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_8958
|
Jeffrey Lynn Goldblum is an American actor who has starred in films, including a 1978 American science-fiction horror film directed by Philip Kaufman.
|
{
"evidence": [
"Jeff Goldblum",
"Invasion of the Body Snatchers (1978 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:\nJeffrey Lynn Goldblum is an American actor who has starred in films, including a 1978 American science-fiction horror film directed by Philip Kaufman.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jeff Goldblum",
"Invasion of the Body Snatchers (1978 film)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3184,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
60128
|
June Babies, the first melodic pop album produced and recorded by Andy Hamill for English singer-songwriter Jeb Loy Nichols, was released on 9 October 2001 on Emu Records and was played on Jeremy Vine's BBC Radio 2 show.
|
{
"evidence": [
"June Babies_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:\nJune Babies, the first melodic pop album produced and recorded by Andy Hamill for English singer-songwriter Jeb Loy Nichols, was released on 9 October 2001 on Emu Records and was played on Jeremy Vine's BBC Radio 2 show.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"June Babies_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3185,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "15.188",
"value": "?search="
},
{
"operation": "search",
"time": "19.157",
"value": "June Babies"
},
{
"operation": "Now on",
"time": "20.004",
"value": "June Babies"
},
{
"operation": "Page search",
"time": "51.288",
"value": "Nichols"
},
{
"operation": "Highlighting",
"time": "64.05",
"value": "June Babies_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "70.274",
"value": "June Babies_sentence_1"
},
{
"operation": "Highlighting",
"time": "72.474",
"value": "June Babies_sentence_0"
},
{
"operation": "Highlighting",
"time": "117.155",
"value": "June Babies_sentence_4"
},
{
"operation": "Highlighting",
"time": "117.159",
"value": "June Babies_section_0"
},
{
"operation": "Highlighting deleted",
"time": "119.651",
"value": "June Babies_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "119.655",
"value": "June Babies_section_0"
},
{
"operation": "search",
"time": "154.402",
"value": "Contains...Jeb Loy Nichols"
},
{
"operation": "Now on",
"time": "156.554",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "164.574",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "164.862",
"value": "June Babies"
},
{
"operation": "finish",
"time": "169.485",
"value": "finish"
}
]
}
|
29850
|
Ulrich Makosch worked as an editor for the local radio station in Schwerin neither in 1955 nor in 1956; then worked as a chief foreign correspondent for the East German Television Corporation from 1965 to 1971.
|
{
"evidence": [
"Ulrich Makosch_sentence_10",
"Ulrich Makosch_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:\nUlrich Makosch worked as an editor for the local radio station in Schwerin neither in 1955 nor in 1956; then worked as a chief foreign correspondent for the East German Television Corporation from 1965 to 1971.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Ulrich Makosch_sentence_10",
"Ulrich Makosch_sentence_12"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3186,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.048",
"value": "?search="
},
{
"operation": "search",
"time": "9.738",
"value": "Ulrich Makosch"
},
{
"operation": "Now on",
"time": "10.546",
"value": "Ulrich Makosch"
},
{
"operation": "Highlighting",
"time": "25.879",
"value": "Ulrich Makosch_sentence_10"
},
{
"operation": "Highlighting",
"time": "42.583",
"value": "Ulrich Makosch_sentence_12"
},
{
"operation": "finish",
"time": "60.838",
"value": "finish"
}
]
}
|
exfever_3151
|
AC/DC is an American rock band whose music has been described simply as a popular music genre that developed in the United States during the late 1940s and early 1950s.
|
{
"evidence": [
"AC/DC",
"Rock and roll"
],
"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:\nAC/DC is an American rock band whose music has been described simply as a popular music genre that developed in the United States during the late 1940s and early 1950s.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"AC/DC",
"Rock and roll"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3187,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
75301
|
Murray Canal is a canal in the municipalities of Quinte West and Brighton, Canada in the northern part of North America.
|
{
"evidence": [
"Murray Canal_sentence_1",
"Canada_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:\nMurray Canal is a canal in the municipalities of Quinte West and Brighton, Canada in the northern part of North America.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Murray Canal_sentence_1",
"Canada_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3188,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.083",
"value": "?search="
},
{
"operation": "search",
"time": "12.78",
"value": "Murray Canal"
},
{
"operation": "Now on",
"time": "13.612",
"value": "Murray Canal"
},
{
"operation": "Highlighting",
"time": "31.469",
"value": "Murray Canal_sentence_1"
},
{
"operation": "hyperlink",
"time": "69.228",
"value": "Canada"
},
{
"operation": "Now on",
"time": "71.344",
"value": "Canada"
},
{
"operation": "Highlighting",
"time": "73.134",
"value": "Canada_sentence_2"
},
{
"operation": "finish",
"time": "259.625",
"value": "finish"
}
]
}
|
exfever_5260
|
Edgar Allan Poe was one of the country's earliest practitioners of a piece of prose fiction that can typically be read in one sitting.
|
{
"evidence": [
"Edgar Allan Poe",
"Short story"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nEdgar Allan Poe was one of the country's earliest practitioners of a piece of prose fiction that can typically be read in one sitting.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Edgar Allan Poe",
"Short story"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3189,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7083
|
WeChat developed by Tencent is a Chinese mobile payment computer program or software application designed to run on a mobile device such as a phone, tablet, or watch.
|
{
"evidence": [
"WeChat",
"Mobile app"
],
"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:\nWeChat developed by Tencent is a Chinese mobile payment computer program or software application designed to run on a mobile device such as a phone, tablet, or watch.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"WeChat",
"Mobile app"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3190,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
73072
|
West Coast Treetop Walk is a tourist attraction built by an Australian eco-tourism company wherein it has a walkway that leads through the canopy of mature native West Coast forest that passes close to the crowns of mature rimu trees and sits above smaller trees and tree ferns.
|
{
"evidence": [
"West Coast Treetop Walk_sentence_1",
"West Coast Treetop Walk_sentence_2",
"West Coast Treetop Walk_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:\nWest Coast Treetop Walk is a tourist attraction built by an Australian eco-tourism company wherein it has a walkway that leads through the canopy of mature native West Coast forest that passes close to the crowns of mature rimu trees and sits above smaller trees and tree ferns.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"West Coast Treetop Walk_sentence_1",
"West Coast Treetop Walk_sentence_2",
"West Coast Treetop Walk_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3191,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.934",
"value": "?search="
},
{
"operation": "search",
"time": "9.486",
"value": "West Coast Treetop Walk"
},
{
"operation": "Now on",
"time": "10.135",
"value": "West Coast Treetop Walk"
},
{
"operation": "Highlighting",
"time": "13.315",
"value": "West Coast Treetop Walk_sentence_1"
},
{
"operation": "Highlighting",
"time": "20.69",
"value": "West Coast Treetop Walk_sentence_2"
},
{
"operation": "Highlighting",
"time": "28.555",
"value": "West Coast Treetop Walk_sentence_3"
},
{
"operation": "finish",
"time": "54.669",
"value": "finish"
}
]
}
|
83032
|
Pablo Iglesias Simón has designed the sound of more than 13 shows working for both public and private companies, in December 2006 it was the opening night of his last play “El lado oeste del Golden Gate” (“The West Side of the Golden Gate”) for whose staging he was awarded with the “José Luis Alonso” Award for the Best Young Director 2011.
|
{
"evidence": [
"Pablo Iglesias Simón_sentence_5",
"Pablo Iglesias Simón_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:\nPablo Iglesias Simón has designed the sound of more than 13 shows working for both public and private companies, in December 2006 it was the opening night of his last play “El lado oeste del Golden Gate” (“The West Side of the Golden Gate”) for whose staging he was awarded with the “José Luis Alonso” Award for the Best Young Director 2011.\n",
"role": "user"
}
] |
Numerical Reasoning
|
{
"ground_truth": {
"evidence": [
"Pablo Iglesias Simón_sentence_5",
"Pablo Iglesias Simón_sentence_6"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3192,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.771",
"value": "?search="
},
{
"operation": "search",
"time": "13.641",
"value": "Pablo Iglesias Simón"
},
{
"operation": "Now on",
"time": "14.328",
"value": "Pablo Iglesias Simón"
},
{
"operation": "Highlighting",
"time": "29.56",
"value": "Pablo Iglesias Simón_sentence_6"
},
{
"operation": "Highlighting",
"time": "71.871",
"value": "Pablo Iglesias Simón_item_2_9"
},
{
"operation": "Highlighting",
"time": "71.872",
"value": "Pablo Iglesias Simón_section_2"
},
{
"operation": "Highlighting",
"time": "71.872",
"value": "Pablo Iglesias Simón_section_4"
},
{
"operation": "Highlighting deleted",
"time": "74.319",
"value": "Pablo Iglesias Simón_item_2_9"
},
{
"operation": "Highlighting deleted",
"time": "74.321",
"value": "Pablo Iglesias Simón_section_2"
},
{
"operation": "Highlighting deleted",
"time": "74.321",
"value": "Pablo Iglesias Simón_section_4"
},
{
"operation": "Highlighting deleted",
"time": "86.735",
"value": "Pablo Iglesias Simón_sentence_6"
},
{
"operation": "Highlighting",
"time": "87.287",
"value": "Pablo Iglesias Simón_sentence_5"
},
{
"operation": "Highlighting",
"time": "103.831",
"value": "Pablo Iglesias Simón_sentence_6"
},
{
"operation": "finish",
"time": "108.975",
"value": "finish"
}
]
}
|
exfever_1527
|
Mel Columcille Gerard Gibson is an American actor who portrayed the fictional character Martin Riggs in the buddy cop film series Lethal Weapon.
|
{
"evidence": [
"Mel Gibson",
"Martin Riggs"
],
"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:\nMel Columcille Gerard Gibson is an American actor who portrayed the fictional character Martin Riggs in the buddy cop film series Lethal Weapon.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Mel Gibson",
"Martin Riggs"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3193,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5287
|
The Shield is an American crime drama television series starring an Italian actor, television director, and television producer who played Commissioner Tony Scali in the ABC comedy-drama television series in the United States that aired from September 28, 1991, to January 11, 1996.
|
{
"evidence": [
"The Shield",
"Michael Chiklis",
"The Commish"
],
"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 Shield is an American crime drama television series starring an Italian actor, television director, and television producer who played Commissioner Tony Scali in the ABC comedy-drama television series in the United States that aired from September 28, 1991, to January 11, 1996.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Shield",
"Michael Chiklis",
"The Commish"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3194,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
50269
|
Polyamides, a polymer with repeating units linked by amide bonds, has 13–16% DecaBDE and brominated polystyrene; while Polystyrene foam has 0.8–4% HBCD.
|
{
"evidence": [
"Polyamide_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:\nPolyamides, a polymer with repeating units linked by amide bonds, has 13–16% DecaBDE and brominated polystyrene; while Polystyrene foam has 0.8–4% HBCD.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Polyamide_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3195,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.4",
"value": "?search="
},
{
"operation": "search",
"time": "9.245",
"value": "Polyamides"
},
{
"operation": "Now on",
"time": "10.138",
"value": "Polyamide"
},
{
"operation": "Highlighting",
"time": "15.163",
"value": "Polyamide_sentence_0"
},
{
"operation": "hyperlink",
"time": "64.239",
"value": "amide"
},
{
"operation": "Now on",
"time": "65.082",
"value": "Amide"
},
{
"operation": "back-button-clicked",
"time": "75.655",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "76.176",
"value": "Polyamide"
},
{
"operation": "search",
"time": "102.331",
"value": "Contains...13–16% DecaBDE and brominated polystyrene"
},
{
"operation": "Now on",
"time": "103.589",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "111.708",
"value": "Decabromodiphenyl ether"
},
{
"operation": "Now on",
"time": "112.553",
"value": "Decabromodiphenyl ether"
},
{
"operation": "search",
"time": "144.962",
"value": "Contains...DecaBDE and brominated polystyrene"
},
{
"operation": "Now on",
"time": "145.453",
"value": "undefined"
},
{
"operation": "search",
"time": "169.603",
"value": "Contains...Polystyrene foam has 0.8–4% HBCD"
},
{
"operation": "Now on",
"time": "170.698",
"value": "undefined"
},
{
"operation": "finish",
"time": "186.015",
"value": "finish"
}
]
}
|
exfever_1555
|
The Carolina Panthers are a professional American football team that competes in a professional American football league that consists of 32 teams split between the American Football Conference and the National Football Conference.
|
{
"evidence": [
"Carolina Panthers",
"National Football League"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Carolina Panthers are a professional American football team that competes in a professional American football league that consists of 32 teams split between the American Football Conference and the National Football Conference.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Carolina Panthers",
"National Football League"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3196,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2295
|
Kung Fu Panda 3 is a 2013 computer-animated fantasy martial arts comedy film directed by Jennifer Yuh Nelson and an Italian film director, animator, and art director.
|
{
"evidence": [
"Kung Fu Panda 3",
"Alessandro Carloni"
],
"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:\nKung Fu Panda 3 is a 2013 computer-animated fantasy martial arts comedy film directed by Jennifer Yuh Nelson and an Italian film director, animator, and art director.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Kung Fu Panda 3",
"Alessandro Carloni"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3197,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
84237
|
Albert Schinz taught at the University of Minnesota for one year, then became professor of French literature at Clark University from 1897 to 1898, then he finally retired after teaching French at the University of Pennsylvania (a private Ivy League research university in Philadelphia) in 1941.
