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 |
|---|---|---|---|---|---|---|---|---|
58509
|
The 1939 USC Trojans football team represented the University of Southern California, Trojans defeated the Tennessee Volunteers but finished third in the final AP Poll which ranks the top 25 NCAA teams.
|
{
"evidence": [
"1939 USC Trojans football team_sentence_0",
"1939 USC Trojans football team_sentence_1",
"1939 USC Trojans football team_sentence_2",
"AP Poll_sentence_0"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe 1939 USC Trojans football team represented the University of Southern California, Trojans defeated the Tennessee Volunteers but finished third in the final AP Poll which ranks the top 25 NCAA teams.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"1939 USC Trojans football team_sentence_0",
"1939 USC Trojans football team_sentence_1",
"1939 USC Trojans football team_sentence_2",
"AP Poll_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4084,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.8",
"value": "?search="
},
{
"operation": "search",
"time": "11.523",
"value": "1939 USC Trojans football team"
},
{
"operation": "Now on",
"time": "12.337",
"value": "1939 USC Trojans football team"
},
{
"operation": "Highlighting",
"time": "16.893",
"value": "1939 USC Trojans football team_sentence_0"
},
{
"operation": "Highlighting",
"time": "184.014",
"value": "1939 USC Trojans football team_cell_1_10_0"
},
{
"operation": "Highlighting",
"time": "184.016",
"value": "1939 USC Trojans football team_section_0"
},
{
"operation": "Highlighting",
"time": "184.019",
"value": "1939 USC Trojans football team_header_cell_1_0_0"
},
{
"operation": "Highlighting",
"time": "185.803",
"value": "1939 USC Trojans football team_cell_1_10_1"
},
{
"operation": "Highlighting",
"time": "185.806",
"value": "1939 USC Trojans football team_header_cell_1_0_1"
},
{
"operation": "Highlighting",
"time": "186.715",
"value": "1939 USC Trojans football team_cell_1_10_4"
},
{
"operation": "Highlighting",
"time": "186.719",
"value": "1939 USC Trojans football team_header_cell_1_0_4"
},
{
"operation": "Highlighting",
"time": "202.555",
"value": "1939 USC Trojans football team_sentence_2"
},
{
"operation": "hyperlink",
"time": "206.289",
"value": "AP Poll"
},
{
"operation": "Now on",
"time": "207.095",
"value": "AP Poll"
},
{
"operation": "back-button-clicked",
"time": "208.998",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "209.065",
"value": "1939 USC Trojans football team"
},
{
"operation": "Highlighting",
"time": "211.218",
"value": "1939 USC Trojans football team_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "213.653",
"value": "1939 USC Trojans football team_cell_1_10_4"
},
{
"operation": "Highlighting deleted",
"time": "213.657",
"value": "1939 USC Trojans football team_header_cell_1_0_4"
},
{
"operation": "Highlighting deleted",
"time": "214.323",
"value": "1939 USC Trojans football team_cell_1_10_1"
},
{
"operation": "Highlighting deleted",
"time": "214.327",
"value": "1939 USC Trojans football team_header_cell_1_0_1"
},
{
"operation": "Highlighting deleted",
"time": "215.058",
"value": "1939 USC Trojans football team_cell_1_10_0"
},
{
"operation": "Highlighting deleted",
"time": "215.06",
"value": "1939 USC Trojans football team_section_0"
},
{
"operation": "Highlighting deleted",
"time": "215.064",
"value": "1939 USC Trojans football team_header_cell_1_0_0"
},
{
"operation": "Highlighting deleted",
"time": "217.574",
"value": "1939 USC Trojans football team_sentence_2"
},
{
"operation": "Highlighting",
"time": "217.968",
"value": "1939 USC Trojans football team_sentence_2"
},
{
"operation": "hyperlink",
"time": "222.299",
"value": "AP Poll"
},
{
"operation": "Now on",
"time": "222.704",
"value": "AP Poll"
},
{
"operation": "Highlighting",
"time": "223.863",
"value": "AP Poll_sentence_0"
},
{
"operation": "back-button-clicked",
"time": "225.431",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "225.497",
"value": "1939 USC Trojans football team"
},
{
"operation": "finish",
"time": "231.367",
"value": "finish"
}
]
}
|
exfever_1902
|
Thomas Jeffrey Hanks's first film was The Splash.
