "155.072",
"value": "finish"
}
]
}
|
exfever_7846
|
Shinsegae is a South Korean department store franchise with its flagship store and the world's largest department store in South Korea's fifth-most populous city with a population of over 3.4 million inhabitants.
|
{
"evidence": [
"Shinsegae",
"Busan"
],
"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:\nShinsegae is a South Korean department store franchise with its flagship store and the world's largest department store in South Korea's fifth-most populous city with a population of over 3.4 million inhabitants.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Shinsegae",
"Busan"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7445,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5869
|
The Crazies is a 2010 American science fiction horror series that starred an award-winning American actor.
|
{
"evidence": [
"The Crazies (2010 film)",
"Timothy Olyphant"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Crazies is a 2010 American science fiction horror series that starred an award-winning American actor.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Crazies (2010 film)",
"Timothy Olyphant"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7446,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
74949
|
Frances Farmer played as Melanie in Thunder Rock, a play that would later win the Peabody Award.
|
{
"evidence": [
"Frances Farmer_sentence_87"
],
"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:\nFrances Farmer played as Melanie in Thunder Rock, a play that would later win the Peabody Award.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Frances Farmer_sentence_87"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7447,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.84",
"value": "?search="
},
{
"operation": "search",
"time": "13.236",
"value": "Frances Farmer"
},
{
"operation": "Now on",
"time": "14.528",
"value": "Frances Farmer"
},
{
"operation": "Page search",
"time": "25.519",
"value": "thunder rock"
},
{
"operation": "Highlighting",
"time": "35.634",
"value": "Frances Farmer_sentence_87"
},
{
"operation": "Page search",
"time": "49.135",
"value": "peabody award"
},
{
"operation": "Page search",
"time": "86.464",
"value": "peabody"
},
{
"operation": "finish",
"time": "127.794",
"value": "finish"
}
]
}
|
61363
|
Letitia Wright won an NAACP Image Award for her work On Black Panther, a 2018 American superhero film.
|
{
"evidence": [
"Letitia Wright_sentence_21",
"Letitia Wright_sentence_19",
"Black Panther (film)_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:\nLetitia Wright won an NAACP Image Award for her work On Black Panther, a 2018 American superhero film.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Letitia Wright_sentence_21",
"Letitia Wright_sentence_19",
"Black Panther (film)_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7448,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.826",
"value": "?search="
},
{
"operation": "search",
"time": "10.599",
"value": "Letitia Wright"
},
{
"operation": "Now on",
"time": "11.578",
"value": "Letitia Wright"
},
{
"operation": "Page search",
"time": "26.741",
"value": "NAACP Image Award"
},
{
"operation": "Highlighting",
"time": "34.841",
"value": "Letitia Wright_sentence_21"
},
{
"operation": "Highlighting",
"time": "53.393",
"value": "Letitia Wright_sentence_19"
},
{
"operation": "hyperlink",
"time": "80.865",
"value": "Black Panther"
},
{
"operation": "Now on",
"time": "82.19",
"value": "Black Panther (film)"
},
{
"operation": "Highlighting",
"time": "83.705",
"value": "Black Panther (film)_sentence_2"
},
{
"operation": "finish",
"time": "91.265",
"value": "finish"
}
]
}
|
exfever_5335
|
Lewis Friedman is an American screenwriter whose credits include the 1998 drama film starring an American actor, animator, writer, producer, and composer.
|
{
"evidence": [
"Lewis Friedman",
"BASEketball",
"Matt Stone"
],
"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:\nLewis Friedman is an American screenwriter whose credits include the 1998 drama film starring an American actor, animator, writer, producer, and composer.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Lewis Friedman",
"BASEketball",
"Matt Stone"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7449,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4138
|
Louis C.K. is an American multi-talented actor who has received numerous awards, including those presented by the National Academy of Recording Arts and Sciences of the United Kingdom to "honor artistic achievement in comedy."
|
{
"evidence": [
"Louis C.K.",
"Grammy Award for Best Comedy 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:\nLouis C.K. is an American multi-talented actor who has received numerous awards, including those presented by the National Academy of Recording Arts and Sciences of the United Kingdom to \"honor artistic achievement in comedy.\"\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Louis C.K.",
"Grammy Award for Best Comedy Album"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7450,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
26528
|
Aidan Maloney was an Australian politician and executive who represented the electoral district of Ferryland in the Newfoundland and Labrador House of Assembly from 1966 to 1971 and served in cabinet as Minister of Fisheries, and as Community & Social Development.
|
{
"evidence": [
"Aidan Maloney_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:\nAidan Maloney was an Australian politician and executive who represented the electoral district of Ferryland in the Newfoundland and Labrador House of Assembly from 1966 to 1971 and served in cabinet as Minister of Fisheries, and as Community & Social Development.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Aidan Maloney_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7451,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.798",
"value": "?search="
},
{
"operation": "search",
"time": "10.924",
"value": "Aidan Maloney"
},
{
"operation": "Now on",
"time": "11.426",
"value": "Aidan Maloney"
},
{
"operation": "Highlighting",
"time": "29.493",
"value": "Aidan Maloney_sentence_0"
},
{
"operation": "finish",
"time": "35.44",
"value": "finish"
}
]
}
|
64400
|
Give a Little was released a year after it was announced by Hanson, which included Taylor Hanson, Issac Hanson, and Zac Hanson.