|
{
"evidence": [
"Albert Schinz_sentence_3",
"Albert Schinz_sentence_4"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAlbert Schinz taught at the University of Minnesota for one year, then became professor of French literature at Clark University from 1897 to 1898, then he finally retired after teaching French at the University of Pennsylvania (a private Ivy League research university in Philadelphia) in 1941.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Albert Schinz_sentence_3",
"Albert Schinz_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3198,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.715",
"value": "?search="
},
{
"operation": "search",
"time": "131.83",
"value": "Albert Schinz"
},
{
"operation": "Now on",
"time": "132.759",
"value": "Albert Schinz"
},
{
"operation": "Highlighting",
"time": "168.949",
"value": "Albert Schinz_sentence_3"
},
{
"operation": "Highlighting",
"time": "183.85",
"value": "Albert Schinz_sentence_4"
},
{
"operation": "finish",
"time": "201.515",
"value": "finish"
}
]
}
|
35396
|
Hengshan County is located in Hong Kong with a time zone of UTC+10.
|
{
"evidence": [
"Hengshan County_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:\nHengshan County is located in Hong Kong with a time zone of UTC+10.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Hengshan County_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3199,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.079",
"value": "?search="
},
{
"operation": "search",
"time": "27.095",
"value": "Hengshan County"
},
{
"operation": "Now on",
"time": "27.992",
"value": "Hengshan County"
},
{
"operation": "Highlighting",
"time": "59.391",
"value": "Hengshan County_sentence_1"
},
{
"operation": "finish",
"time": "89.801",
"value": "finish"
}
]
}
|
25104
|
SAS, an American multinational developer of analytics software based in Cary, North Carolina, spent 2.5 times the industry average on R&D; and as of 2010 revenues come relatively evenly from Europe, Africa, the Middle East and the Americas.
|
{
"evidence": [
"SAS Institute_sentence_0",
"SAS Institute_sentence_44",
"SAS Institute_sentence_45"
],
"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:\nSAS, an American multinational developer of analytics software based in Cary, North Carolina, spent 2.5 times the industry average on R&D; and as of 2010 revenues come relatively evenly from Europe, Africa, the Middle East and the Americas.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"SAS Institute_sentence_0",
"SAS Institute_sentence_44",
"SAS Institute_sentence_45"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3200,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.942",
"value": "?search="
},
{
"operation": "search",
"time": "22.474",
"value": "SAS"
},
{
"operation": "Now on",
"time": "24.501",
"value": "SAS"
},
{
"operation": "hyperlink",
"time": "54.076",
"value": "SAS Institute"
},
{
"operation": "Now on",
"time": "55.165",
"value": "SAS Institute"
},
{
"operation": "Highlighting",
"time": "56.704",
"value": "SAS Institute_sentence_0"
},
{
"operation": "Page search",
"time": "93.171",
"value": "spent 2.5 times the industry average"
},
{
"operation": "Highlighting",
"time": "102.171",
"value": "SAS Institute_sentence_44"
},
{
"operation": "Highlighting",
"time": "109.013",
"value": "SAS Institute_sentence_45"
},
{
"operation": "finish",
"time": "129.547",
"value": "finish"
}
]
}
|
88280
|
Aeronáutica, which was an airline established in 2001 that provided consumer services for airlines however it has been banned from operating due to safety concerns.
|
{
"evidence": [
"Aeronáutica (Angola)_sentence_1",
"Aeronáutica (Angola)_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:\nAeronáutica, which was an airline established in 2001 that provided consumer services for airlines however it has been banned from operating due to safety concerns.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Aeronáutica (Angola)_sentence_1",
"Aeronáutica (Angola)_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3201,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.918",
"value": "?search="
},
{
"operation": "search",
"time": "7.981",
"value": "Aeronáutica"
},
{
"operation": "Now on",
"time": "8.823",
"value": "Aeronautica"
},
{
"operation": "search",
"time": "588.508",
"value": "ATA Airlines (Iran)"
},
{
"operation": "Now on",
"time": "589.479",
"value": "ATA Airlines (Iran)"
},
{
"operation": "search",
"time": "673.249",
"value": "Aeronáutica"
},
{
"operation": "Now on",
"time": "674.203",
"value": "Aeronautica"
},
{
"operation": "hyperlink",
"time": "676.478",
"value": "Aeronáutica (Angola)"
},
{
"operation": "Now on",
"time": "676.841",
"value": "Aeronáutica (Angola)"
},
{
"operation": "Highlighting",
"time": "684.364",
"value": "Aeronáutica (Angola)_sentence_1"
},
{
"operation": "Highlighting",
"time": "696.103",
"value": "Aeronáutica (Angola)_sentence_2"
},
{
"operation": "Highlighting",
"time": "703.994",
"value": "Aeronáutica (Angola)_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "708.945",
"value": "Aeronáutica (Angola)_sentence_3"
},
{
"operation": "finish",
"time": "738.627",
"value": "finish"
}
]
}
|
15625
|
Jan Hofer is a German journalist, broadcast news analyst and retired television presenter who joined the Tagesschau in 1985 where he became the managing editor in 2004.
|
{
"evidence": [
"Jan Hofer_sentence_0",
"Jan Hofer_sentence_2",
"Jan Hofer_sentence_6"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJan Hofer is a German journalist, broadcast news analyst and retired television presenter who joined the Tagesschau in 1985 where he became the managing editor in 2004.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Jan Hofer_sentence_0",
"Jan Hofer_sentence_2",
"Jan Hofer_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3202,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.109",
"value": "?search="
},
{
"operation": "search",
"time": "12.703",
"value": "Jan Hofer"
},
{
"operation": "Now on",
"time": "13.83",
"value": "Jan Hofer"
},
{
"operation": "Highlighting",
"time": "17.66",
"value": "Jan Hofer_sentence_0"
},
{
"operation": "Highlighting",
"time": "31.201",
"value": "Jan Hofer_sentence_2"
},
{
"operation": "Highlighting",
"time": "57.695",
"value": "Jan Hofer_sentence_6"
},
{
"operation": "finish",
"time": "135.829",
"value": "finish"
}
]
}
|
exfever_7248
|
Jerry Maguire is a 1997 American romantic comedy-drama sports film that stars an American actress and director who received various accolades, including an Academy Award, a Golden Globe Award, three Peabody Awards, and four Primetime Emmy Awards.
|
{
"evidence": [
"Jerry Maguire",
"Regina King"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJerry Maguire is a 1997 American romantic comedy-drama sports film that stars an American actress and director who received various accolades, including an Academy Award, a Golden Globe Award, three Peabody Awards, and four Primetime Emmy Awards.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jerry Maguire",
"Regina King"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3203,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
8656
|
Cervantez, an American artist and Chicana activist, moved to Orange County with her family; then during her high school days, she focused on her watercolor skills.
|
{
"evidence": [
"Yreina Cervantez_sentence_0",
"Yreina Cervantez_sentence_5",
"Yreina Cervantez_sentence_6"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nCervantez, an American artist and Chicana activist, moved to Orange County with her family; then during her high school days, she focused on her watercolor skills.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Yreina Cervantez_sentence_0",
"Yreina Cervantez_sentence_5",
"Yreina Cervantez_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3204,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.763",
"value": "?search="
},
{
"operation": "search",
"time": "29.561",
"value": "Contains...Cervantez"
},
{
"operation": "Now on",
"time": "30.69",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "34.637",
"value": "Miguel de Cervantes"
},
{
"operation": "Now on",
"time": "35.787",
"value": "Miguel de Cervantes"
},
{
"operation": "back-button-clicked",
"time": "43.882",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "44.64",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "56.145",
"value": "cervantes"
},
{
"operation": "Now on",
"time": "59.864",
"value": "undefined"
},
{
"operation": "search",
"time": "87.653",
"value": "chicana activist"
},
{
"operation": "Now on",
"time": "88.734",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "104.52",
"value": "Yreina Cervantez"
},
{
"operation": "Now on",
"time": "105.999",
"value": "Yreina Cervantez"
},
{
"operation": "Highlighting",
"time": "110.04",
"value": "Yreina Cervantez_sentence_0"
},
{
"operation": "Highlighting",
"time": "122.24",
"value": "Yreina Cervantez_sentence_5"
},
{
"operation": "Highlighting",
"time": "126.732",
"value": "Yreina Cervantez_sentence_6"
},
{
"operation": "finish",
"time": "149.95",
"value": "finish"
}
]
}
|
exfever_7109
|
Measles is a hereditary disease with complications including an inflammatory condition of the lung primarily affecting the small air sacs known as alveoli.
|
{
"evidence": [
"Measles",
"Pneumonia"
],
"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:\nMeasles is a hereditary disease with complications including an inflammatory condition of the lung primarily affecting the small air sacs known as alveoli.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Measles",
"Pneumonia"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3205,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
27674
|
Skottie Young has never drawn covers for books, however he wrote and drew a Rocket Raccoon solo series for Marvel Comics starting in June 2016.
|
{
"evidence": [
"Skottie Young_sentence_6",
"Skottie Young_sentence_9"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nSkottie Young has never drawn covers for books, however he wrote and drew a Rocket Raccoon solo series for Marvel Comics starting in June 2016.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Skottie Young_sentence_6",
"Skottie Young_sentence_9"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3206,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.142",
"value": "?search="
},
{
"operation": "search",
"time": "12.156",
"value": "Skottie Young"
},
{
"operation": "Now on",
"time": "12.969",
"value": "Skottie Young"
},
{
"operation": "Highlighting",
"time": "24.818",
"value": "Skottie Young_sentence_6"
},
{
"operation": "Highlighting",
"time": "30.177",
"value": "Skottie Young_sentence_9"
},
{
"operation": "finish",
"time": "65.401",
"value": "finish"
}
]
}
|
exfever_4305
|
Black Eyed Peas were the highest earning hip hop group in America.
|
{
"evidence": [
"The Black Eyed Peas",
"Alternative hip hop"
],
"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 Eyed Peas were the highest earning hip hop group in America.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Black Eyed Peas",
"Alternative hip hop"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3207,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4660
|
Doctor Who Series 10 holds a 88% approval rating on online reviews.
|
{
"evidence": [
"Doctor Who (series 10)",
"Doctor Who"
],
"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:\nDoctor Who Series 10 holds a 88% approval rating on online reviews.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Doctor Who (series 10)",
"Doctor Who"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3208,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
19932
|
The RBM8A, which was thought to have two genes encoding the protein, is associated with spliced mRNAs.
|
{
"evidence": [
"RBM8A_sentence_5",
"RBM8A_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 RBM8A, which was thought to have two genes encoding the protein, is associated with spliced mRNAs.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"RBM8A_sentence_5",
"RBM8A_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3209,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.886",
"value": "?search="
},
{
"operation": "search",
"time": "12.862",
"value": "RBM8A"
},
{
"operation": "Now on",
"time": "13.884",
"value": "RBM8A"
},
{
"operation": "Highlighting",
"time": "46.565",
"value": "RBM8A_sentence_5"
},
{
"operation": "Highlighting",
"time": "55.034",
"value": "RBM8A_sentence_3"
},
{
"operation": "finish",
"time": "96.3",
"value": "finish"
}
]
}
|
11951
|
Fonogram 2007 winner Magdi Ruzsa, outvoting five other artists, represented Hungary in the Eurovision Song Contest 2007 with the song Unsubstantial Blues.
|
{
"evidence": [
"Magdi Rúzsa_sentence_2",
"Magdi Rúzsa_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:\nFonogram 2007 winner Magdi Ruzsa, outvoting five other artists, represented Hungary in the Eurovision Song Contest 2007 with the song Unsubstantial Blues.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Magdi Rúzsa_sentence_2",
"Magdi Rúzsa_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3210,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1",
"value": "?search="
},
{
"operation": "search",
"time": "22.976",
"value": "Magdi Rúzsa"
},
{
"operation": "Now on",
"time": "24.301",
"value": "Magdi Rúzsa"
},
{
"operation": "Highlighting",
"time": "42.793",
"value": "Magdi Rúzsa_sentence_2"
},
{
"operation": "Highlighting",
"time": "51.56",
"value": "Magdi Rúzsa_sentence_3"
},
{
"operation": "hyperlink",
"time": "87.872",
"value": "Fonogram Hungarian Music Awards"
},
{
"operation": "Now on",
"time": "88.75",
"value": "Hungarian Music Awards"
},
{
"operation": "finish",
"time": "103.805",
"value": "finish"
}
]
}
|
exfever_2461
|
Calvin Harris is a DJ and record producer who released his first studio album, 18 Months, which involves more dance music in a broad range of percussive electronic music genres made largely for nightclubs.
|
{
"evidence": [
"Calvin Harris",
"Electronic dance music"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nCalvin Harris is a DJ and record producer who released his first studio album, 18 Months, which involves more dance music in a broad range of percussive electronic music genres made largely for nightclubs.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Calvin Harris",
"Electronic dance music"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3211,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3159
|
Andorra is a sovereign nearshore microstate on the Iberian Peninsula and the people are a Romance ethnic group of originally a descent that speaks Western Romance language derived from Vulgar Latin.