|
{
"evidence": [
"Tom Hanks",
"Bachelor Party (1984 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:\nThomas Jeffrey Hanks's first film was The Splash.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Tom Hanks",
"Bachelor Party (1984 film)"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4085,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
38889
|
During the 1953 Indianapolis championship, Alberto Ascari had more points than Luigi Villoresi and Art Cross.
|
{
"evidence": [
"1953 Formula One season_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:\nDuring the 1953 Indianapolis championship, Alberto Ascari had more points than Luigi Villoresi and Art Cross.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"1953 Formula One season_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4086,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.634",
"value": "?search="
},
{
"operation": "search",
"time": "22.88",
"value": "Contains...1953 Indianapolis championship"
},
{
"operation": "Now on",
"time": "24.074",
"value": "undefined"
},
{
"operation": "search",
"time": "48.361",
"value": "Alberto Ascari"
},
{
"operation": "Now on",
"time": "49.705",
"value": "Alberto Ascari"
},
{
"operation": "Page search",
"time": "65.395",
"value": "1953"
},
{
"operation": "Page search",
"time": "118.375",
"value": "alberto"
},
{
"operation": "Page search",
"time": "126.697",
"value": "luigi"
},
{
"operation": "Page search",
"time": "193.485",
"value": "indianapolis"
},
{
"operation": "Page search",
"time": "249.999",
"value": "cross"
},
{
"operation": "Page search",
"time": "277.855",
"value": "1953 500"
},
{
"operation": "Page search",
"time": "312.332",
"value": "Indianapolis"
},
{
"operation": "hyperlink",
"time": "315.59",
"value": "Indianapolis 500"
},
{
"operation": "Now on",
"time": "316.5",
"value": "Indianapolis 500"
},
{
"operation": "Page search",
"time": "324.157",
"value": "1953"
},
{
"operation": "hyperlink",
"time": "332.697",
"value": "Indianapolis Motor Speedway Radio Network"
},
{
"operation": "Now on",
"time": "333.522",
"value": "Indianapolis Motor Speedway Radio Network"
},
{
"operation": "back-button-clicked",
"time": "337.647",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "337.807",
"value": "Indianapolis 500"
},
{
"operation": "Page search",
"time": "343.403",
"value": "1953"
},
{
"operation": "search",
"time": "483.786",
"value": "Alberto Ascari"
},
{
"operation": "Now on",
"time": "484.634",
"value": "Alberto Ascari"
},
{
"operation": "hyperlink",
"time": "489.661",
"value": "1953"
},
{
"operation": "Now on",
"time": "490.75",
"value": "1953 Formula One season"
},
{
"operation": "Page search",
"time": "496.114",
"value": "lugi"
},
{
"operation": "Page search",
"time": "499.208",
"value": "luigi"
},
{
"operation": "Page search",
"time": "547.815",
"value": "ascari"
},
{
"operation": "Highlighting",
"time": "556.645",
"value": "1953 Formula One season_sentence_3"
},
{
"operation": "finish",
"time": "564.854",
"value": "finish"
}
]
}
|
exfever_7763
|
James Garner was an American producer who starred in a horror drama television series aired on the NBC network.
|
{
"evidence": [
"James Garner",
"The Rockford Files"
],
"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:\nJames Garner was an American producer who starred in a horror drama television series aired on the NBC network.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"James Garner",
"The Rockford Files"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4087,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
22717
|
Mister Heavenly's "Beat Down" was teased on their official Facebook account on July 19, 2017 prior to its YouTube release on July 26 as part of their second album Boxing the Moonlight produced by Polyvinyl Record Co.