|
{
"evidence": [
"Give a Little_sentence_2",
"Give a Little_sentence_3"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nGive a Little was released a year after it was announced by Hanson, which included Taylor Hanson, Issac Hanson, and Zac Hanson.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Give a Little_sentence_2",
"Give a Little_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7452,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.212",
"value": "?search="
},
{
"operation": "search",
"time": "9.048",
"value": "Give a Little"
},
{
"operation": "Now on",
"time": "10.065",
"value": "Give a Little"
},
{
"operation": "Highlighting",
"time": "16.956",
"value": "Give a Little_sentence_2"
},
{
"operation": "Highlighting",
"time": "32.727",
"value": "Give a Little_sentence_3"
},
{
"operation": "finish",
"time": "54.6",
"value": "finish"
}
]
}
|
63430
|
Fearless Fosdick is a long-running parody of Dick Tracy, which first appeared in 1942 and was popular enough to have a television show in 1952; newspaper editors wanted Fosdick to star in his own movie but the creator of Dick Tracy did not find the parody funny.
|
{
"evidence": [
"Fearless Fosdick_sentence_0",
"Fearless Fosdick_sentence_2",
"Fearless Fosdick_sentence_101",
"Fearless Fosdick_sentence_78",
"Fearless Fosdick_sentence_79"
],
"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:\nFearless Fosdick is a long-running parody of Dick Tracy, which first appeared in 1942 and was popular enough to have a television show in 1952; newspaper editors wanted Fosdick to star in his own movie but the creator of Dick Tracy did not find the parody funny.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Fearless Fosdick_sentence_0",
"Fearless Fosdick_sentence_2",
"Fearless Fosdick_sentence_101",
"Fearless Fosdick_sentence_78",
"Fearless Fosdick_sentence_79"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7453,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.773",
"value": "?search="
},
{
"operation": "search",
"time": "197.515",
"value": "Fearless Fosdick"
},
{
"operation": "Now on",
"time": "203.173",
"value": "Fearless Fosdick"
},
{
"operation": "Highlighting",
"time": "213.155",
"value": "Fearless Fosdick_sentence_0"
},
{
"operation": "Highlighting",
"time": "233.085",
"value": "Fearless Fosdick_sentence_2"
},
{
"operation": "Highlighting",
"time": "412.204",
"value": "Fearless Fosdick_sentence_101"
},
{
"operation": "Page search",
"time": "892.869",
"value": "newspaper editors"
},
{
"operation": "Highlighting",
"time": "905.189",
"value": "Fearless Fosdick_sentence_80"
},
{
"operation": "Highlighting",
"time": "906.423",
"value": "Fearless Fosdick_sentence_78"
},
{
"operation": "Highlighting deleted",
"time": "907.372",
"value": "Fearless Fosdick_sentence_80"
},
{
"operation": "Highlighting",
"time": "950.928",
"value": "Fearless Fosdick_sentence_79"
},
{
"operation": "finish",
"time": "968.088",
"value": "finish"
}
]
}
|
72661
|
Naichi, a term to distinguish the area of Japan from its outlying territories during the prewar period, has an estimated population of 72,000,000.
|
{
"evidence": [
"Mainland Japan_sentence_0",
"Mainland Japan_sentence_1",
"Mainland Japan_sentence_2"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nNaichi, a term to distinguish the area of Japan from its outlying territories during the prewar period, has an estimated population of 72,000,000.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Mainland Japan_sentence_0",
"Mainland Japan_sentence_1",
"Mainland Japan_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7454,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.065",
"value": "?search="
},
{
"operation": "Now on",
"time": "8.761",
"value": "?search="
},
{
"operation": "search",
"time": "105.043",
"value": "Naichi"
},
{
"operation": "Now on",
"time": "105.888",
"value": "Naichi"
},
{
"operation": "Highlighting",
"time": "119.583",
"value": "Mainland Japan_sentence_1"
},
{
"operation": "Highlighting",
"time": "133.949",
"value": "Mainland Japan_sentence_2"
},
{
"operation": "search",
"time": "496.215",
"value": "Naichi"
},
{
"operation": "Now on",
"time": "497.288",
"value": "Naichi"
},
{
"operation": "Highlighting deleted",
"time": "526.237",
"value": "Mainland Japan_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "526.724",
"value": "Mainland Japan_sentence_1"
},
{
"operation": "Highlighting",
"time": "527.772",
"value": "Mainland Japan_sentence_0"
},
{
"operation": "Highlighting",
"time": "528.781",
"value": "Mainland Japan_sentence_1"
},
{
"operation": "Highlighting",
"time": "529.34",
"value": "Mainland Japan_sentence_2"
},
{
"operation": "finish",
"time": "1487.151",
"value": "finish"
}
]
}
|
50422
|
HNK Rijeka was founded in 1946 and a Yugoslavian defender named Višković played for them.