|
{
"evidence": [
"Andorra",
"Catalan language"
],
"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:\nAndorra is a sovereign nearshore microstate on the Iberian Peninsula and the people are a Romance ethnic group of originally a descent that speaks Western Romance language derived from Vulgar Latin.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Andorra",
"Catalan language"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3212,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1423
|
Zhou Enlai was the first Premier of the People's Republic of China who served under Chairman Mao, a Chinese communist revolutionary who was the founder of the People's Republic of China.
|
{
"evidence": [
"Zhou Enlai",
"Mao Zedong"
],
"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:\nZhou Enlai was the first Premier of the People's Republic of China who served under Chairman Mao, a Chinese communist revolutionary who was the founder of the People's Republic of China.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Zhou Enlai",
"Mao Zedong"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3213,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
64029
|
Nacereddine Khoualed (born 1986 in Biskra, Algeria) is an Algerian football defense player who plays for US Biskra has been capped for Algeria at the Under-20.
|
{
"evidence": [
"Nacereddine Khoualed_sentence_0",
"Nacereddine Khoualed_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:\nNacereddine Khoualed (born 1986 in Biskra, Algeria) is an Algerian football defense player who plays for US Biskra has been capped for Algeria at the Under-20.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Nacereddine Khoualed_sentence_0",
"Nacereddine Khoualed_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3214,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "4.224",
"value": "?search="
},
{
"operation": "search",
"time": "9.079",
"value": "Nacereddine Khoualed"
},
{
"operation": "Now on",
"time": "9.785",
"value": "Nacereddine Khoualed"
},
{
"operation": "Highlighting",
"time": "38.236",
"value": "Nacereddine Khoualed_sentence_0"
},
{
"operation": "Highlighting",
"time": "48.653",
"value": "Nacereddine Khoualed_sentence_1"
},
{
"operation": "finish",
"time": "63.949",
"value": "finish"
}
]
}
|
52890
|
Among the factors which could have led to the Conservatives losing seats in the Isle of Wight council are the recent reforms on the Isle of Wight.
|
{
"evidence": [
"2009 Isle of Wight Council election_sentence_4",
"2009 Isle of Wight Council election_sentence_5"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAmong the factors which could have led to the Conservatives losing seats in the Isle of Wight council are the recent reforms on the Isle of Wight.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"2009 Isle of Wight Council election_sentence_4",
"2009 Isle of Wight Council election_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3215,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.318",
"value": "?search="
},
{
"operation": "search",
"time": "17.54",
"value": "Contains...Among the factors which could have led to the Conservatives losing seats in the Isle of Wight council are the recent reforms on the Isle of Wight."
},
{
"operation": "Now on",
"time": "19.806",
"value": "undefined"
},
{
"operation": "search",
"time": "35.36",
"value": "Contains...reforms on the Isle of Wight"
},
{
"operation": "Now on",
"time": "36.924",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "47.192",
"value": "Education reforms on the Isle of Wight"
},
{
"operation": "Now on",
"time": "47.733",
"value": "Education reforms on the Isle of Wight"
},
{
"operation": "Page search",
"time": "89.542",
"value": "conservative"
},
{
"operation": "search",
"time": "130.376",
"value": "2009 Isle of Wight Council election"
},
{
"operation": "Now on",
"time": "133.747",
"value": "2009 Isle of Wight Council election"
},
{
"operation": "Highlighting",
"time": "160.731",
"value": "2009 Isle of Wight Council election_sentence_4"
},
{
"operation": "Highlighting",
"time": "162.337",
"value": "2009 Isle of Wight Council election_sentence_5"
},
{
"operation": "finish",
"time": "173.971",
"value": "finish"
}
]
}
|
27534
|
Rapid economic development in Hong Kong during the 1970s is attributed to a surge in the labor force.
|
{
"evidence": [
"1970s in Hong Kong_sentence_0",
"1970s in Hong Kong_sentence_1",
"1970s in Hong Kong_sentence_94"
],
"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:\nRapid economic development in Hong Kong during the 1970s is attributed to a surge in the labor force.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"1970s in Hong Kong_sentence_0",
"1970s in Hong Kong_sentence_1",
"1970s in Hong Kong_sentence_94"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3216,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.067",
"value": "?search="
},
{
"operation": "search",
"time": "60.984",
"value": "Economy of Hong Kong"
},
{
"operation": "Now on",
"time": "62.71",
"value": "Economy of Hong Kong"
},
{
"operation": "Page search",
"time": "118.551",
"value": "Rapid economic development"
},
{
"operation": "search",
"time": "141.74",
"value": "Rapid economic development in Hong Kong during the 1970s is attributed to a surge in the labor force"
},
{
"operation": "Now on",
"time": "145.019",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "223.249",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "223.817",
"value": "Economy of Hong Kong"
},
{
"operation": "Page search",
"time": "230.858",
"value": "1970s"
},
{
"operation": "search",
"time": "259.317",
"value": "1970s in Hong Kong"
},
{
"operation": "Now on",
"time": "260.729",
"value": "1970s in Hong Kong"
},
{
"operation": "Highlighting",
"time": "264.728",
"value": "1970s in Hong Kong_sentence_0"
},
{
"operation": "Highlighting",
"time": "266.217",
"value": "1970s in Hong Kong_sentence_1"
},
{
"operation": "Page search",
"time": "283.065",
"value": "economic development"
},
{
"operation": "Page search",
"time": "301.051",
"value": "labor"
},
{
"operation": "hyperlink",
"time": "356.672",
"value": "5 Economy 1970s in Hong Kong_section_13"
},
{
"operation": "Highlighting",
"time": "390.386",
"value": "1970s in Hong Kong_sentence_94"
},
{
"operation": "finish",
"time": "409.964",
"value": "finish"
}
]
}
|
exfever_535
|
Alicia Augello Cook is an American singer, and songwriter signed with Arista Records and later released her debut album, Songs in A Minor, with an Australian record label owned and operated by Bertelsmann Music Group.
|
{
"evidence": [
"Alicia Keys",
"J Records"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAlicia Augello Cook is an American singer, and songwriter signed with Arista Records and later released her debut album, Songs in A Minor, with an Australian record label owned and operated by Bertelsmann Music Group.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Alicia Keys",
"J Records"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3217,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5560
|
Robert Arum is an American lawyer and boxing promoter who was employed as a person who practices law.
|
{
"evidence": [
"Bob Arum",
"Lawyer"
],
"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:\nRobert Arum is an American lawyer and boxing promoter who was employed as a person who practices law.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Bob Arum",
"Lawyer"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3218,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
6339
|
Rogue Pictures was formed as a division of PolyGram Pictures but after Universal Pictures (an American film studio owned by Comcast through the NBCUniversal Film and Entertainment) bought PolyGram, it was revived as part of Universal-owned Focus Features.
|
{
"evidence": [
"Rogue Pictures_sentence_6",
"Rogue Pictures_sentence_7",
"Universal Pictures_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:\nRogue Pictures was formed as a division of PolyGram Pictures but after Universal Pictures (an American film studio owned by Comcast through the NBCUniversal Film and Entertainment) bought PolyGram, it was revived as part of Universal-owned Focus Features.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Rogue Pictures_sentence_6",
"Rogue Pictures_sentence_7",
"Universal Pictures_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3219,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.053",
"value": "?search="
},
{
"operation": "search",
"time": "8.63",
"value": "Rogue Pictures"
},
{
"operation": "Now on",
"time": "10.216",
"value": "Rogue Pictures"
},
{
"operation": "Highlighting",
"time": "851.348",
"value": "Rogue Pictures_sentence_6"
},
{
"operation": "Highlighting",
"time": "864.624",
"value": "Rogue Pictures_sentence_7"
},
{
"operation": "hyperlink",
"time": "870.186",
"value": "Universal Pictures"
},
{
"operation": "Now on",
"time": "871.48",
"value": "Universal Pictures"
},
{
"operation": "Highlighting",
"time": "880.287",
"value": "Universal Pictures_sentence_3"
},
{
"operation": "finish",
"time": "887.356",
"value": "finish"
}
]
}
|
11711
|
Starting in 1907, Julia Evangeline Brooks was one of nine women who wrote a constitution, motto, chose colors and created a name for the first African-American sorority that was ncorporated in 1913.
|
{
"evidence": [
"Julia Evangeline Brooks_sentence_0",
"Julia Evangeline Brooks_sentence_19",
"Alpha Kappa Alpha_sentence_0",
"Alpha Kappa Alpha_sentence_16",
"Alpha Kappa Alpha_sentence_17",
"Alpha Kappa Alpha_sentence_12"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nStarting in 1907, Julia Evangeline Brooks was one of nine women who wrote a constitution, motto, chose colors and created a name for the first African-American sorority that was ncorporated in 1913.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Julia Evangeline Brooks_sentence_0",
"Julia Evangeline Brooks_sentence_19",
"Alpha Kappa Alpha_sentence_0",
"Alpha Kappa Alpha_sentence_16",
"Alpha Kappa Alpha_sentence_17",
"Alpha Kappa Alpha_sentence_12"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3220,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "3.315",
"value": "?search="
},
{
"operation": "search",
"time": "13.363",
"value": "Julia Evangeline Brooks"
},
{
"operation": "Now on",
"time": "17.906",
"value": "Julia Evangeline Brooks"
},
{
"operation": "Highlighting",
"time": "60.563",
"value": "Julia Evangeline Brooks_sentence_0"
},
{
"operation": "Highlighting",
"time": "91.178",
"value": "Julia Evangeline Brooks_sentence_19"
},
{
"operation": "Highlighting",
"time": "103.178",
"value": "Julia Evangeline Brooks_sentence_18"
},
{
"operation": "Highlighting deleted",
"time": "110.538",
"value": "Julia Evangeline Brooks_sentence_18"
},
{
"operation": "hyperlink",
"time": "118.659",
"value": "Alpha Kappa Alpha"
},
{
"operation": "Now on",
"time": "128.459",
"value": "Alpha Kappa Alpha"
},
{
"operation": "Highlighting",
"time": "130.491",
"value": "Alpha Kappa Alpha_sentence_0"
},
{
"operation": "Highlighting",
"time": "192.723",
"value": "Alpha Kappa Alpha_sentence_16"
},
{
"operation": "Highlighting",
"time": "196.402",
"value": "Alpha Kappa Alpha_sentence_17"
},
{
"operation": "Highlighting",
"time": "227.235",
"value": "Alpha Kappa Alpha_sentence_12"
},
{
"operation": "finish",
"time": "311.978",
"value": "finish"
}
]
}
|
exfever_8687
|
Nineteen Eighty-Four is a dystopian social science fiction novel that centers on the consequences of a form of government and a political system that prohibits all opposition events, often led by a political leader who possesses absolute power.
|
{
"evidence": [
"Nineteen Eighty-Four",
"Totalitarianism",
"Dictator"
],
"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:\nNineteen Eighty-Four is a dystopian social science fiction novel that centers on the consequences of a form of government and a political system that prohibits all opposition events, often led by a political leader who possesses absolute power.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Nineteen Eighty-Four",
"Totalitarianism",
"Dictator"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3221,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
16977
|
Goffers Knoll is a prominent knoll on the Hertfordshire-Cambridgeshire border formed from a spur of the chalk uplands and stands 60m above sea level visible from the A505 road (majority of the road is flat).
|
{
"evidence": [
"Goffers Knoll_sentence_0",
"Goffers Knoll_sentence_1",
"Goffers Knoll_sentence_2",
"A505 road_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:\nGoffers Knoll is a prominent knoll on the Hertfordshire-Cambridgeshire border formed from a spur of the chalk uplands and stands 60m above sea level visible from the A505 road (majority of the road is flat).\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Goffers Knoll_sentence_0",
"Goffers Knoll_sentence_1",
"Goffers Knoll_sentence_2",
"A505 road_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3222,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.999",
"value": "?search="
},
{
"operation": "search",
"time": "10.955",
"value": "Goffers Knoll"
},
{
"operation": "Now on",
"time": "11.632",
"value": "Goffers Knoll"
},
{
"operation": "Highlighting",
"time": "20.01",
"value": "Goffers Knoll_sentence_0"
},
{
"operation": "Highlighting",
"time": "25.425",
"value": "Goffers Knoll_sentence_1"
},
{
"operation": "Highlighting",
"time": "30.777",
"value": "Goffers Knoll_sentence_2"
},
{
"operation": "hyperlink",
"time": "34.08",
"value": "A505 road"
},
{
"operation": "Now on",
"time": "34.908",
"value": "A505 road"
},
{
"operation": "Highlighting",
"time": "40.624",
"value": "A505 road_sentence_2"
},
{
"operation": "finish",
"time": "48.074",
"value": "finish"
}
]
}
|
exfever_539
|
The Silence of the Lambs is a 1991 Canadian psychological horror film starring an American actor who played a serial killer, "Buffalo Bill".