|
{
"evidence": [
"Mister Heavenly_sentence_4",
"Mister Heavenly_sentence_5",
"Boxing the Moonlight_sentence_0",
"Boxing the Moonlight_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:\nMister Heavenly's \"Beat Down\" was teased on their official Facebook account on July 19, 2017 prior to its YouTube release on July 26 as part of their second album Boxing the Moonlight produced by Polyvinyl Record Co.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Mister Heavenly_sentence_4",
"Mister Heavenly_sentence_5",
"Boxing the Moonlight_sentence_0",
"Boxing the Moonlight_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4088,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.593",
"value": "?search="
},
{
"operation": "search",
"time": "16.257",
"value": "Beat Down (EP)"
},
{
"operation": "Now on",
"time": "16.968",
"value": "Beat Down (EP)"
},
{
"operation": "back-button-clicked",
"time": "21.646",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "21.673",
"value": "?search="
},
{
"operation": "search",
"time": "27.615",
"value": "Beat Down"
},
{
"operation": "Now on",
"time": "28.197",
"value": "Beat Down"
},
{
"operation": "Page search",
"time": "42.323",
"value": "heavenly"
},
{
"operation": "search",
"time": "52.256",
"value": "Mister Heavenly"
},
{
"operation": "Now on",
"time": "53.08",
"value": "Mister Heavenly"
},
{
"operation": "Page search",
"time": "56.858",
"value": "beat"
},
{
"operation": "Highlighting",
"time": "71.463",
"value": "Mister Heavenly_sentence_5"
},
{
"operation": "Highlighting deleted",
"time": "77.408",
"value": "Mister Heavenly_sentence_5"
},
{
"operation": "Highlighting",
"time": "78.424",
"value": "Mister Heavenly_sentence_4"
},
{
"operation": "Highlighting",
"time": "79.176",
"value": "Mister Heavenly_sentence_5"
},
{
"operation": "Highlighting",
"time": "100.376",
"value": "Mister Heavenly_item_0_0"
},
{
"operation": "Highlighting",
"time": "100.377",
"value": "Mister Heavenly_section_0"
},
{
"operation": "Highlighting",
"time": "101.024",
"value": "Mister Heavenly_item_0_1"
},
{
"operation": "hyperlink",
"time": "106.929",
"value": "Boxing the Moonlight"
},
{
"operation": "Now on",
"time": "107.446",
"value": "Boxing the Moonlight"
},
{
"operation": "back-button-clicked",
"time": "112.772",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "112.798",
"value": "Mister Heavenly"
},
{
"operation": "Highlighting deleted",
"time": "114.173",
"value": "Mister Heavenly_item_0_1"
},
{
"operation": "Highlighting deleted",
"time": "114.648",
"value": "Mister Heavenly_item_0_0"
},
{
"operation": "Highlighting deleted",
"time": "114.65",
"value": "Mister Heavenly_section_0"
},
{
"operation": "hyperlink",
"time": "115.468",
"value": "Boxing the Moonlight"
},
{
"operation": "Now on",
"time": "115.815",
"value": "Boxing the Moonlight"
},
{
"operation": "Highlighting",
"time": "117.238",
"value": "Boxing the Moonlight_sentence_0"
},
{
"operation": "Highlighting",
"time": "127.303",
"value": "Boxing the Moonlight_sentence_1"
},
{
"operation": "back-button-clicked",
"time": "131.865",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "131.891",
"value": "Mister Heavenly"
},
{
"operation": "finish",
"time": "164.121",
"value": "finish"
}
]
}
|
27851
|
The majority of Cordillera voters did not want it to be an autonomous region because of the effect on their families and the possibility of terrorism; none of the provinces voted for autonomy.