|
{
"evidence": [
"HNK Rijeka_sentence_0",
"HNK Rijeka_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:\nHNK Rijeka was founded in 1946 and a Yugoslavian defender named Višković played for them.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"HNK Rijeka_sentence_0",
"HNK Rijeka_sentence_4"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7455,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.107",
"value": "?search="
},
{
"operation": "search",
"time": "6.795",
"value": "HNK Rijeka"
},
{
"operation": "Now on",
"time": "8.909",
"value": "HNK Rijeka"
},
{
"operation": "Highlighting",
"time": "11.38",
"value": "HNK Rijeka_sentence_0"
},
{
"operation": "Highlighting",
"time": "18.014",
"value": "HNK Rijeka_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "19.107",
"value": "HNK Rijeka_cell_0_0_1"
},
{
"operation": "Highlighting",
"time": "19.121",
"value": "HNK Rijeka_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "20.813",
"value": "HNK Rijeka_header_cell_0_3_0"
},
{
"operation": "Highlighting",
"time": "21.276",
"value": "HNK Rijeka_cell_0_3_1"
},
{
"operation": "Highlighting",
"time": "21.289",
"value": "HNK Rijeka_header_cell_0_3_0"
},
{
"operation": "Highlighting deleted",
"time": "39.001",
"value": "HNK Rijeka_cell_0_3_1"
},
{
"operation": "Highlighting deleted",
"time": "39.007",
"value": "HNK Rijeka_header_cell_0_3_0"
},
{
"operation": "Highlighting deleted",
"time": "40.115",
"value": "HNK Rijeka_cell_0_0_1"
},
{
"operation": "Highlighting deleted",
"time": "40.121",
"value": "HNK Rijeka_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "43.065",
"value": "HNK Rijeka_sentence_4"
},
{
"operation": "search",
"time": "101.573",
"value": "Višković"
},
{
"operation": "Now on",
"time": "102.546",
"value": "Višković"
},
{
"operation": "back-button-clicked",
"time": "126.063",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "126.917",
"value": "HNK Rijeka"
},
{
"operation": "finish",
"time": "137.022",
"value": "finish"
}
]
}
|
exfever_2064
|
Idris Elba is an American actor, producer, and musician known for his role in Mandela: Long Walk to Freedom. Mandela: Long Walk to Freedom is a British-South African biographical film written by William Nicholson.
|
{
"evidence": [
"Idris Elba",
"Mandela: Long Walk to Freedom"
],
"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:\nIdris Elba is an American actor, producer, and musician known for his role in Mandela: Long Walk to Freedom. Mandela: Long Walk to Freedom is a British-South African biographical film written by William Nicholson.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Idris Elba",
"Mandela: Long Walk to Freedom"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7456,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_6759
|
Steve Irwin was the first wildlife expert in Australia.
|
{
"evidence": [
"Steve Irwin",
"The Crocodile Hunter Diaries"
],
"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:\nSteve Irwin was the first wildlife expert in Australia.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Steve Irwin",
"The Crocodile Hunter Diaries"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7457,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7238
|
Amy Winehouse's debut studio album, Frank, is titled after one of her influences, one of the best-selling music artists of all time.?
|
{
"evidence": [
"Frank (Amy Winehouse album)",
"Frank Sinatra"
],
"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:\nAmy Winehouse's debut studio album, Frank, is titled after one of her influences, one of the best-selling music artists of all time.?\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Frank (Amy Winehouse album)",
"Frank Sinatra"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7458,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_905
|
Trolls is Anna Kendrick's first computer-animated film.
|
{
"evidence": [
"Trolls (film)",
"Comedy 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:\nTrolls is Anna Kendrick's first computer-animated film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Trolls (film)",
"Comedy film"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7459,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1425
|
Enemy is a Canadian psychological comedy film starring an Italian actress who is the daughter of the Swedish actress Ingrid Bergman and the Italian painter Roberto Rossellini.
|
{
"evidence": [
"Enemy (2013 film)",
"Isabella Rossellini"
],
"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:\nEnemy is a Canadian psychological comedy film starring an Italian actress who is the daughter of the Swedish actress Ingrid Bergman and the Italian painter Roberto Rossellini.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Enemy (2013 film)",
"Isabella Rossellini"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7460,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8138
|
War of the Worlds is a 2015 film directed by Steven Spielberg and written by Josh Friedman and ninth most successful screenwriter of all time in terms of U.S. box office receipts with a total gross of over $2.3 billion.
|
{
"evidence": [
"War of the Worlds (2005 film)",
"David Koepp"
],
"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:\nWar of the Worlds is a 2015 film directed by Steven Spielberg and written by Josh Friedman and ninth most successful screenwriter of all time in terms of U.S. box office receipts with a total gross of over $2.3 billion.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"War of the Worlds (2005 film)",
"David Koepp"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7461,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
85539
|
WALL is a radio station licensed to Middletown, New York, that serves Orange County, New York and is owned by Neversink Media Group through licensee Digital Radio Broadcasting, Inc.