|
{
"evidence": [
"The Silence of the Lambs (film)",
"Ted Levine"
],
"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 Silence of the Lambs is a 1991 Canadian psychological horror film starring an American actor who played a serial killer, \"Buffalo Bill\".\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Silence of the Lambs (film)",
"Ted Levine"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3223,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
7196
|
Jooseppi Mustakallio, born to chaplain Henrik Schwartzberg ja Laura Katariina Stenbäck, graduated from the Kuopio Lyceum in 1878, and was ordained a minister in 1889.
|
{
"evidence": [
"Jooseppi Mustakallio_sentence_3",
"Jooseppi Mustakallio_sentence_4",
"Jooseppi Mustakallio_sentence_6"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJooseppi Mustakallio, born to chaplain Henrik Schwartzberg ja Laura Katariina Stenbäck, graduated from the Kuopio Lyceum in 1878, and was ordained a minister in 1889.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jooseppi Mustakallio_sentence_3",
"Jooseppi Mustakallio_sentence_4",
"Jooseppi Mustakallio_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3224,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.052",
"value": "?search="
},
{
"operation": "search",
"time": "28.784",
"value": "Jooseppi Mustakallio"
},
{
"operation": "Now on",
"time": "29.628",
"value": "Jooseppi Mustakallio"
},
{
"operation": "Highlighting",
"time": "62.683",
"value": "Jooseppi Mustakallio_sentence_3"
},
{
"operation": "Highlighting",
"time": "71.394",
"value": "Jooseppi Mustakallio_sentence_4"
},
{
"operation": "Highlighting",
"time": "74.834",
"value": "Jooseppi Mustakallio_sentence_6"
},
{
"operation": "finish",
"time": "86.404",
"value": "finish"
}
]
}
|
64296
|
Harry Macdonald Kyle ( failed to graduate from University of St. Andrews founded in 1413) became alienated from his wife and children, but reconciled with one of his sisters later in life, everything is known about his later life.
|
{
"evidence": [
"Harry Macdonald Kyle_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:\nHarry Macdonald Kyle ( failed to graduate from University of St. Andrews founded in 1413) became alienated from his wife and children, but reconciled with one of his sisters later in life, everything is known about his later life.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Harry Macdonald Kyle_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3225,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.336",
"value": "?search="
},
{
"operation": "search",
"time": "18.962",
"value": "Harry Macdonald Kyle"
},
{
"operation": "Now on",
"time": "19.77",
"value": "Harry Macdonald Kyle"
},
{
"operation": "Highlighting",
"time": "25.391",
"value": "Harry Macdonald Kyle_sentence_1"
},
{
"operation": "finish",
"time": "34.817",
"value": "finish"
}
]
}
|
exfever_4403
|
Silicon is a chemical element with the symbol Al and atomic number 13 and has a great affinity toward the chemical element with the symbol O and atomic number 8.
|
{
"evidence": [
"Aluminium",
"Oxygen"
],
"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:\nSilicon is a chemical element with the symbol Al and atomic number 13 and has a great affinity toward the chemical element with the symbol O and atomic number 8.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Aluminium",
"Oxygen"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3226,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
45186
|
Brown Bear Seamount, part of the Cobb-Eickelberg Seamount chain which is a range of undersea mountains located in the Pacific Ocean, is separated in two areas, the Northwestern and Southern side.
|
{
"evidence": [
"Brown Bear Seamount_sentence_1",
"Cobb–Eickelberg Seamount chain_sentence_0",
"Cobb–Eickelberg Seamount chain_sentence_4",
"Brown Bear Seamount_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:\nBrown Bear Seamount, part of the Cobb-Eickelberg Seamount chain which is a range of undersea mountains located in the Pacific Ocean, is separated in two areas, the Northwestern and Southern side.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Brown Bear Seamount_sentence_1",
"Cobb–Eickelberg Seamount chain_sentence_0",
"Cobb–Eickelberg Seamount chain_sentence_4",
"Brown Bear Seamount_sentence_4"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3227,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.931",
"value": "?search="
},
{
"operation": "search",
"time": "8.792",
"value": "Brown Bear Seamount"
},
{
"operation": "Now on",
"time": "9.519",
"value": "Brown Bear Seamount"
},
{
"operation": "hyperlink",
"time": "45.487",
"value": "Bear Seamount"
},
{
"operation": "Now on",
"time": "46.243",
"value": "Bear Seamount"
},
{
"operation": "back-button-clicked",
"time": "76.211",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "76.313",
"value": "Brown Bear Seamount"
},
{
"operation": "Highlighting",
"time": "81.915",
"value": "Brown Bear Seamount_sentence_1"
},
{
"operation": "hyperlink",
"time": "92.245",
"value": "Cobb hotspot"
},
{
"operation": "Now on",
"time": "93.056",
"value": "Cobb hotspot"
},
{
"operation": "hyperlink",
"time": "102.921",
"value": "Cobb-Eicklberg seamount chain"
},
{
"operation": "Now on",
"time": "104.118",
"value": "Cobb–Eickelberg Seamount chain"
},
{
"operation": "Highlighting",
"time": "110.956",
"value": "Cobb–Eickelberg Seamount chain_sentence_0"
},
{
"operation": "Highlighting",
"time": "123.027",
"value": "Cobb–Eickelberg Seamount chain_sentence_4"
},
{
"operation": "hyperlink",
"time": "126.864",
"value": "Brown Bear"
},
{
"operation": "Now on",
"time": "127.275",
"value": "Brown Bear Seamount"
},
{
"operation": "hyperlink",
"time": "152.913",
"value": "ocean spreading"
},
{
"operation": "Now on",
"time": "155.129",
"value": "Mid-ocean ridge"
},
{
"operation": "back-button-clicked",
"time": "171.581",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "171.685",
"value": "Brown Bear Seamount"
},
{
"operation": "Highlighting",
"time": "173.781",
"value": "Brown Bear Seamount_sentence_4"
},
{
"operation": "finish",
"time": "189.511",
"value": "finish"
}
]
}
|
39502
|
The Tivoli Provisioning Manager's actions are fully automated and need only minimal supervision from humans.
|
{
"evidence": [
"Tivoli Provisioning Manager_sentence_1",
"Tivoli Provisioning Manager_sentence_2",
"Hypervisor_sentence_0",
"Tivoli Provisioning Manager_sentence_10",
"Tivoli Provisioning Manager_sentence_11",
"Tivoli Provisioning Manager_sentence_15",
"Tivoli Provisioning Manager_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:\nThe Tivoli Provisioning Manager's actions are fully automated and need only minimal supervision from humans.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Tivoli Provisioning Manager_sentence_1",
"Tivoli Provisioning Manager_sentence_2",
"Hypervisor_sentence_0",
"Tivoli Provisioning Manager_sentence_10",
"Tivoli Provisioning Manager_sentence_11",
"Tivoli Provisioning Manager_sentence_15",
"Tivoli Provisioning Manager_sentence_16"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3228,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.624",
"value": "?search="
},
{
"operation": "search",
"time": "9.674",
"value": "Tivoli Provisioning Manager"
},
{
"operation": "Now on",
"time": "11.237",
"value": "Tivoli Provisioning Manager"
},
{
"operation": "Page search",
"time": "38.58",
"value": "auto"
},
{
"operation": "Page search",
"time": "62.853",
"value": "supervis"
},
{
"operation": "Page search",
"time": "72.628",
"value": "human"
},
{
"operation": "hyperlink",
"time": "79.454",
"value": "Tivoli Software"
},
{
"operation": "Now on",
"time": "80.599",
"value": "Tivoli Software"
},
{
"operation": "hyperlink",
"time": "101.697",
"value": "Tivoli Provisioning Manager"
},
{
"operation": "Now on",
"time": "102.975",
"value": "Tivoli Provisioning Manager"
},
{
"operation": "Highlighting",
"time": "105.265",
"value": "Tivoli Provisioning Manager_sentence_1"
},
{
"operation": "Highlighting",
"time": "109.505",
"value": "Tivoli Provisioning Manager_sentence_2"
},
{
"operation": "hyperlink",
"time": "114.652",
"value": "hypervisors"
},
{
"operation": "Now on",
"time": "116.396",
"value": "Hypervisor"
},
{
"operation": "Highlighting",
"time": "118.983",
"value": "Hypervisor_sentence_0"
},
{
"operation": "back-button-clicked",
"time": "122.388",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "122.518",
"value": "Tivoli Provisioning Manager"
},
{
"operation": "Highlighting",
"time": "143.552",
"value": "Tivoli Provisioning Manager_sentence_10"
},
{
"operation": "Highlighting",
"time": "149.138",
"value": "Tivoli Provisioning Manager_sentence_11"
},
{
"operation": "Highlighting",
"time": "160.508",
"value": "Tivoli Provisioning Manager_sentence_15"
},
{
"operation": "Highlighting",
"time": "161.565",
"value": "Tivoli Provisioning Manager_sentence_16"
},
{
"operation": "hyperlink",
"time": "170.638",
"value": "Tivoli Software"
},
{
"operation": "Now on",
"time": "171.458",
"value": "Tivoli Software"
},
{
"operation": "back-button-clicked",
"time": "185.342",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "185.479",
"value": "Tivoli Provisioning Manager"
},
{
"operation": "finish",
"time": "217.02",
"value": "finish"
}
]
}
|
89350
|
Or83b's function is only one, that is, to interact with specific odor stimuli independently of other odorant receptors (ORs).
|
{
"evidence": [
"Or83b odorant receptor_sentence_2",
"Or83b odorant receptor_sentence_3",
"Or83b odorant receptor_sentence_4",
"Or83b odorant receptor_sentence_5"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nOr83b's function is only one, that is, to interact with specific odor stimuli independently of other odorant receptors (ORs).\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Or83b odorant receptor_sentence_2",
"Or83b odorant receptor_sentence_3",
"Or83b odorant receptor_sentence_4",
"Or83b odorant receptor_sentence_5"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3229,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.342",
"value": "?search="
},
{
"operation": "search",
"time": "9.038",
"value": "Or83b odorant receptor"
},
{
"operation": "Now on",
"time": "10.184",
"value": "Or83b odorant receptor"
},
{
"operation": "Highlighting",
"time": "22.746",
"value": "Or83b odorant receptor_sentence_4"
},
{
"operation": "Highlighting",
"time": "40.174",
"value": "Or83b odorant receptor_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "44.846",
"value": "Or83b odorant receptor_sentence_4"
},
{
"operation": "Highlighting",
"time": "45.534",
"value": "Or83b odorant receptor_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "48.524",
"value": "Or83b odorant receptor_sentence_5"
},
{
"operation": "Highlighting",
"time": "49.182",
"value": "Or83b odorant receptor_sentence_3"
},
{
"operation": "Highlighting",
"time": "49.886",
"value": "Or83b odorant receptor_sentence_4"
},
{
"operation": "Highlighting",
"time": "50.43",
"value": "Or83b odorant receptor_sentence_5"
},
{
"operation": "finish",
"time": "56.486",
"value": "finish"
}
]
}
|
20569
|
In March 2017, three adolescents accused Arunabh Kumar of sexual harassment and he was booked by police for molestation on March 29, 2017.
|
{
"evidence": [
"Arunabh Kumar_sentence_8",
"Arunabh Kumar_sentence_10",
"Arunabh Kumar_sentence_12",
"Arunabh Kumar_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:\nIn March 2017, three adolescents accused Arunabh Kumar of sexual harassment and he was booked by police for molestation on March 29, 2017.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Arunabh Kumar_sentence_8",
"Arunabh Kumar_sentence_10",
"Arunabh Kumar_sentence_12",
"Arunabh Kumar_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3230,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.642",
"value": "?search="
},
{
"operation": "search",
"time": "90.066",
"value": "Arunabh Kumar"
},
{
"operation": "Now on",
"time": "95.144",
"value": "?search="
},
{
"operation": "search",
"time": "98.327",
"value": "Arunabh Kumar"
},
{
"operation": "Now on",
"time": "98.763",
"value": "Arunabh Kumar"
},
{
"operation": "Page search",
"time": "199.986",
"value": "adolescents"
},
{
"operation": "Highlighting",
"time": "279.687",
"value": "Arunabh Kumar_sentence_8"
},
{
"operation": "Highlighting",
"time": "283.841",
"value": "Arunabh Kumar_sentence_9"
},
{
"operation": "Highlighting",
"time": "289.708",
"value": "Arunabh Kumar_sentence_10"
},
{
"operation": "Highlighting",
"time": "300.102",
"value": "Arunabh Kumar_sentence_11"
},
{
"operation": "Highlighting",
"time": "302.337",
"value": "Arunabh Kumar_sentence_12"
},
{
"operation": "Highlighting",
"time": "324.148",
"value": "Arunabh Kumar_sentence_1"
},
{
"operation": "hyperlink",
"time": "349.809",
"value": "The Viral Fever"
},
{
"operation": "Now on",
"time": "350.535",
"value": "The Viral Fever"
},
{
"operation": "Page search",
"time": "355.669",
"value": "adolescents"
},
{
"operation": "back-button-clicked",
"time": "392.801",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "392.848",
"value": "Arunabh Kumar"
},
{
"operation": "Highlighting deleted",
"time": "416.318",
"value": "Arunabh Kumar_sentence_9"
},
{
"operation": "Highlighting deleted",
"time": "425.667",
"value": "Arunabh Kumar_sentence_11"
},
{
"operation": "finish",
"time": "437.145",
"value": "finish"
}
]
}
|
exfever_1011
|
Bryan Lee Cranston is an Italian actor known for portraying Hal in Malcolm in the Middle, which was broadcasted on an American commercial broadcast television network headquartered in New York City.