|
{
"evidence": [
"Cordillera autonomy movement_sentence_25",
"Cordillera autonomy movement_sentence_27",
"Cordillera autonomy movement_sentence_28",
"Cordillera autonomy movement_sentence_29",
"Cordillera autonomy movement_sentence_30",
"Cordillera autonomy movement_sentence_31"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe majority of Cordillera voters did not want it to be an autonomous region because of the effect on their families and the possibility of terrorism; none of the provinces voted for autonomy.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Cordillera autonomy movement_sentence_25",
"Cordillera autonomy movement_sentence_27",
"Cordillera autonomy movement_sentence_28",
"Cordillera autonomy movement_sentence_29",
"Cordillera autonomy movement_sentence_30",
"Cordillera autonomy movement_sentence_31"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4089,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.107",
"value": "?search="
},
{
"operation": "search",
"time": "16.123",
"value": "Cordillera"
},
{
"operation": "Now on",
"time": "16.816",
"value": "Cordillera"
},
{
"operation": "search",
"time": "26.75",
"value": "Cordillera Administrative Region"
},
{
"operation": "Now on",
"time": "28.161",
"value": "Cordillera Administrative Region"
},
{
"operation": "hyperlink",
"time": "88.67",
"value": "autonomy in the Cordillera region"
},
{
"operation": "Now on",
"time": "89.204",
"value": "Cordillera autonomy movement"
},
{
"operation": "hyperlink",
"time": "163.061",
"value": "Cordilleras"
},
{
"operation": "Now on",
"time": "163.701",
"value": "Cordillera Administrative Region"
},
{
"operation": "hyperlink",
"time": "219.965",
"value": "Cordillera autonomy movement"
},
{
"operation": "Now on",
"time": "220.328",
"value": "Cordillera autonomy movement"
},
{
"operation": "Highlighting",
"time": "264.128",
"value": "Cordillera autonomy movement_sentence_25"
},
{
"operation": "Highlighting",
"time": "269.367",
"value": "Cordillera autonomy movement_sentence_28"
},
{
"operation": "Highlighting deleted",
"time": "271.191",
"value": "Cordillera autonomy movement_sentence_28"
},
{
"operation": "Highlighting",
"time": "271.813",
"value": "Cordillera autonomy movement_sentence_27"
},
{
"operation": "Highlighting",
"time": "272.526",
"value": "Cordillera autonomy movement_sentence_28"
},
{
"operation": "Highlighting",
"time": "275.301",
"value": "Cordillera autonomy movement_sentence_29"
},
{
"operation": "Highlighting",
"time": "277.405",
"value": "Cordillera autonomy movement_sentence_30"
},
{
"operation": "Highlighting",
"time": "287.598",
"value": "Cordillera autonomy movement_sentence_31"
},
{
"operation": "finish",
"time": "314.727",
"value": "finish"
}
]
}
|
exfever_6867
|
Heartbreak Ridge is a 1978 American war film produced and directed by Clint Eastwood with co-stars including an American actor, who first rose to prominence for his portrayal of a caveman in Quest for Fire.
|
{
"evidence": [
"Heartbreak Ridge",
"Everett McGill"
],
"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:\nHeartbreak Ridge is a 1978 American war film produced and directed by Clint Eastwood with co-stars including an American actor, who first rose to prominence for his portrayal of a caveman in Quest for Fire.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Heartbreak Ridge",
"Everett McGill"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4090,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
45715
|
The 111 Second Street is designed by Architect Rem Koolhaas and it has 52 floors.