|
{
"evidence": [
"WALL_sentence_2",
"WALL_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:\nWALL is a radio station licensed to Middletown, New York, that serves Orange County, New York and is owned by Neversink Media Group through licensee Digital Radio Broadcasting, Inc.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"WALL_sentence_2",
"WALL_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7462,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.997",
"value": "?search="
},
{
"operation": "search",
"time": "16.547",
"value": "WALL"
},
{
"operation": "Now on",
"time": "17.765",
"value": "WALL"
},
{
"operation": "Highlighting",
"time": "25.762",
"value": "WALL_sentence_2"
},
{
"operation": "Page search",
"time": "58.04",
"value": "media"
},
{
"operation": "Highlighting",
"time": "62.098",
"value": "WALL_sentence_3"
},
{
"operation": "finish",
"time": "168.623",
"value": "finish"
}
]
}
|
exfever_1387
|
The Dog Day Afternoon is a 1975 American biographical crime drama film starring an actor who was nominated for the Academy Award for Best Supporting Actor for a 1983 American war comedy film directed by John Wojtowicz.
|
{
"evidence": [
"Dog Day Afternoon",
"Charles Durning",
"To Be or Not to Be (1983 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:\nThe Dog Day Afternoon is a 1975 American biographical crime drama film starring an actor who was nominated for the Academy Award for Best Supporting Actor for a 1983 American war comedy film directed by John Wojtowicz.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Dog Day Afternoon",
"Charles Durning",
"To Be or Not to Be (1983 film)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7463,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
40139
|
Maitha bint Mohammed bin Rashid Al Maktoum was the flag bearer of the United Arab Emirates at the 2006 Asian Games, held in Doha, Qatar.
|
{
"evidence": [
"Maitha bint Mohammed bin Rashid Al Maktoum_sentence_3"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMaitha bint Mohammed bin Rashid Al Maktoum was the flag bearer of the United Arab Emirates at the 2006 Asian Games, held in Doha, Qatar.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Maitha bint Mohammed bin Rashid Al Maktoum_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7464,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.797",
"value": "?search="
},
{
"operation": "search",
"time": "24.522",
"value": "Maitha bint Mohammed bin Rashid Al Maktoum"
},
{
"operation": "Now on",
"time": "25.213",
"value": "Maitha bint Mohammed bin Rashid Al Maktoum"
},
{
"operation": "hyperlink",
"time": "74.041",
"value": "United Arab Emirates"
},
{
"operation": "Now on",
"time": "75.311",
"value": "United Arab Emirates"
},
{
"operation": "back-button-clicked",
"time": "79.24",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "79.344",
"value": "Maitha bint Mohammed bin Rashid Al Maktoum"
},
{
"operation": "hyperlink",
"time": "82.217",
"value": "2006 Asian Games"
},
{
"operation": "Now on",
"time": "83.471",
"value": "2006 Asian Games"
},
{
"operation": "back-button-clicked",
"time": "120.088",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "120.199",
"value": "Maitha bint Mohammed bin Rashid Al Maktoum"
},
{
"operation": "Highlighting",
"time": "122.104",
"value": "Maitha bint Mohammed bin Rashid Al Maktoum_sentence_3"
},
{
"operation": "finish",
"time": "147.357",
"value": "finish"
}
]
}
|
66506
|
Christian Oliva made his debut with the Nacional's first team during the Supercopa Uruguaya, an annual competition in Uruguay.
|
{
"evidence": [
"Christian Oliva_sentence_6",
"Supercopa Uruguaya_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:\nChristian Oliva made his debut with the Nacional's first team during the Supercopa Uruguaya, an annual competition in Uruguay.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Christian Oliva_sentence_6",
"Supercopa Uruguaya_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7465,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.569",
"value": "?search="
},
{
"operation": "search",
"time": "6.205",
"value": "Christian Oliva"
},
{
"operation": "Now on",
"time": "8.043",
"value": "Christian Oliva"
},
{
"operation": "Highlighting",
"time": "18.621",
"value": "Christian Oliva_cell_1_2_0"
},
{
"operation": "Highlighting",
"time": "18.623",
"value": "Christian Oliva_section_3"
},
{
"operation": "Highlighting",
"time": "18.642",
"value": "Christian Oliva_header_cell_1_0_0"
},
{
"operation": "Highlighting deleted",
"time": "25.346",
"value": "Christian Oliva_cell_1_2_0"
},
{
"operation": "Highlighting deleted",
"time": "25.35",
"value": "Christian Oliva_section_3"
},
{
"operation": "Highlighting deleted",
"time": "25.368",
"value": "Christian Oliva_header_cell_1_0_0"
},
{
"operation": "Highlighting",
"time": "33.425",
"value": "Christian Oliva_cell_1_2_0"
},
{
"operation": "Highlighting",
"time": "33.426",
"value": "Christian Oliva_section_3"
},
{
"operation": "Highlighting",
"time": "33.441",
"value": "Christian Oliva_header_cell_1_0_0"
},
{
"operation": "Page search",
"time": "63.054",
"value": "supercopa"
},
{
"operation": "Highlighting",
"time": "66.483",
"value": "Christian Oliva_sentence_6"
},
{
"operation": "Highlighting deleted",
"time": "165.919",
"value": "Christian Oliva_cell_1_2_0"
},
{
"operation": "Highlighting deleted",
"time": "165.922",
"value": "Christian Oliva_section_3"
},
{
"operation": "Highlighting deleted",
"time": "165.941",
"value": "Christian Oliva_header_cell_1_0_0"
},
{
"operation": "hyperlink",
"time": "170.178",
"value": "Supercopa Uruguaya"
},
{
"operation": "Now on",
"time": "175.014",
"value": "Supercopa Uruguaya"
},
{
"operation": "Highlighting",
"time": "178.359",
"value": "Supercopa Uruguaya_sentence_0"
},
{
"operation": "finish",
"time": "182.331",
"value": "finish"
}
]
}
|
exfever_8499
|
Brock Pemberton also gave the Antoinette Perry Award its nickname, the Tony.