|
{
"evidence": [
"Bryan Cranston",
"Fox Broadcasting Company"
],
"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:\nBryan Lee Cranston is an Italian actor known for portraying Hal in Malcolm in the Middle, which was broadcasted on an American commercial broadcast television network headquartered in New York City.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Bryan Cranston",
"Fox Broadcasting Company"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3231,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3877
|
The Mozilla Foundation is also a partner of Knoxville Zoo.
|
{
"evidence": [
"Firefox",
"Mozilla Foundation"
],
"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 Mozilla Foundation is also a partner of Knoxville Zoo.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Firefox",
"Mozilla Foundation"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3232,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
32145
|
Maridjan led ceremonies to appease the spirits of the volcano, and one of his most important duties was the performance of the annual Labuhan sacrificial ceremony dedicated to the spirits of Mount Merapi.
|
{
"evidence": [
"Mbah Maridjan_sentence_8",
"Mbah Maridjan_sentence_9"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMaridjan led ceremonies to appease the spirits of the volcano, and one of his most important duties was the performance of the annual Labuhan sacrificial ceremony dedicated to the spirits of Mount Merapi.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Mbah Maridjan_sentence_8",
"Mbah Maridjan_sentence_9"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3233,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.14",
"value": "?search="
},
{
"operation": "search",
"time": "154.87",
"value": "Maridjan"
},
{
"operation": "Now on",
"time": "155.938",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "161.122",
"value": "Mbah Maridjan"
},
{
"operation": "Now on",
"time": "161.806",
"value": "Mbah Maridjan"
},
{
"operation": "Highlighting",
"time": "181.259",
"value": "Mbah Maridjan_sentence_8"
},
{
"operation": "Highlighting",
"time": "185.842",
"value": "Mbah Maridjan_sentence_9"
},
{
"operation": "finish",
"time": "222.1",
"value": "finish"
}
]
}
|
36229
|
Virginia State Route 5 has many major intersections, including Osborne Turnpike, S. Boundary Street, and W. Francis Street.
|
{
"evidence": [
"Virginia State Route 5_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:\nVirginia State Route 5 has many major intersections, including Osborne Turnpike, S. Boundary Street, and W. Francis Street.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Virginia State Route 5_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3234,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.036",
"value": "?search="
},
{
"operation": "Now on",
"time": "6.85",
"value": "?search="
},
{
"operation": "search",
"time": "16.219",
"value": "Virginia State Route 5"
},
{
"operation": "Now on",
"time": "17.098",
"value": "Virginia State Route 5"
},
{
"operation": "Page search",
"time": "89.721",
"value": "osborne"
},
{
"operation": "Page search",
"time": "157.945",
"value": "intersection"
},
{
"operation": "hyperlink",
"time": "183.586",
"value": "4 Major intersections Virginia State Route 5_section_3"
},
{
"operation": "Highlighting",
"time": "214.181",
"value": "Virginia State Route 5_sentence_0"
},
{
"operation": "finish",
"time": "219.483",
"value": "finish"
}
]
}
|
exfever_6982
|
WGBH-TV, virtual channel 2 is the secondary Public Broadcasting Service (PBS) member television station licensed to the 24th-most populous city in the USA.
|
{
"evidence": [
"WGBH-TV",
"Boston"
],
"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:\nWGBH-TV, virtual channel 2 is the secondary Public Broadcasting Service (PBS) member television station licensed to the 24th-most populous city in the USA.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"WGBH-TV",
"Boston"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3235,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
17398
|
Mario Hirsch (born 6 April 1949 in Luxembourg City) is a Luxembourgian political scientist and journalist receiving his PhD at Fondation Nationale des Sciences Politiques and when Luxembourg held the Presidency of the Council of the European Union in the second half of 1997 Hirsch worked with Miguel Angel Moratinos, the European Union Special Representative for the Middle East Peace Process, as the president's liaison officer.
|
{
"evidence": [
"Mario Hirsch_sentence_0",
"Mario Hirsch_sentence_1",
"Mario Hirsch_sentence_8"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nMario Hirsch (born 6 April 1949 in Luxembourg City) is a Luxembourgian political scientist and journalist receiving his PhD at Fondation Nationale des Sciences Politiques and when Luxembourg held the Presidency of the Council of the European Union in the second half of 1997 Hirsch worked with Miguel Angel Moratinos, the European Union Special Representative for the Middle East Peace Process, as the president's liaison officer.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Mario Hirsch_sentence_0",
"Mario Hirsch_sentence_1",
"Mario Hirsch_sentence_8"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3236,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.736",
"value": "?search="
},
{
"operation": "search",
"time": "8.405",
"value": "Mario Hirsch"
},
{
"operation": "Now on",
"time": "30.098",
"value": "Mario Hirsch"
},
{
"operation": "search",
"time": "883.509",
"value": "Mario Hirsch"
},
{
"operation": "Now on",
"time": "884.896",
"value": "Mario Hirsch"
},
{
"operation": "Highlighting",
"time": "923.627",
"value": "Mario Hirsch_sentence_0"
},
{
"operation": "Highlighting",
"time": "948.447",
"value": "Mario Hirsch_sentence_1"
},
{
"operation": "Highlighting",
"time": "965.83",
"value": "Mario Hirsch_sentence_8"
},
{
"operation": "finish",
"time": "982.356",
"value": "finish"
}
]
}
|
exfever_8581
|
Toy Story is a 1995 American computer-animated funny film which emphasizes on humor to make the audience laugh.
|
{
"evidence": [
"Toy Story",
"Comedy film"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nToy Story is a 1995 American computer-animated funny film which emphasizes on humor to make the audience laugh.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Toy Story",
"Comedy film"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3237,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
30466
|
The routes within the scope of this article spring westward from Salisbury, which was reached from Waterloo station in London, 84 miles away; then from Salisbury, the main line continued broadly west, passing no major population centre until reaching Exeter.
|
{
"evidence": [
"Southern Railway routes west of Salisbury_sentence_2",
"Southern Railway routes west of Salisbury_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 routes within the scope of this article spring westward from Salisbury, which was reached from Waterloo station in London, 84 miles away; then from Salisbury, the main line continued broadly west, passing no major population centre until reaching Exeter.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Southern Railway routes west of Salisbury_sentence_2",
"Southern Railway routes west of Salisbury_sentence_3"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3238,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.169",
"value": "?search="
},
{
"operation": "search",
"time": "67.312",
"value": "Contains...The routes within the scope of this article spring westward from Salisbury, which was reached from Waterloo station in London, 84 miles away"
},
{
"operation": "Now on",
"time": "70.876",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "73.642",
"value": "Southern Railway routes west of Salisbury"
},
{
"operation": "Now on",
"time": "74.667",
"value": "Southern Railway routes west of Salisbury"
},
{
"operation": "Page search",
"time": "338.938",
"value": "spring westward"
},
{
"operation": "Highlighting",
"time": "346.171",
"value": "Southern Railway routes west of Salisbury_sentence_2"
},
{
"operation": "Highlighting",
"time": "362.934",
"value": "Southern Railway routes west of Salisbury_sentence_3"
},
{
"operation": "finish",
"time": "422.531",
"value": "finish"
}
]
}
|
74451
|
The United States required almost 19,000 tonnes of uranium between 2006 and 2008 while France required over 10,000 tonnes during the same time.
|
{
"evidence": [
"Peak uranium_sentence_46"
],
"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 United States required almost 19,000 tonnes of uranium between 2006 and 2008 while France required over 10,000 tonnes during the same time.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Peak uranium_sentence_46"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3239,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.314",
"value": "?search="
},
{
"operation": "search",
"time": "86.895",
"value": "Uranium mining"
},
{
"operation": "Now on",
"time": "88.761",
"value": "Uranium mining"
},
{
"operation": "Page search",
"time": "104.939",
"value": "france"
},
{
"operation": "hyperlink",
"time": "141.304",
"value": "Uranium mining by country"
},
{
"operation": "Now on",
"time": "144.171",
"value": "Uranium mining by country"
},
{
"operation": "Page search",
"time": "166.201",
"value": "france"
},
{
"operation": "hyperlink",
"time": "200.95",
"value": "List of countries by uranium production"
},
{
"operation": "Now on",
"time": "201.753",
"value": "List of countries by uranium production"
},
{
"operation": "back-button-clicked",
"time": "225.516",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "225.615",
"value": "Uranium mining by country"
},
{
"operation": "hyperlink",
"time": "228.406",
"value": "List of countries by uranium reserves"
},
{
"operation": "Now on",
"time": "229.286",
"value": "List of countries by uranium reserves"
},
{
"operation": "search",
"time": "282.198",
"value": "Contains...19,000 tonnes of uranium"
},
{
"operation": "Now on",
"time": "284.375",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "298.933",
"value": "Uranium mining"
},
{
"operation": "Now on",
"time": "299.187",
"value": "Uranium mining"
},
{
"operation": "Page search",
"time": "312.8",
"value": "19,000 tonnes"
},
{
"operation": "hyperlink",
"time": "340.444",
"value": "Uranium mining by country"
},
{
"operation": "Now on",
"time": "341.262",
"value": "Uranium mining by country"
},
{
"operation": "Page search",
"time": "345.825",
"value": "2006"
},
{
"operation": "search",
"time": "379",
"value": "Contains...uranium mining france"
},
{
"operation": "Now on",
"time": "381.298",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "390.762",
"value": "Uranium mining"
},
{
"operation": "Now on",
"time": "391.249",
"value": "Uranium mining"
},
{
"operation": "Page search",
"time": "395.65",
"value": "france"
},
{
"operation": "hyperlink",
"time": "460.522",
"value": "List of uranium mines"
},
{
"operation": "Now on",
"time": "476.577",
"value": "List of uranium projects"
},
{
"operation": "Page search",
"time": "484.475",
"value": "france"
},
{
"operation": "back-button-clicked",
"time": "508.99",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "509.092",
"value": "Uranium mining"
},
{
"operation": "hyperlink",
"time": "538.812",
"value": "Peak uranium"
},
{
"operation": "Now on",
"time": "540.784",
"value": "Peak uranium"
},
{
"operation": "Highlighting",
"time": "561.415",
"value": "Peak uranium_sentence_46"
},
{
"operation": "finish",
"time": "592.212",
"value": "finish"
}
]
}
|
29244
|
Lavinia Dock wrote two volumes of the History of Nursing and published Hygiene and Morality, which supported the treatment of venereal disease.
|
{
"evidence": [
"Lavinia Dock_sentence_22",
"Lavinia Dock_sentence_25"
],
"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:\nLavinia Dock wrote two volumes of the History of Nursing and published Hygiene and Morality, which supported the treatment of venereal disease.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Lavinia Dock_sentence_22",
"Lavinia Dock_sentence_25"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3240,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.999",
"value": "?search="
},
{
"operation": "search",
"time": "54.033",
"value": "Lavinia Dock"
},
{
"operation": "Now on",
"time": "54.667",
"value": "Lavinia Dock"
},
{
"operation": "Page search",
"time": "96.244",
"value": "nursing"
},
{
"operation": "Page search",
"time": "100.592",
"value": "wrote"
},
{
"operation": "Highlighting",
"time": "111.746",
"value": "Lavinia Dock_sentence_22"
},
{
"operation": "Page search",
"time": "140.599",
"value": "hygiene"
},
{
"operation": "Highlighting",
"time": "151.273",
"value": "Lavinia Dock_sentence_25"
},
{
"operation": "finish",
"time": "165.063",
"value": "finish"
}
]
}
|
53752
|
Brightling is a village in the England's Rother district and part in the High Weald Area of Outstanding Natural Beauty (one of England's finest landscape with 1461 square kilometers of land area).