|
{
"evidence": [
"Rem Koolhaas_sentence_0"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe 111 Second Street is designed by Architect Rem Koolhaas and it has 52 floors.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Rem Koolhaas_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4091,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.595",
"value": "undefined"
},
{
"operation": "search",
"time": "19.278",
"value": "Contains...111 Second Street"
},
{
"operation": "Now on",
"time": "20.597",
"value": "undefined"
},
{
"operation": "search",
"time": "48.603",
"value": "Rem Koolhaas"
},
{
"operation": "Now on",
"time": "49.544",
"value": "Rem Koolhaas"
},
{
"operation": "Page search",
"time": "51.732",
"value": "Second"
},
{
"operation": "Page search",
"time": "51.903",
"value": "Second"
},
{
"operation": "Page search",
"time": "52.039",
"value": "Second"
},
{
"operation": "Page search",
"time": "65.131",
"value": "Street"
},
{
"operation": "Page search",
"time": "65.304",
"value": "Street"
},
{
"operation": "Page search",
"time": "65.445",
"value": "Street"
},
{
"operation": "search",
"time": "117.337",
"value": "111th Street station"
},
{
"operation": "Now on",
"time": "118.196",
"value": "111th Street"
},
{
"operation": "back-button-clicked",
"time": "122.069",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "122.159",
"value": "Rem Koolhaas"
},
{
"operation": "Page search",
"time": "147.849",
"value": "2nd"
},
{
"operation": "Page search",
"time": "148.058",
"value": "2nd"
},
{
"operation": "Page search",
"time": "165.327",
"value": "52"
},
{
"operation": "Highlighting",
"time": "181.747",
"value": "Rem Koolhaas_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "181.75",
"value": "Rem Koolhaas_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "181.75",
"value": "Rem Koolhaas_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "182.582",
"value": "Rem Koolhaas_cell_0_1_1"
},
{
"operation": "Highlighting deleted",
"time": "182.584",
"value": "Rem Koolhaas_header_cell_0_1_0"
},
{
"operation": "Highlighting deleted",
"time": "182.585",
"value": "Rem Koolhaas_header_cell_0_0_0"
},
{
"operation": "Highlighting",
"time": "183.232",
"value": "Rem Koolhaas_sentence_0"
},
{
"operation": "finish",
"time": "189.468",
"value": "finish"
}
]
}
|
39545
|
Owosso Community Airport which is owned by the Shiawassee Airport Board and located near Owosso, was built in the Shiawassee County in the early 1940s before being officially named in 1949.
|
{
"evidence": [
"Owosso Community Airport_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:\nOwosso Community Airport which is owned by the Shiawassee Airport Board and located near Owosso, was built in the Shiawassee County in the early 1940s before being officially named in 1949.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Owosso Community Airport_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4092,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.888",
"value": "?search="
},
{
"operation": "search",
"time": "11.754",
"value": "Owosso Community Airport"
},
{
"operation": "Now on",
"time": "13.137",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "19.231",
"value": "Owosso Community Airport"
},
{
"operation": "Now on",
"time": "20.242",
"value": "Owosso Community Airport"
},
{
"operation": "Highlighting",
"time": "36.514",
"value": "Owosso Community Airport_sentence_1"
},
{
"operation": "Highlighting",
"time": "59.519",
"value": "Owosso Community Airport_sentence_0"
},
{
"operation": "Page search",
"time": "198",
"value": "built"
},
{
"operation": "Page search",
"time": "198.221",
"value": "built"
},
{
"operation": "Highlighting",
"time": "202.598",
"value": "Owosso Community Airport_sentence_3"
},
{
"operation": "Highlighting",
"time": "222.88",
"value": "Owosso Community Airport_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "228.491",
"value": "Owosso Community Airport_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "229.145",
"value": "Owosso Community Airport_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "237.798",
"value": "Owosso Community Airport_sentence_4"
},
{
"operation": "finish",
"time": "246.226",
"value": "finish"
}
]
}
|
75624
|
EPS15 (Epidermal growth factor receptor substrate 15) is a protein that in humans is encoded by the EPS15 gene that encodes a protein that is part of the EGFR pathway where the protein is present at clathrin-coated pits but does not partake in receptor-mediated endocytosis of EGF.
|
{
"evidence": [
"EPS15_sentence_2"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nEPS15 (Epidermal growth factor receptor substrate 15) is a protein that in humans is encoded by the EPS15 gene that encodes a protein that is part of the EGFR pathway where the protein is present at clathrin-coated pits but does not partake in receptor-mediated endocytosis of EGF.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"EPS15_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4093,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.285",
"value": "?search="
},
{
"operation": "search",
"time": "9.319",
"value": "EPS15"
},
{
"operation": "Now on",
"time": "9.842",
"value": "EPS15"
},
{
"operation": "Highlighting",
"time": "31.509",
"value": "EPS15_sentence_0"
},
{
"operation": "Highlighting",
"time": "55.638",
"value": "EPS15_sentence_1"
},
{
"operation": "Highlighting",
"time": "65.657",
"value": "EPS15_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "125.358",
"value": "EPS15_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "126.121",
"value": "EPS15_sentence_1"
},
{
"operation": "finish",
"time": "228.244",
"value": "finish"
}
]
}
|
55914
|
Manganese peroxidase (belonging to the family of oxidoreductases) an enzyme that catalyzes the chemical reaction, releases Mn(III)-carboxylic acid chelate, as peroxidase structures favor Mn(III)-chelates over free Mn(III) ions.