|
{
"evidence": [
"Whoopi Goldberg",
"Tony Award",
"Brock Pemberton"
],
"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:\nBrock Pemberton also gave the Antoinette Perry Award its nickname, the Tony.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Whoopi Goldberg",
"Tony Award",
"Brock Pemberton"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7466,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2234
|
Paper Moon is a 1974 American road comedy-drama film which sets in Kansas and a state in the Midwestern region of the United States which in the east by a state in the Midwestern region of the United States.
|
{
"evidence": [
"Paper Moon (film)",
"Missouri",
"Illinois"
],
"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:\nPaper Moon is a 1974 American road comedy-drama film which sets in Kansas and a state in the Midwestern region of the United States which in the east by a state in the Midwestern region of the United States.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Paper Moon (film)",
"Missouri",
"Illinois"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7467,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
45781
|
Russia Tower was proposed to be built on plots 2 and 3 of the Moscow International Business Centre in 1994, it was designed by the Chicago-based architecture firm Skidmore and building site was moved to plot 14.
|
{
"evidence": [
"Russia Tower_sentence_16"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nRussia Tower was proposed to be built on plots 2 and 3 of the Moscow International Business Centre in 1994, it was designed by the Chicago-based architecture firm Skidmore and building site was moved to plot 14.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Russia Tower_sentence_16"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7468,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.238",
"value": "?search="
},
{
"operation": "search",
"time": "91.588",
"value": "Russia Tower"
},
{
"operation": "Now on",
"time": "92.617",
"value": "Russia Tower"
},
{
"operation": "Page search",
"time": "166.041",
"value": "plot"
},
{
"operation": "Highlighting",
"time": "168.928",
"value": "Russia Tower_sentence_15"
},
{
"operation": "Highlighting",
"time": "180.393",
"value": "Russia Tower_sentence_16"
},
{
"operation": "Page search",
"time": "210.648",
"value": "skidmore"
},
{
"operation": "Highlighting deleted",
"time": "229.55",
"value": "Russia Tower_sentence_15"
},
{
"operation": "Highlighting",
"time": "230.667",
"value": "Russia Tower_sentence_15"
},
{
"operation": "Highlighting deleted",
"time": "231.53",
"value": "Russia Tower_sentence_16"
},
{
"operation": "Highlighting",
"time": "232.332",
"value": "Russia Tower_sentence_16"
},
{
"operation": "Highlighting",
"time": "238.891",
"value": "Russia Tower_sentence_17"
},
{
"operation": "Highlighting deleted",
"time": "269.687",
"value": "Russia Tower_sentence_16"
},
{
"operation": "search",
"time": "275.665",
"value": "Skidmore, Owings and Merrill."
},
{
"operation": "Now on",
"time": "277.246",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "290.876",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "290.98",
"value": "Russia Tower"
},
{
"operation": "hyperlink",
"time": "293.054",
"value": "Moscow International Business Centre"
},
{
"operation": "Now on",
"time": "295.137",
"value": "Moscow International Business Centre"
},
{
"operation": "back-button-clicked",
"time": "302.079",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "302.178",
"value": "Russia Tower"
},
{
"operation": "Highlighting",
"time": "304.218",
"value": "Russia Tower_sentence_16"
},
{
"operation": "Highlighting deleted",
"time": "304.64",
"value": "Russia Tower_sentence_15"
},
{
"operation": "Highlighting deleted",
"time": "305.432",
"value": "Russia Tower_sentence_17"
},
{
"operation": "finish",
"time": "347.385",
"value": "finish"
}
]
}
|
exfever_6223
|
Ballspielverein Borussia is a German amateur sports club based in Dortmund, which is located in a state in Western Germany that has more than 17.9 billion inhabitants.
|
{
"evidence": [
"Borussia Dortmund",
"North Rhine-Westphalia"
],
"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:\nBallspielverein Borussia is a German amateur sports club based in Dortmund, which is located in a state in Western Germany that has more than 17.9 billion inhabitants.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Borussia Dortmund",
"North Rhine-Westphalia"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7469,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3451
|
Elizabeth Hughes Meriwether is a writer who created a drama titled "The Dropout" for an American subscription streaming service owned by American English-language commercial broadcast television and radio network.