|
{
"evidence": [
"Brightling_sentence_0",
"Brightling_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:\nBrightling is a village in the England's Rother district and part in the High Weald Area of Outstanding Natural Beauty (one of England's finest landscape with 1461 square kilometers of land area).\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Brightling_sentence_0",
"Brightling_sentence_2"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3241,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.039",
"value": "?search="
},
{
"operation": "search",
"time": "19.347",
"value": "Brightling"
},
{
"operation": "Now on",
"time": "21.219",
"value": "Brightling"
},
{
"operation": "Highlighting",
"time": "31.983",
"value": "Brightling_sentence_0"
},
{
"operation": "Highlighting",
"time": "61.035",
"value": "Brightling_sentence_2"
},
{
"operation": "search",
"time": "91.034",
"value": "Contains...High Weald Area of Outstanding Natural Beauty"
},
{
"operation": "Now on",
"time": "93.105",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "118.299",
"value": "High Weald Landscape Trail"
},
{
"operation": "Now on",
"time": "119.088",
"value": "High Weald Landscape Trail"
},
{
"operation": "search",
"time": "150.061",
"value": "AONB"
},
{
"operation": "Now on",
"time": "151.1",
"value": "Area of Outstanding Natural Beauty"
},
{
"operation": "hyperlink",
"time": "167.718",
"value": "7.1 England Area of Outstanding Natural Beauty_section_7"
},
{
"operation": "Page search",
"time": "208.508",
"value": "weald"
},
{
"operation": "hyperlink",
"time": "246.369",
"value": "National parks of England and Wales"
},
{
"operation": "Now on",
"time": "247.818",
"value": "National parks of the United Kingdom"
},
{
"operation": "search",
"time": "270.611",
"value": "aonbs of england"
},
{
"operation": "Now on",
"time": "272.716",
"value": "undefined"
},
{
"operation": "search",
"time": "294.042",
"value": "High Weald"
},
{
"operation": "Now on",
"time": "295.051",
"value": "Weald"
},
{
"operation": "hyperlink",
"time": "345.299",
"value": "Weald and Downland Open Air Museum"
},
{
"operation": "Now on",
"time": "350.532",
"value": "Weald and Downland Living Museum"
},
{
"operation": "search",
"time": "364.117",
"value": "high weald"
},
{
"operation": "Now on",
"time": "364.721",
"value": "High Weald"
},
{
"operation": "hyperlink",
"time": "403.781",
"value": "Recreational walks in Kent"
},
{
"operation": "Now on",
"time": "404.581",
"value": "Recreational walks in Kent"
},
{
"operation": "search",
"time": "427.292",
"value": "Contains...high weald"
},
{
"operation": "Now on",
"time": "428.886",
"value": "undefined"
},
{
"operation": "search",
"time": "473.067",
"value": "Contains...high weald aonb"
},
{
"operation": "Now on",
"time": "473.854",
"value": "undefined"
},
{
"operation": "search",
"time": "534.689",
"value": "Contains...one of England's finest landscape*"
},
{
"operation": "Now on",
"time": "537.844",
"value": "undefined"
},
{
"operation": "search",
"time": "568.614",
"value": "weald one of England's finest landscap*"
},
{
"operation": "Now on",
"time": "570.051",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "576.569",
"value": "A259 road"
},
{
"operation": "Now on",
"time": "600.627",
"value": "A259 road"
},
{
"operation": "back-button-clicked",
"time": "604.593",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "605.179",
"value": "undefined"
},
{
"operation": "finish",
"time": "641.382",
"value": "finish"
}
]
}
|
83479
|
English Turn Golf and Country Club was designed for a PGA Tour event, first won by Tim Simpson.
|
{
"evidence": [
"English Turn Golf and Country Club_sentence_1",
"English Turn Golf and Country Club_sentence_6"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nEnglish Turn Golf and Country Club was designed for a PGA Tour event, first won by Tim Simpson.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"English Turn Golf and Country Club_sentence_1",
"English Turn Golf and Country Club_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3242,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.065",
"value": "?search="
},
{
"operation": "search",
"time": "37.903",
"value": "Contains...English Turn Golf and Country Club"
},
{
"operation": "Now on",
"time": "40.941",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "49.103",
"value": "English Turn Golf and Country Club"
},
{
"operation": "Now on",
"time": "49.775",
"value": "English Turn Golf and Country Club"
},
{
"operation": "Highlighting",
"time": "58.947",
"value": "English Turn Golf and Country Club_sentence_1"
},
{
"operation": "Page search",
"time": "107.904",
"value": "tim simpson"
},
{
"operation": "Highlighting",
"time": "114.077",
"value": "English Turn Golf and Country Club_sentence_6"
},
{
"operation": "finish",
"time": "123.791",
"value": "finish"
}
]
}
|
exfever_6834
|
The Jackson family is an Indian family of musicians and entertainers from Gary, Indiana that form an American pop band founded in 1964 by Joe Jackson, as well as by brothers Jackie, Tito, and Jermaine, with younger brothers Marlon and Michael.
|
{
"evidence": [
"Jackson family",
"The Jackson 5"
],
"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 Jackson family is an Indian family of musicians and entertainers from Gary, Indiana that form an American pop band founded in 1964 by Joe Jackson, as well as by brothers Jackie, Tito, and Jermaine, with younger brothers Marlon and Michael.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jackson family",
"The Jackson 5"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3243,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7448
|
Tony Bill is an American actor who had a supporting role in a 1975 American satirical comedy-drama film directed by Hal Ashby.
|
{
"evidence": [
"Tony Bill",
"Shampoo (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:\nTony Bill is an American actor who had a supporting role in a 1975 American satirical comedy-drama film directed by Hal Ashby.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Tony Bill",
"Shampoo (film)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3244,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8193
|
Danielle Cormack is a New Zealand stage and screen actress who is known for her role as Shota in an American television series created by Sam Raimi.
|
{
"evidence": [
"Danielle Cormack",
"Legend of the Seeker"
],
"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:\nDanielle Cormack is a New Zealand stage and screen actress who is known for her role as Shota in an American television series created by Sam Raimi.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Danielle Cormack",
"Legend of the Seeker"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3245,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3710
|
Dennis Lee Hopper was an American actor and filmmaker who attended the?membership organization for professional actors, theatre directors, and playwrights.
|
{
"evidence": [
"Dennis Hopper",
"Actors Studio"
],
"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:\nDennis Lee Hopper was an American actor and filmmaker who attended the?membership organization for professional actors, theatre directors, and playwrights.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Dennis Hopper",
"Actors Studio"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3246,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_573
|
At fourteen years old, Taylor Swift pursued a career as a singer-songwriter whose genre of popular music originated with American folk music forms, including the term that is used to describe both the early folk or roots music traditions of rural Louisiana.
|
{
"evidence": [
"Taylor Swift (album)",
"Country music",
"Creole music"
],
"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:\nAt fourteen years old, Taylor Swift pursued a career as a singer-songwriter whose genre of popular music originated with American folk music forms, including the term that is used to describe both the early folk or roots music traditions of rural Louisiana.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Taylor Swift (album)",
"Country music",
"Creole music"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3247,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_680
|
Paul Simon began performing in his early teens with an American singer, poet, and actor who was ranked 86th in an American monthly magazine that focuses on music, politics, and popular culture.
|
{
"evidence": [
"Paul Simon",
"Art Garfunkel",
"Rolling Stone"
],
"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:\nPaul Simon began performing in his early teens with an American singer, poet, and actor who was ranked 86th in an American monthly magazine that focuses on music, politics, and popular culture.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Paul Simon",
"Art Garfunkel",
"Rolling Stone"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3248,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
43254
|
Earle Bradford Mayfield won the Democratic nomination to the US Senate in Texas in 1922 after challenging five-term US Senator Charles A. Culberson, who also served as the 21st Governor of Texas.
|
{
"evidence": [
"Earle Bradford Mayfield_sentence_12",
"Earle Bradford Mayfield_sentence_9",
"Charles Allen Culberson_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:\nEarle Bradford Mayfield won the Democratic nomination to the US Senate in Texas in 1922 after challenging five-term US Senator Charles A. Culberson, who also served as the 21st Governor of Texas.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Earle Bradford Mayfield_sentence_12",
"Earle Bradford Mayfield_sentence_9",
"Charles Allen Culberson_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3249,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.036",
"value": "?search="
},
{
"operation": "search",
"time": "20.544",
"value": "Earle Bradford Mayfield"
},
{
"operation": "Now on",
"time": "22.769",
"value": "Earle Bradford Mayfield"
},
{
"operation": "hyperlink",
"time": "34.258",
"value": "2.2 United States Senate Earle Bradford Mayfield_section_3"
},
{
"operation": "Highlighting",
"time": "55.042",
"value": "Earle Bradford Mayfield_sentence_12"
},
{
"operation": "Highlighting",
"time": "59.919",
"value": "Earle Bradford Mayfield_sentence_9"
},
{
"operation": "hyperlink",
"time": "75.645",
"value": "Charles A. Culberson"
},
{
"operation": "Now on",
"time": "76.542",
"value": "Charles Allen Culberson"
},
{
"operation": "Highlighting",
"time": "80.409",
"value": "Charles Allen Culberson_sentence_0"
},
{
"operation": "finish",
"time": "111.071",
"value": "finish"
}
]
}
|
exfever_2594
|
Macbeth is a love story by William Shakespeare, first published in the Comedies, Histories, & Tragedies, a collection of plays.
|
{
"evidence": [
"Macbeth",
"First Folio"
],
"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 love story by William Shakespeare, first published in the Comedies, Histories, & Tragedies, a collection of plays.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Macbeth",
"First Folio"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3250,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
22320
|
Russia produces the most raspberry's out of the five countries that produce it worldwide.
|
{
"evidence": [
"Raspberry_sentence_7"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nRussia produces the most raspberry's out of the five countries that produce it worldwide.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Raspberry_sentence_7"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3251,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.628",
"value": "?search="
},
{
"operation": "search",
"time": "35.633",
"value": "List of largest producing countries of agricultural commodities"
},
{
"operation": "Now on",
"time": "38.074",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "44.278",
"value": "Sanitary paper"
},
{
"operation": "Now on",
"time": "44.692",
"value": "Sanitary paper"
},
{
"operation": "search",
"time": "81.496",
"value": "Raspberry"
},
{
"operation": "Now on",
"time": "82.383",
"value": "Raspberry"
},
{
"operation": "Highlighting",
"time": "87.28",
"value": "Raspberry_sentence_7"
},
{
"operation": "search",
"time": "148.319",
"value": "List of largest producing countries of agricultural commodities"
},
{
"operation": "Now on",
"time": "149.554",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "154.453",
"value": "Make in India"
},
{
"operation": "Now on",
"time": "155.327",
"value": "Make in India"
},
{
"operation": "finish",
"time": "175.487",
"value": "finish"
}
]
}
|
exfever_3180
|
Isaac Liev Schreiber became known during the late 1990s and early 2000s after appearing in several film features that is produced outside the major film studio system.
|
{
"evidence": [
"Liev Schreiber",
"Independent 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:\nIsaac Liev Schreiber became known during the late 1990s and early 2000s after appearing in several film features that is produced outside the major film studio system.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Liev Schreiber",
"Independent film"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3252,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
13768
|
Oluwaseun Temitope Osewa is a Nigerian internet entrepreneur and founder of the popular internet forum, Nairaland.
|
{
"evidence": [
"Seun Osewa_sentence_0",
"Seun Osewa_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:\nOluwaseun Temitope Osewa is a Nigerian internet entrepreneur and founder of the popular internet forum, Nairaland.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Seun Osewa_sentence_0",
"Seun Osewa_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3253,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.015",
"value": "?search="
},
{
"operation": "search",
"time": "12.616",
"value": "Contains...Oluwaseun Temitope Osewa"
},
{
"operation": "Now on",
"time": "13.21",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "17.982",
"value": "Seun Osewa"
},
{
"operation": "Now on",
"time": "18.733",
"value": "Seun Osewa"
},
{
"operation": "Highlighting",
"time": "25.892",
"value": "Seun Osewa_sentence_0"
},
{
"operation": "Highlighting",
"time": "29.137",
"value": "Seun Osewa_sentence_1"
},
{
"operation": "finish",
"time": "50.582",
"value": "finish"
}
]
}
|
exfever_2241
|
The King and I is the seventh musical that premiered in Broadway's St. James Theatre.
|
{
"evidence": [
"The King and I",
"Musical theatre"
],
"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 King and I is the seventh musical that premiered in Broadway's St. James Theatre.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The King and I",
"Musical theatre"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3254,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
36323
|
Velous, a stage name based on a comment about his marvelous production skills, released his debut mixtape called Velocity The Mixtape in 2011 which only took success after a few years since its release.
|
{
"evidence": [
"Velous_sentence_0",
"Velous_sentence_13",
"Velous_sentence_14"
],
"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:\nVelous, a stage name based on a comment about his marvelous production skills, released his debut mixtape called Velocity The Mixtape in 2011 which only took success after a few years since its release.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Velous_sentence_0",
"Velous_sentence_13",
"Velous_sentence_14"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3255,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.026",
"value": "undefined"
},
{
"operation": "search",
"time": "8.977",
"value": "Velous"
},
{
"operation": "Now on",
"time": "10.067",
"value": "Velous"
},
{
"operation": "Highlighting",
"time": "13.31",
"value": "Velous_sentence_0"
},
{
"operation": "Highlighting",
"time": "48.883",
"value": "Velous_sentence_14"
},
{
"operation": "Highlighting deleted",
"time": "128.879",
"value": "Velous_sentence_14"
},
{
"operation": "Highlighting",
"time": "140.71",
"value": "Velous_sentence_13"
},
{
"operation": "Highlighting",
"time": "143.344",
"value": "Velous_sentence_14"
},
{
"operation": "finish",
"time": "147.269",
"value": "finish"
}
]
}
|
exfever_6245
|
Fred Trump was a member of the Singaporean and German-American family originating in modern Germany.
|
{
"evidence": [
"Fred Trump",
"Trump family"
],
"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:\nFred Trump was a member of the Singaporean and German-American family originating in modern Germany.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Fred Trump",
"Trump family"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3256,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
46130
|
Spanish footballer Ignacio Maganto played his your career at Getafe then went to the US and played for Iona where he made 41 goals and now plays for Union Adarve.