|
{
"evidence": [
"Manganese peroxidase_sentence_0",
"Manganese peroxidase_sentence_2",
"Manganese peroxidase_sentence_22",
"Manganese peroxidase_sentence_20"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nManganese peroxidase (belonging to the family of oxidoreductases) an enzyme that catalyzes the chemical reaction, releases Mn(III)-carboxylic acid chelate, as peroxidase structures favor Mn(III)-chelates over free Mn(III) ions.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Manganese peroxidase_sentence_0",
"Manganese peroxidase_sentence_2",
"Manganese peroxidase_sentence_22",
"Manganese peroxidase_sentence_20"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4094,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.606",
"value": "?search="
},
{
"operation": "search",
"time": "20.55",
"value": "Manganese peroxidase"
},
{
"operation": "Now on",
"time": "22.613",
"value": "Manganese peroxidase"
},
{
"operation": "Highlighting",
"time": "27.205",
"value": "Manganese peroxidase_sentence_0"
},
{
"operation": "Highlighting",
"time": "36.937",
"value": "Manganese peroxidase_sentence_2"
},
{
"operation": "Highlighting",
"time": "106.101",
"value": "Manganese peroxidase_sentence_22"
},
{
"operation": "Highlighting",
"time": "111.064",
"value": "Manganese peroxidase_sentence_20"
},
{
"operation": "finish",
"time": "129.292",
"value": "finish"
}
]
}
|
exfever_6992
|
The Americans is an American period spy drama television series that follows the story of a fictional character who was a KGB agent who, with her husband Philip, is illegal, posing as a travel agent in Washington, D.C.
|
{
"evidence": [
"The Americans (2013 TV series)",
"Elizabeth Jennings (The Americans)"
],
"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 Americans is an American period spy drama television series that follows the story of a fictional character who was a KGB agent who, with her husband Philip, is illegal, posing as a travel agent in Washington, D.C.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Americans (2013 TV series)",
"Elizabeth Jennings (The Americans)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4095,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_1190
|
Christian states are countries with Christianity as their official religion, including a landlocked country located in the Armenian Highlands of Northern Asia.
|
{
"evidence": [
"Christian state",
"Armenia"
],
"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:\nChristian states are countries with Christianity as their official religion, including a landlocked country located in the Armenian Highlands of Northern Asia.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Christian state",
"Armenia"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4096,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2607
|
Eric Trump is an Indian businessman who is the trustee and executive vice president of his father's business, the Trump Organization, running it alongside his brother, an American political activist, who is he eldest child of the 45th president of the United States.
|
{
"evidence": [
"Eric Trump",
"Donald Trump Jr."
],
"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:\nEric Trump is an Indian businessman who is the trustee and executive vice president of his father's business, the Trump Organization, running it alongside his brother, an American political activist, who is he eldest child of the 45th president of the United States.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Eric Trump",
"Donald Trump Jr."
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4097,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5434
|
Blizzard Entertainment, Inc. is an American video game developer and a company that publishes video games that have been developed either internally by the publisher or externally by a software developer specializing in video game development.
|
{
"evidence": [
"Blizzard Entertainment",
"Video game publisher",
"Video game developer"
],
"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:\nBlizzard Entertainment, Inc. is an American video game developer and a company that publishes video games that have been developed either internally by the publisher or externally by a software developer specializing in video game development.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Blizzard Entertainment",
"Video game publisher",
"Video game developer"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4098,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_8654
|
Beauty Shop, directed by Bille Woodruff, is a comedy film that stars a British actor who created SixDegrees.org, a charitable foundation.
|
{
"evidence": [
"Beauty Shop",
"Kevin Bacon"
],
"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:\nBeauty Shop, directed by Bille Woodruff, is a comedy film that stars a British actor who created SixDegrees.org, a charitable foundation.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Beauty Shop",
"Kevin Bacon"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4099,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5978
|
The Homesman is a 2014 Western historical drama film that features an American actor who is prolific in films, television, and on stage.