|
{
"evidence": [
"Elizabeth Meriwether",
"Hulu",
"NBC"
],
"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:\nElizabeth Hughes Meriwether is a writer who created a drama titled \"The Dropout\" for an American subscription streaming service owned by American English-language commercial broadcast television and radio network.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Elizabeth Meriwether",
"Hulu",
"NBC"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7470,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
10970
|
Magali Herrera, who was born in a notable family in Rivera, Uruguay, was avidly fond of famous and well-known poems and stories who enjoyed organizing poetry evenings.
|
{
"evidence": [
"Magali Herrera_sentence_1",
"Magali Herrera_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:\nMagali Herrera, who was born in a notable family in Rivera, Uruguay, was avidly fond of famous and well-known poems and stories who enjoyed organizing poetry evenings.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Magali Herrera_sentence_1",
"Magali Herrera_sentence_4"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7471,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.539",
"value": "?search="
},
{
"operation": "search",
"time": "31.724",
"value": "magali herrera"
},
{
"operation": "Now on",
"time": "32.792",
"value": "Magali Herrera"
},
{
"operation": "Highlighting",
"time": "42.869",
"value": "Magali Herrera_sentence_1"
},
{
"operation": "Highlighting",
"time": "55.819",
"value": "Magali Herrera_sentence_4"
},
{
"operation": "Page search",
"time": "66.307",
"value": "poe"
},
{
"operation": "Page search",
"time": "87.444",
"value": "famous"
},
{
"operation": "Page search",
"time": "91.428",
"value": "known"
},
{
"operation": "finish",
"time": "141.308",
"value": "finish"
}
]
}
|
3848
|
Voting rights in Singapore is impacted by Paines view, and the Supreme Court says that representative democracy does not appear in the Constitution of Singapore.
|
{
"evidence": [
"Voting rights in Singapore_sentence_0",
"Voting rights in Singapore_sentence_6",
"Voting rights in Singapore_sentence_20",
"Voting rights in Singapore_sentence_22",
"Voting rights in Singapore_sentence_24",
"Voting rights in Singapore_sentence_25",
"Voting rights in Singapore_sentence_30",
"Voting rights in Singapore_sentence_31"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nVoting rights in Singapore is impacted by Paines view, and the Supreme Court says that representative democracy does not appear in the Constitution of Singapore.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Voting rights in Singapore_sentence_0",
"Voting rights in Singapore_sentence_6",
"Voting rights in Singapore_sentence_20",
"Voting rights in Singapore_sentence_22",
"Voting rights in Singapore_sentence_24",
"Voting rights in Singapore_sentence_25",
"Voting rights in Singapore_sentence_30",
"Voting rights in Singapore_sentence_31"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7472,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "17.248",
"value": "Voting rights in Singapore"
},
{
"operation": "Highlighting",
"time": "35.167",
"value": "Voting rights in Singapore_sentence_0"
},
{
"operation": "Highlighting",
"time": "85.024",
"value": "Voting rights in Singapore_sentence_6"
},
{
"operation": "Page search",
"time": "112.098",
"value": "paine"
},
{
"operation": "Highlighting",
"time": "180.651",
"value": "Voting rights in Singapore_sentence_20"
},
{
"operation": "Highlighting",
"time": "181.82",
"value": "Voting rights in Singapore_sentence_22"
},
{
"operation": "Highlighting",
"time": "198.501",
"value": "Voting rights in Singapore_sentence_24"
},
{
"operation": "Highlighting",
"time": "203.748",
"value": "Voting rights in Singapore_sentence_25"
},
{
"operation": "Highlighting",
"time": "304.049",
"value": "Voting rights in Singapore_sentence_1Voting rights in Singapore_sentence_2"
},
{
"operation": "Highlighting",
"time": "421.617",
"value": "Voting rights in Singapore_sentence_30"
},
{
"operation": "Highlighting",
"time": "430.559",
"value": "Voting rights in Singapore_sentence_31"
},
{
"operation": "finish",
"time": "559.606",
"value": "finish"
}
]
}
|
exfever_7438
|
One of the awards given annually to people working in the motion picture industry was received by the Canadian comedy-drama film The Paper on the year 1994.
|
{
"evidence": [
"The Paper (film)",
"Academy Award for Best Original Song"
],
"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:\nOne of the awards given annually to people working in the motion picture industry was received by the Canadian comedy-drama film The Paper on the year 1994.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Paper (film)",
"Academy Award for Best Original Song"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7473,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
20265
|
This protein, a component of an evolutionarily conserved, genotoxin-activated checkpoint complex, forms a heterotrimeric complex with checkpoint proteins RAD9 and RAD2.