|
{
"evidence": [
"Ignacio Maganto_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:\nSpanish footballer Ignacio Maganto played his your career at Getafe then went to the US and played for Iona where he made 41 goals and now plays for Union Adarve.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Ignacio Maganto_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3257,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.069",
"value": "?search="
},
{
"operation": "search",
"time": "9.559",
"value": "Ignacio Maganto"
},
{
"operation": "Now on",
"time": "10.392",
"value": "Ignacio Maganto"
},
{
"operation": "Highlighting",
"time": "22.131",
"value": "Ignacio Maganto_sentence_0"
},
{
"operation": "Highlighting",
"time": "30.452",
"value": "Ignacio Maganto_header_cell_0_9_0"
},
{
"operation": "Highlighting",
"time": "32.437",
"value": "Ignacio Maganto_cell_0_9_1"
},
{
"operation": "Highlighting",
"time": "32.457",
"value": "Ignacio Maganto_header_cell_0_9_0"
},
{
"operation": "Highlighting",
"time": "32.457",
"value": "Ignacio Maganto_header_cell_0_8_0"
},
{
"operation": "Highlighting",
"time": "47.56",
"value": "Ignacio Maganto_header_cell_0_12_0"
},
{
"operation": "Highlighting",
"time": "49.843",
"value": "Ignacio Maganto_cell_0_12_1"
},
{
"operation": "Highlighting",
"time": "49.865",
"value": "Ignacio Maganto_header_cell_0_12_0"
},
{
"operation": "Highlighting",
"time": "49.865",
"value": "Ignacio Maganto_header_cell_0_10_0"
},
{
"operation": "Highlighting",
"time": "52.203",
"value": "Ignacio Maganto_cell_0_12_3"
},
{
"operation": "Highlighting",
"time": "71.518",
"value": "Ignacio Maganto_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "73.583",
"value": "Ignacio Maganto_cell_0_12_3"
},
{
"operation": "Highlighting deleted",
"time": "74.192",
"value": "Ignacio Maganto_cell_0_12_1"
},
{
"operation": "Highlighting deleted",
"time": "74.209",
"value": "Ignacio Maganto_header_cell_0_12_0"
},
{
"operation": "Highlighting deleted",
"time": "74.21",
"value": "Ignacio Maganto_header_cell_0_10_0"
},
{
"operation": "Highlighting deleted",
"time": "75.349",
"value": "Ignacio Maganto_cell_0_9_1"
},
{
"operation": "Highlighting deleted",
"time": "75.363",
"value": "Ignacio Maganto_header_cell_0_9_0"
},
{
"operation": "Highlighting deleted",
"time": "75.366",
"value": "Ignacio Maganto_header_cell_0_8_0"
},
{
"operation": "Highlighting",
"time": "76.632",
"value": "Ignacio Maganto_cell_0_9_1"
},
{
"operation": "Highlighting",
"time": "76.648",
"value": "Ignacio Maganto_header_cell_0_9_0"
},
{
"operation": "Highlighting",
"time": "76.648",
"value": "Ignacio Maganto_header_cell_0_8_0"
},
{
"operation": "Highlighting deleted",
"time": "77.357",
"value": "Ignacio Maganto_cell_0_9_1"
},
{
"operation": "Highlighting deleted",
"time": "77.373",
"value": "Ignacio Maganto_header_cell_0_9_0"
},
{
"operation": "Highlighting deleted",
"time": "77.375",
"value": "Ignacio Maganto_header_cell_0_8_0"
},
{
"operation": "Highlighting deleted",
"time": "80.215",
"value": "Ignacio Maganto_sentence_0"
},
{
"operation": "finish",
"time": "100.751",
"value": "finish"
}
]
}
|
66553
|
Athani Taluk's commercial crops include sugarcane, making it one of the largest sugarcane cultivation taluks in India.
|
{
"evidence": [
"Athani Taluk_sentence_15",
"Athani Taluk_sentence_0",
"Athani Taluk_sentence_14"
],
"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:\nAthani Taluk's commercial crops include sugarcane, making it one of the largest sugarcane cultivation taluks in India.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Athani Taluk_sentence_15",
"Athani Taluk_sentence_0",
"Athani Taluk_sentence_14"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3258,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.227",
"value": "?search="
},
{
"operation": "search",
"time": "13.805",
"value": "Athani Taluk"
},
{
"operation": "Now on",
"time": "14.746",
"value": "Athani Taluk"
},
{
"operation": "Highlighting",
"time": "25.739",
"value": "Athani Taluk_sentence_14"
},
{
"operation": "Highlighting",
"time": "33.11",
"value": "Athani Taluk_sentence_15"
},
{
"operation": "Highlighting",
"time": "94.322",
"value": "Athani Taluk_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "98.985",
"value": "Athani Taluk_sentence_0"
},
{
"operation": "Highlighting",
"time": "99.735",
"value": "Athani Taluk_sentence_0"
},
{
"operation": "Highlighting",
"time": "287.969",
"value": "Athani Taluk_sentence_14"
},
{
"operation": "finish",
"time": "299.576",
"value": "finish"
}
]
}
|
exfever_6072
|
Ron Dennis is best known as the founder of a Burmese motor racing team.
|
{
"evidence": [
"Ron Dennis",
"McLaren"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nRon Dennis is best known as the founder of a Burmese motor racing team.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Ron Dennis",
"McLaren"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3259,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
48310
|
Tófű is a village in Upper Hungary where its name was first mentioned in 1382 in the form of Thofew, and was probably named for the nearby river, where it has a population of 166, as of 2015.
|
{
"evidence": [
"Tófű_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:\nTófű is a village in Upper Hungary where its name was first mentioned in 1382 in the form of Thofew, and was probably named for the nearby river, where it has a population of 166, as of 2015.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Tófű_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3260,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.557",
"value": "?search="
},
{
"operation": "search",
"time": "11.923",
"value": "Tófű"
},
{
"operation": "Now on",
"time": "13.548",
"value": "Tófű"
},
{
"operation": "Highlighting",
"time": "30.627",
"value": "Tófű_sentence_0"
},
{
"operation": "Highlighting",
"time": "34.463",
"value": "Tófű_sentence_2"
},
{
"operation": "Highlighting",
"time": "36.803",
"value": "Tófű_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "38.253",
"value": "Tófű_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "38.886",
"value": "Tófű_sentence_0"
},
{
"operation": "finish",
"time": "55.769",
"value": "finish"
}
]
}
|
46987
|
The oreta subvinosa moths were first described in 1903 in New Guinea, and have a 36mm wingspan, with pale yellow forewings, and brown, red, and yellow markings on its body.
|
{
"evidence": [
"Oreta subvinosa_sentence_0",
"Oreta subvinosa_sentence_1",
"Oreta subvinosa_sentence_3",
"Oreta subvinosa_sentence_4",
"Oreta subvinosa_sentence_5",
"Oreta subvinosa_sentence_7",
"Oreta subvinosa_sentence_8"
],
"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 oreta subvinosa moths were first described in 1903 in New Guinea, and have a 36mm wingspan, with pale yellow forewings, and brown, red, and yellow markings on its body.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Oreta subvinosa_sentence_0",
"Oreta subvinosa_sentence_1",
"Oreta subvinosa_sentence_3",
"Oreta subvinosa_sentence_4",
"Oreta subvinosa_sentence_5",
"Oreta subvinosa_sentence_7",
"Oreta subvinosa_sentence_8"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3261,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.595",
"value": "undefined"
},
{
"operation": "search",
"time": "16.082",
"value": "Oreta subvinosa"
},
{
"operation": "Now on",
"time": "16.988",
"value": "Oreta subvinosa"
},
{
"operation": "Highlighting",
"time": "22.657",
"value": "Oreta subvinosa_sentence_0"
},
{
"operation": "Highlighting",
"time": "27.232",
"value": "Oreta subvinosa_sentence_1"
},
{
"operation": "hyperlink",
"time": "34.507",
"value": "William Warren"
},
{
"operation": "Now on",
"time": "34.993",
"value": "William Warren (entomologist)"
},
{
"operation": "back-button-clicked",
"time": "109.582",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "109.674",
"value": "Oreta subvinosa"
},
{
"operation": "Highlighting",
"time": "121.131",
"value": "Oreta subvinosa_sentence_3"
},
{
"operation": "Highlighting",
"time": "126.111",
"value": "Oreta subvinosa_sentence_4"
},
{
"operation": "Highlighting",
"time": "143.391",
"value": "Oreta subvinosa_sentence_5"
},
{
"operation": "Highlighting",
"time": "150.472",
"value": "Oreta subvinosa_sentence_7"
},
{
"operation": "Highlighting",
"time": "162.536",
"value": "Oreta subvinosa_sentence_8"
},
{
"operation": "finish",
"time": "211.749",
"value": "finish"
}
]
}
|
exfever_488
|
Toledo is the seat of government of Wayne County and the largest U.S city on the world's longest international border, stretching 8,891 kilometers.
|
{
"evidence": [
"Detroit",
"Canada–United States border"
],
"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:\nToledo is the seat of government of Wayne County and the largest U.S city on the world's longest international border, stretching 8,891 kilometers.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Detroit",
"Canada–United States border"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3262,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5097
|
Perth is part of the South West Land Division of Western Australia, with most of the metropolitan area on the geographic feature which contains the Swan River as it travels west to the Indian Ocean.
|
{
"evidence": [
"Perth",
"Swan Coastal Plain"
],
"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:\nPerth is part of the South West Land Division of Western Australia, with most of the metropolitan area on the geographic feature which contains the Swan River as it travels west to the Indian Ocean.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Perth",
"Swan Coastal Plain"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3263,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8111
|
Daenerys Targaryen is a fictional character by an American novelist?and author of a series of novels whose genre is high fantasy.?
|
{
"evidence": [
"Daenerys Targaryen",
"George R. R. Martin",
"High fantasy"
],
"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:\nDaenerys Targaryen is a fictional character by an American novelist?and author of a series of novels whose genre is high fantasy.?\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Daenerys Targaryen",
"George R. R. Martin",
"High fantasy"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3264,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
65147
|
Journalist Alexandra Close, the founder of Ethnic Media Services, worked as the China editor in Hong Kong for the Asian news magazine Far Eastern Economic Review.
|
{
"evidence": [
"Sandy Close_sentence_0",
"Sandy Close_sentence_3",
"Far Eastern Economic Review_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:\nJournalist Alexandra Close, the founder of Ethnic Media Services, worked as the China editor in Hong Kong for the Asian news magazine Far Eastern Economic Review.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Sandy Close_sentence_0",
"Sandy Close_sentence_3",
"Far Eastern Economic Review_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3265,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.017",
"value": "?search="
},
{
"operation": "search",
"time": "10.131",
"value": "Contains...Journalist Alexandra Close"
},
{
"operation": "Now on",
"time": "11.977",
"value": "undefined"
},
{
"operation": "search",
"time": "30.38",
"value": "Contains...Alexandra Close"
},
{
"operation": "Now on",
"time": "37.016",
"value": "undefined"
},
{
"operation": "search",
"time": "51.635",
"value": "Ethnic Media Services"
},
{
"operation": "Now on",
"time": "53.66",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "62.631",
"value": "Sandy Close"
},
{
"operation": "Now on",
"time": "68.192",
"value": "Sandy Close"
},
{
"operation": "Highlighting",
"time": "80.278",
"value": "Sandy Close_sentence_0"
},
{
"operation": "Highlighting",
"time": "87.096",
"value": "Sandy Close_sentence_3"
},
{
"operation": "hyperlink",
"time": "104.546",
"value": "Far Eastern Economic Review"
},
{
"operation": "Now on",
"time": "109.527",
"value": "Far Eastern Economic Review"
},
{
"operation": "Highlighting",
"time": "111.869",
"value": "Far Eastern Economic Review_sentence_0"
},
{
"operation": "finish",
"time": "137.034",
"value": "finish"
}
]
}
|
exfever_418
|
Wayne Mark Rooney was a former player of Derby County Football Club.
|
{
"evidence": [
"Wayne Rooney",
"Derby County F.C.",
"Pride Park Stadium"
],
"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:\nWayne Mark Rooney was a former player of Derby County Football Club.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Wayne Rooney",
"Derby County F.C.",
"Pride Park Stadium"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3266,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1318
|
Kuala Lumpur is among the fastest-growing metropolitan regions in the geographical southeastern subregion of Asia.
|
{
"evidence": [
"Kuala Lumpur",
"Southeast Asia"
],
"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:\nKuala Lumpur is among the fastest-growing metropolitan regions in the geographical southeastern subregion of Asia.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Kuala Lumpur",
"Southeast Asia"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3267,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8349
|
Alligator's skin is mostly seen at the top of the lake so people can be warned about them.
|
{
"evidence": [
"Top of the Lake",
"Jane Campion"
],
"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:\nAlligator's skin is mostly seen at the top of the lake so people can be warned about them.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Top of the Lake",
"Jane Campion"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3268,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8480
|
A hate group is a dance group that advocates and practices angry emotional responses towards certain people or ideas, usually related to disliking something.