|
{
"evidence": [
"The Homesman",
"John Lithgow"
],
"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 Homesman is a 2014 Western historical drama film that features an American actor who is prolific in films, television, and on stage.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Homesman",
"John Lithgow"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4100,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
41205
|
Not only CS50 lectures are recorded and uploaded to several services including iTunes U, EdX, and YouTube, but additional video "walkthroughs" are also recorded with professors and volunteer students; as well as, course questions which are available in both PDF and HTML format..
|
{
"evidence": [
"CS50_sentence_6",
"CS50_sentence_7",
"CS50_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:\nNot only CS50 lectures are recorded and uploaded to several services including iTunes U, EdX, and YouTube, but additional video \"walkthroughs\" are also recorded with professors and volunteer students; as well as, course questions which are available in both PDF and HTML format..\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"CS50_sentence_6",
"CS50_sentence_7",
"CS50_sentence_8"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4101,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "4.311",
"value": "?search="
},
{
"operation": "search",
"time": "15.067",
"value": "\"additional video \"walkthroughs\" are also recorded\""
},
{
"operation": "Now on",
"time": "19.111",
"value": "undefined"
},
{
"operation": "search",
"time": "27.998",
"value": "Contains...CS50 lectures"
},
{
"operation": "Now on",
"time": "30.758",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "33.828",
"value": "CS50"
},
{
"operation": "Now on",
"time": "35.716",
"value": "CS50"
},
{
"operation": "Page search",
"time": "39.499",
"value": "recorded"
},
{
"operation": "Highlighting",
"time": "41.755",
"value": "CS50_sentence_6"
},
{
"operation": "Highlighting",
"time": "43.969",
"value": "CS50_sentence_7"
},
{
"operation": "Highlighting",
"time": "56.576",
"value": "CS50_sentence_8"
},
{
"operation": "finish",
"time": "72.222",
"value": "finish"
}
]
}
|
76291
|
A Meeting by the River received professional ratings from three musci critics.
|
{
"evidence": [
"A Meeting by the River_sentence_27",
"A Meeting by the River_sentence_29"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nA Meeting by the River received professional ratings from three musci critics.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"A Meeting by the River_sentence_27",
"A Meeting by the River_sentence_29"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4102,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.758",
"value": "?search="
},
{
"operation": "search",
"time": "14.332",
"value": "A Meeting by the River"
},
{
"operation": "Now on",
"time": "15.309",
"value": "A Meeting by the River"
},
{
"operation": "Highlighting",
"time": "45.328",
"value": "A Meeting by the River_sentence_27"
},
{
"operation": "Highlighting",
"time": "49.445",
"value": "A Meeting by the River_sentence_29"
},
{
"operation": "finish",
"time": "99.712",
"value": "finish"
}
]
}
|
exfever_5296
|
Wilhelmina Slater is a fictional character in the American dramedy series Ugly Betty, played by Vanessa Williams, who received a Best TV Villain award at the annual award show that airs on the Fox television network which?was voted on by viewers in the United States via various social media sites, including the American multimedia instant messaging app and service developed by Snap Inc.
|
{
"evidence": [
"Wilhelmina Slater",
"Teen Choice Awards",
"Snapchat"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nWilhelmina Slater is a fictional character in the American dramedy series Ugly Betty, played by Vanessa Williams, who received a Best TV Villain award at the annual award show that airs on the Fox television network which?was voted on by viewers in the United States via various social media sites, including the American multimedia instant messaging app and service developed by Snap Inc.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Wilhelmina Slater",
"Teen Choice Awards",
"Snapchat"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4103,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2224
|
Denmark is a Nordic country in a continent recognized as a part of the largest continental area on Earth, comprising all of Europe and Asia.