|
{
"evidence": [
"HUS1_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:\nThis protein, a component of an evolutionarily conserved, genotoxin-activated checkpoint complex, forms a heterotrimeric complex with checkpoint proteins RAD9 and RAD2.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"HUS1_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7474,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.691",
"value": "?search="
},
{
"operation": "search",
"time": "23.455",
"value": "checkpoint proteins RAD9 and RAD2"
},
{
"operation": "Now on",
"time": "24.901",
"value": "undefined"
},
{
"operation": "search",
"time": "71.305",
"value": "heterotrimeric complex"
},
{
"operation": "Now on",
"time": "72.175",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "88.397",
"value": "G beta-gamma complex Heterotrimeric G protein_section_1"
},
{
"operation": "Now on",
"time": "88.838",
"value": "Heterotrimeric G protein#G beta-gamma complex Heterotrimeric G protein section 1"
},
{
"operation": "search",
"time": "136.284",
"value": "genotoxin-activated checkpoing"
},
{
"operation": "Now on",
"time": "136.99",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "166.749",
"value": "HUS1"
},
{
"operation": "Now on",
"time": "167.094",
"value": "HUS1"
},
{
"operation": "Highlighting",
"time": "211.237",
"value": "HUS1_sentence_2"
},
{
"operation": "finish",
"time": "235.733",
"value": "finish"
}
]
}
|
exfever_1280
|
Ruth Negga is an Ethiopian-Irish actress known for an American supernatural adventure television series developed by Sam Catlin, Evan Goldberg, and Seth Rogen for AMC.
|
{
"evidence": [
"Ruth Negga",
"Preacher (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:\nRuth Negga is an Ethiopian-Irish actress known for an American supernatural adventure television series developed by Sam Catlin, Evan Goldberg, and Seth Rogen for AMC.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Ruth Negga",
"Preacher (TV series)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7475,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
47851
|
Le Procès Veauradieux is a drama.
|
{
"evidence": [
"Le Procès Veauradieux_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:\nLe Procès Veauradieux is a drama.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Le Procès Veauradieux_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7476,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.776",
"value": "?search="
},
{
"operation": "search",
"time": "30.137",
"value": "Le Procès Veauradieux"
},
{
"operation": "Now on",
"time": "30.881",
"value": "Le Procès Veauradieux"
},
{
"operation": "Page search",
"time": "40.188",
"value": "drama"
},
{
"operation": "hyperlink",
"time": "55.709",
"value": "farce"
},
{
"operation": "Now on",
"time": "56.469",
"value": "Farce"
},
{
"operation": "back-button-clicked",
"time": "60.265",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "60.386",
"value": "Le Procès Veauradieux"
},
{
"operation": "Highlighting",
"time": "62.007",
"value": "Le Procès Veauradieux_sentence_0"
},
{
"operation": "finish",
"time": "72.498",
"value": "finish"
}
]
}
|
30817
|
Gopala Dasa, named "Bhaganna" at birth and known to have been a meteorologist as well, was a prominent 18th-century Kannada language poet and saint belonging to the Haridasa tradition.
|
{
"evidence": [
"Gopala Dasa_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:\nGopala Dasa, named \"Bhaganna\" at birth and known to have been a meteorologist as well, was a prominent 18th-century Kannada language poet and saint belonging to the Haridasa tradition.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Gopala Dasa_sentence_5"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 7477,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.175",
"value": "?search="
},
{
"operation": "search",
"time": "56.709",
"value": "Gopala Dasa"
},
{
"operation": "Now on",
"time": "57.93",
"value": "Gopala Dasa"
},
{
"operation": "Highlighting",
"time": "71.073",
"value": "Gopala Dasa_sentence_2"
},
{
"operation": "Page search",
"time": "92.979",
"value": "meteor"
},
{
"operation": "Page search",
"time": "98.987",
"value": "mete"
},
{
"operation": "Highlighting deleted",
"time": "104.33",
"value": "Gopala Dasa_sentence_2"
},
{
"operation": "Highlighting",
"time": "105.302",
"value": "Gopala Dasa_sentence_5"
},
{
"operation": "finish",
"time": "124.89",
"value": "finish"
}
]
}
|
67511
|
Edward Frederick Sanderson later on became a minister and supported the Nantucket Whaling Museum, the flagship site of the Nantucket Historical Association’s fleet of properties.
|
{
"evidence": [
"Edward Frederick Sanderson_sentence_2",
"Edward Frederick Sanderson_sentence_3",
"Nantucket Whaling Museum_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:\nEdward Frederick Sanderson later on became a minister and supported the Nantucket Whaling Museum, the flagship site of the Nantucket Historical Association’s fleet of properties.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Edward Frederick Sanderson_sentence_2",
"Edward Frederick Sanderson_sentence_3",
"Nantucket Whaling Museum_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7478,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.098",
"value": "?search="
},
{
"operation": "search",
"time": "10.836",
"value": "Edward Frederick Sanderson"
},
{
"operation": "Now on",
"time": "11.896",
"value": "Edward Frederick Sanderson"
},
{
"operation": "Page search",
"time": "24.95",
"value": "Nantucket Whaling"
},
{
"operation": "Highlighting",
"time": "26.832",
"value": "Edward Frederick Sanderson_sentence_3"
},
{
"operation": "Highlighting",
"time": "54.398",
"value": "Edward Frederick Sanderson_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "61.918",
"value": "Edward Frederick Sanderson_sentence_3"
},
{
"operation": "Highlighting",
"time": "62.406",
"value": "Edward Frederick Sanderson_sentence_3"
},
{
"operation": "hyperlink",
"time": "63.519",
"value": "Nantucket Whaling Museum"
},
{
"operation": "Now on",
"time": "64.431",
"value": "Nantucket Whaling Museum"
},
{
"operation": "Highlighting",
"time": "75.423",
"value": "Nantucket Whaling Museum_sentence_2"
},
{
"operation": "finish",
"time": "113.76",
"value": "finish"
}
]
}
|
exfever_7805
|
Grant Gustin is an American actor who appears in The Flash on the American English-language network that is operated by The CW Network.