|
{
"evidence": [
"Hate group",
"Hatred"
],
"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:\nA hate group is a dance group that advocates and practices angry emotional responses towards certain people or ideas, usually related to disliking something.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Hate group",
"Hatred"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3269,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
47535
|
Richard Wallace "Rick" Bloomingdale is a labor union activist from Pittsburg, Pennsylvania who has served as Secretary-Treasurer and President of the Pennsylvania AFL-CIO since 2010
|
{
"evidence": [
"Richard Bloomingdale_sentence_0",
"Richard Bloomingdale_sentence_2",
"Richard Bloomingdale_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:\nRichard Wallace \"Rick\" Bloomingdale is a labor union activist from Pittsburg, Pennsylvania who has served as Secretary-Treasurer and President of the Pennsylvania AFL-CIO since 2010\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Richard Bloomingdale_sentence_0",
"Richard Bloomingdale_sentence_2",
"Richard Bloomingdale_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3270,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.776",
"value": "?search="
},
{
"operation": "search",
"time": "40.331",
"value": "Contains...Richard Wallace \"Rick\" Bloomingdale"
},
{
"operation": "Now on",
"time": "41.468",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "43.981",
"value": "Richard Bloomingdale"
},
{
"operation": "Now on",
"time": "44.573",
"value": "Richard Bloomingdale"
},
{
"operation": "Highlighting",
"time": "75.706",
"value": "Richard Bloomingdale_sentence_0"
},
{
"operation": "Highlighting",
"time": "156.879",
"value": "Richard Bloomingdale_sentence_2"
},
{
"operation": "Highlighting",
"time": "162.529",
"value": "Richard Bloomingdale_sentence_3"
},
{
"operation": "finish",
"time": "175.862",
"value": "finish"
}
]
}
|
exfever_438
|
Gordon Ramsay is a chef known for his highly acclaimed restaurants and cookbooks.
|
{
"evidence": [
"Hotel Hell",
"Ramsay's Kitchen Nightmares"
],
"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:\nGordon Ramsay is a chef known for his highly acclaimed restaurants and cookbooks.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Hotel Hell",
"Ramsay's Kitchen Nightmares"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3271,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8668
|
Nathaniel Faxon co-wrote and co-directed the 2013 American coming-of-age comedy-drama film.
|
{
"evidence": [
"Nat Faxon",
"The Way, Way Back"
],
"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:\nNathaniel Faxon co-wrote and co-directed the 2013 American coming-of-age comedy-drama film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Nat Faxon",
"The Way, Way Back"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3272,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_4288
|
John Cusack is an American actor who has starred in numerous films, including Better Off Dead. Better Off Dead is a 1985 American comedy film written and directed by Will Smith.
|
{
"evidence": [
"John Cusack",
"Better Off Dead (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:\nJohn Cusack is an American actor who has starred in numerous films, including Better Off Dead. Better Off Dead is a 1985 American comedy film written and directed by Will Smith.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"John Cusack",
"Better Off Dead (film)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3273,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5217
|
Jack Dylan Grazer is an American actor who had a breakthrough playing the role of Eddie Kaspbrak in the film adaptation of the Stephen King novel It, directed by Andy Muschietti and written by Chase Palmer.
|
{
"evidence": [
"Jack Dylan Grazer",
"It (2017 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:\nJack Dylan Grazer is an American actor who had a breakthrough playing the role of Eddie Kaspbrak in the film adaptation of the Stephen King novel It, directed by Andy Muschietti and written by Chase Palmer.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jack Dylan Grazer",
"It (2017 film)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3274,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
1781
|
Dorion station is a commuter rail station operated by Exo and it is served the Vaudreuil-Hudson Line.
|
{
"evidence": [
"Dorion station_sentence_0",
"Dorion station_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:\nDorion station is a commuter rail station operated by Exo and it is served the Vaudreuil-Hudson Line.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Dorion station_sentence_0",
"Dorion station_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3275,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "16.096",
"value": "Dorian Station"
},
{
"operation": "hyperlink",
"time": "22.582",
"value": "dorion station"
},
{
"operation": "hyperlink",
"time": "26.731",
"value": "Dorion station"
},
{
"operation": "Highlighting",
"time": "38.9",
"value": "Dorion station_sentence_0"
},
{
"operation": "Highlighting",
"time": "39.849",
"value": "Dorion station_sentence_1"
},
{
"operation": "finish",
"time": "85.597",
"value": "finish"
}
]
}
|
30337
|
The Alawite State was created out of French control over parts of Syria in the early 1900s.
|
{
"evidence": [
"Alawite State_sentence_5"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Alawite State was created out of French control over parts of Syria in the early 1900s.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Alawite State_sentence_5"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3276,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.137",
"value": "?search="
},
{
"operation": "search",
"time": "6.985",
"value": "Alawite State"
},
{
"operation": "Now on",
"time": "8.693",
"value": "Alawite State"
},
{
"operation": "Highlighting",
"time": "30.299",
"value": "Alawite State_sentence_5"
},
{
"operation": "Page search",
"time": "48.9",
"value": "create"
},
{
"operation": "finish",
"time": "67.949",
"value": "finish"
}
]
}
|
47781
|
At the 2006 Winter Olympics held neither in Pragelato nor in Italy, silver medallist Felix Gottwald of Austria and bronze medallist Magnus Moan of Norway both managed to beat Hettich by more than a minute in the cross-country leg; then Moan beat compatriot Petter Tande in a dash for the finish line.
|
{
"evidence": [
"Nordic combined at the 2006 Winter Olympics – Individual Gundersen_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:\nAt the 2006 Winter Olympics held neither in Pragelato nor in Italy, silver medallist Felix Gottwald of Austria and bronze medallist Magnus Moan of Norway both managed to beat Hettich by more than a minute in the cross-country leg; then Moan beat compatriot Petter Tande in a dash for the finish line.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Nordic combined at the 2006 Winter Olympics – Individual Gundersen_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3277,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.761",
"value": "?search="
},
{
"operation": "search",
"time": "13.835",
"value": "2006 Winter Olympics"
},
{
"operation": "Now on",
"time": "15.123",
"value": "2006 Winter Olympics"
},
{
"operation": "Page search",
"time": "48.137",
"value": "pragelato"
},
{
"operation": "Highlighting",
"time": "64.47",
"value": "2006 Winter Olympics_item_2_11"
},
{
"operation": "Highlighting",
"time": "64.471",
"value": "2006 Winter Olympics_title"
},
{
"operation": "Highlighting",
"time": "64.472",
"value": "2006 Winter Olympics_section_24"
},
{
"operation": "Highlighting",
"time": "64.472",
"value": "2006 Winter Olympics_section_25"
},
{
"operation": "Highlighting",
"time": "64.473",
"value": "2006 Winter Olympics_section_27"
},
{
"operation": "Highlighting",
"time": "77.927",
"value": "2006 Winter Olympics_item_2_12"
},
{
"operation": "hyperlink",
"time": "80.815",
"value": "Pragelato Plan"
},
{
"operation": "Now on",
"time": "81.258",
"value": "Pragelato Plan"
},
{
"operation": "hyperlink",
"time": "99.03",
"value": "cross-country skiing"
},
{
"operation": "Now on",
"time": "99.825",
"value": "Cross-country skiing at the 2006 Winter Olympics"
},
{
"operation": "Page search",
"time": "120.944",
"value": "felix gottwald"
},
{
"operation": "search",
"time": "141.607",
"value": "Moan beat compatriot Petter Tande in a dash for the finish line"
},
{
"operation": "Now on",
"time": "143.171",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "150.303",
"value": "Results Nordic combined at the 2006 Winter Olympics – Individual Gundersen_section_0"
},
{
"operation": "Now on",
"time": "151.073",
"value": "Nordic combined at the 2006 Winter Olympics – Individual Gundersen#Results Nordic combined at the 2006 Winter Olympics .E2.80.93 Individual Gundersen section 0"
},
{
"operation": "Page search",
"time": "157.436",
"value": "Moan beat compatriot Petter Tande in a dash for the finish line"
},
{
"operation": "Highlighting",
"time": "170.87",
"value": "Nordic combined at the 2006 Winter Olympics – Individual Gundersen_sentence_7"
},
{
"operation": "Highlighting",
"time": "170.871",
"value": "Nordic combined at the 2006 Winter Olympics – Individual Gundersen_section_0"
},
{
"operation": "Highlighting",
"time": "170.871",
"value": "Nordic combined at the 2006 Winter Olympics – Individual Gundersen_section_2"
},
{
"operation": "Highlighting deleted",
"time": "184.963",
"value": "Nordic combined at the 2006 Winter Olympics – Individual Gundersen_sentence_7"
},
{
"operation": "Highlighting deleted",
"time": "184.967",
"value": "Nordic combined at the 2006 Winter Olympics – Individual Gundersen_section_0"
},
{
"operation": "Highlighting deleted",
"time": "184.968",
"value": "Nordic combined at the 2006 Winter Olympics – Individual Gundersen_section_2"
},
{
"operation": "Highlighting",
"time": "186.483",
"value": "Nordic combined at the 2006 Winter Olympics – Individual Gundersen_sentence_0"
},
{
"operation": "Highlighting",
"time": "203.347",
"value": "Nordic combined at the 2006 Winter Olympics – Individual Gundersen_sentence_0"
},
{
"operation": "finish",
"time": "211.592",
"value": "finish"
}
]
}
|
exfever_208
|
Sparta referred its name to its main settlement on the banks of the Eurotas River in Laconia, in south-eastern peninsula that was known as Morea during the late medieval period that lasted approximately from the 5th to the late 15th centuries.
|
{
"evidence": [
"Sparta",
"Peloponnese",
"Middle Ages"
],
"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:\nSparta referred its name to its main settlement on the banks of the Eurotas River in Laconia, in south-eastern peninsula that was known as Morea during the late medieval period that lasted approximately from the 5th to the late 15th centuries.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Sparta",
"Peloponnese",
"Middle Ages"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3278,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2562
|
The Birth of the Dragon was the most prominent film created by George Nolfi.
|
{
"evidence": [
"Birth of the Dragon",
"Action 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:\nThe Birth of the Dragon was the most prominent film created by George Nolfi.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Birth of the Dragon",
"Action film"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3279,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8160
|
Glee is an American comedy-drama television series that is also classified as a film genre in which songs by the characters are interwoven into the narrative that is exemplified by the films of Busby Berkeley that were typified by lavish production numbers such as a pre-Code Warner Bros. musical film directed by Jason Brock with songs by Harry Warren.
|
{
"evidence": [
"Glee (TV series)",
"Musical film",
"Gold Diggers of 1933"
],
"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:\nGlee is an American comedy-drama television series that is also classified as a film genre in which songs by the characters are interwoven into the narrative that is exemplified by the films of Busby Berkeley that were typified by lavish production numbers such as a pre-Code Warner Bros. musical film directed by Jason Brock with songs by Harry Warren.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Glee (TV series)",
"Musical film",
"Gold Diggers of 1933"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 3280,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_133
|
Pharrell Williams was the first American rapper to win several Grammy Awards.
|
{
"evidence": [
"Pharrell Williams",
"Hip hop music"
],
"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:\nPharrell Williams was the first American rapper to win several Grammy Awards.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Pharrell Williams",
"Hip hop music"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 3281,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
61968
|
The idea of the new company was for non-computer experts to be able to use a simple interface that allowed the user to publish, upload and view streaming videos through standard web browsers and modern internet speeds; ultimately, creating an easy to use video streaming platform.
|
{
"evidence": [
"History of YouTube_sentence_17",
"History of YouTube_sentence_18"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe idea of the new company was for non-computer experts to be able to use a simple interface that allowed the user to publish, upload and view streaming videos through standard web browsers and modern internet speeds; ultimately, creating an easy to use video streaming platform.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"History of YouTube_sentence_17",
"History of YouTube_sentence_18"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3282,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.746",
"value": "?search="
},
{
"operation": "search",
"time": "38.846",
"value": "History of YouTube"
},
{
"operation": "Now on",
"time": "40.107",
"value": "History of YouTube"
},
{
"operation": "Page search",
"time": "43.349",
"value": "new com"
},
{
"operation": "Highlighting",
"time": "47.125",
"value": "History of YouTube_sentence_17"
},
{
"operation": "Highlighting",
"time": "54.683",
"value": "History of YouTube_sentence_18"
},
{
"operation": "finish",
"time": "191.307",
"value": "finish"
}
]
}
|
31346
|
Stark Ritchie was one of the players of the 1936 Michigan Wolverines football team.
|
{
"evidence": [
"Stark Ritchie_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:\nStark Ritchie was one of the players of the 1936 Michigan Wolverines football team.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Stark Ritchie_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 3283,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.673",
"value": "?search="
},
{
"operation": "search",
"time": "15.911",
"value": "Stark Ritchie"
},
{
"operation": "Now on",
"time": "16.561",
"value": "Stark Ritchie"
},
{
"operation": "Highlighting",
"time": "136.238",
"value": "Stark Ritchie_sentence_1"
},
{
"operation": "finish",
"time": "150.092",
"value": "finish"
}
]
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.