|
{
"evidence": [
"Grant Gustin",
"The CW"
],
"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:\nGrant Gustin is an American actor who appears in The Flash on the American English-language network that is operated by The CW Network.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Grant Gustin",
"The CW"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7479,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7529
|
War of the Worlds is a science fiction film in which the protagonist bumps into a series of events that typically involve violence and physical feats.
|
{
"evidence": [
"War of the Worlds (2005 film)",
"Action 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:\nWar of the Worlds is a science fiction film in which the protagonist bumps into a series of events that typically involve violence and physical feats.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"War of the Worlds (2005 film)",
"Action film"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7480,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
59927
|
Two of Douglas Gordon's best-known art works are The 24 Hour Psycho (1993), which slows down Alfred Hitchcock's film Psycho so that it lasts twenty four hours, and Feature Film, a projection of Gordon's own film of James Conlon (current music director of Los Angeles Opera born on March 18, 1950) conducting Bernard Herrmann's score to Vertigo.
|
{
"evidence": [
"Douglas Gordon_sentence_13",
"Douglas Gordon_sentence_10",
"James Conlon_sentence_2",
"James Conlon_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:\nTwo of Douglas Gordon's best-known art works are The 24 Hour Psycho (1993), which slows down Alfred Hitchcock's film Psycho so that it lasts twenty four hours, and Feature Film, a projection of Gordon's own film of James Conlon (current music director of Los Angeles Opera born on March 18, 1950) conducting Bernard Herrmann's score to Vertigo.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Douglas Gordon_sentence_13",
"Douglas Gordon_sentence_10",
"James Conlon_sentence_2",
"James Conlon_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7481,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.269",
"value": "undefined"
},
{
"operation": "search",
"time": "37.339",
"value": "Douglas Gordon"
},
{
"operation": "Now on",
"time": "38.692",
"value": "Douglas Gordon"
},
{
"operation": "Page search",
"time": "131.642",
"value": "feature film"
},
{
"operation": "Page search",
"time": "134.694",
"value": "feature film"
},
{
"operation": "Highlighting",
"time": "163.028",
"value": "Douglas Gordon_sentence_13"
},
{
"operation": "Highlighting",
"time": "173.405",
"value": "Douglas Gordon_sentence_10"
},
{
"operation": "hyperlink",
"time": "235.753",
"value": "James Conlon"
},
{
"operation": "Now on",
"time": "236.522",
"value": "James Conlon"
},
{
"operation": "Highlighting",
"time": "253.042",
"value": "James Conlon_sentence_2"
},
{
"operation": "Highlighting",
"time": "258.774",
"value": "James Conlon_sentence_1"
},
{
"operation": "finish",
"time": "271.638",
"value": "finish"
}
]
}
|
exfever_2095
|
Chris McKenna is an American television writer, film producer, screenwriter, and television producer that has written for an American television sitcom created by Dan Harmon.
|
{
"evidence": [
"Chris McKenna (writer)",
"Community (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:\nChris McKenna is an American television writer, film producer, screenwriter, and television producer that has written for an American television sitcom created by Dan Harmon.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Chris McKenna (writer)",
"Community (TV series)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 7482,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
91115
|
The albums "I Could Not Ask for More" and "Saints and Angels" were released in 2001.
|
{
"evidence": [
"I Could Not Ask for More_sentence_0"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe albums \"I Could Not Ask for More\" and \"Saints and Angels\" were released in 2001.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"I Could Not Ask for More_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 7483,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.108",
"value": "?search="
},
{
"operation": "search",
"time": "8.903",
"value": "I Could Not Ask for More"
},
{
"operation": "Now on",
"time": "10.373",
"value": "I Could Not Ask for More"
},
{
"operation": "hyperlink",
"time": "12.093",
"value": "Diane Warren"
},
{
"operation": "Now on",
"time": "14.379",
"value": "Diane Warren"
},
{
"operation": "back-button-clicked",
"time": "25.332",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "25.488",
"value": "I Could Not Ask for More"
},
{
"operation": "Highlighting",
"time": "43.206",
"value": "I Could Not Ask for More_sentence_0"
},
{
"operation": "search",
"time": "49.984",
"value": "Saints and Angels"
},
{
"operation": "Now on",
"time": "53.744",
"value": "undefined"
},
{
"operation": "search",
"time": "60.077",
"value": "Saints and Angels album"
},
{
"operation": "Now on",
"time": "61.859",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "66.91",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "67.082",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "68.006",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "68.013",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "68.174",
"value": "I Could Not Ask for More"
},
{
"operation": "Page search",
"time": "71.295",
"value": "saints"
},
{
"operation": "search",
"time": "82.848",
"value": "\"Saints and Angels\""
},
{
"operation": "Now on",
"time": "83.659",
"value": "undefined"
},
{
"operation": "finish",
"time": "96.156",
"value": "finish"
}
]
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.