|
{
"evidence": [
"Denmark",
"Europe",
"Eurasia"
],
"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:\nDenmark is a Nordic country in a continent recognized as a part of the largest continental area on Earth, comprising all of Europe and Asia.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Denmark",
"Europe",
"Eurasia"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4104,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
87627
|
Joe Simmonds (born 19 December 1996) is an English rugby union player who made his full debut on 4 March 2018, plays as a fly-half and is the first team captain of Exeter Chiefs and was top points scorer in the 2019–20 European Rugby Champions Cup.
|
{
"evidence": [
"Joe Simmonds_sentence_0",
"Joe Simmonds_sentence_4",
"Joe Simmonds_sentence_1",
"Joe Simmonds_sentence_13"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJoe Simmonds (born 19 December 1996) is an English rugby union player who made his full debut on 4 March 2018, plays as a fly-half and is the first team captain of Exeter Chiefs and was top points scorer in the 2019–20 European Rugby Champions Cup.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Joe Simmonds_sentence_0",
"Joe Simmonds_sentence_4",
"Joe Simmonds_sentence_1",
"Joe Simmonds_sentence_13"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4105,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.396",
"value": "?search="
},
{
"operation": "search",
"time": "13.312",
"value": "Joe Simmonds"
},
{
"operation": "Now on",
"time": "14.203",
"value": "Joe Simmonds"
},
{
"operation": "Highlighting",
"time": "19.295",
"value": "Joe Simmonds_sentence_0"
},
{
"operation": "Highlighting",
"time": "47.273",
"value": "Joe Simmonds_sentence_4"
},
{
"operation": "Highlighting",
"time": "55.115",
"value": "Joe Simmonds_sentence_1"
},
{
"operation": "Highlighting",
"time": "72.703",
"value": "Joe Simmonds_sentence_13"
},
{
"operation": "finish",
"time": "82.022",
"value": "finish"
}
]
}
|
exfever_6550
|
The Ten Commandments is a 1956 American epic religious drama film produced, directed, and narrated by an American film director, producer, and actor regarded as a founding father of American cinema and the most commercially successful producer-director in film history.
|
{
"evidence": [
"The Ten Commandments (1956 film)",
"Cecil B. DeMille"
],
"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 Ten Commandments is a 1956 American epic religious drama film produced, directed, and narrated by an American film director, producer, and actor regarded as a founding father of American cinema and the most commercially successful producer-director in film history.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Ten Commandments (1956 film)",
"Cecil B. DeMille"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4106,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7111
|
The Lion King is a 1995 American animated drama film whose film genre is where the songs of the characters are interwoven into the narrative.
|
{
"evidence": [
"The Lion King",
"Musical film"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Lion King is a 1995 American animated drama film whose film genre is where the songs of the characters are interwoven into the narrative.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Lion King",
"Musical film"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4107,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_954
|
The Evil Queen is a fictional character who appears in the 2nd animated feature film of an American animation studio that creates animated features and short films for The Walt Disney Company.
|
{
"evidence": [
"Evil Queen (Disney)",
"Walt Disney Animation Studios"
],
"label": "REFUTE"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Evil Queen is a fictional character who appears in the 2nd animated feature film of an American animation studio that creates animated features and short films for The Walt Disney Company.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Evil Queen (Disney)",
"Walt Disney Animation Studios"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4108,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
64831
|
Sarcoprion is the only remaining extant genus of the family Helicoprionidae.
|
{
"evidence": [
"Sarcoprion_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:\nSarcoprion is the only remaining extant genus of the family Helicoprionidae.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Sarcoprion_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4109,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.805",
"value": "?search="
},
{
"operation": "search",
"time": "8.998",
"value": "Sarcoprion"
},
{
"operation": "Now on",
"time": "9.692",
"value": "Sarcoprion"
},
{
"operation": "Highlighting",
"time": "17.326",
"value": "Sarcoprion_sentence_0"
},
{
"operation": "finish",
"time": "45.933",
"value": "finish"
}
]
}
|
exfever_1322
|
The Celtic Football Club is a Scottish professional club in a team sport played with a spherical ball between two teams of 11 players.
|
{
"evidence": [
"Celtic F.C.",
"Association football"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Celtic Football Club is a Scottish professional club in a team sport played with a spherical ball between two teams of 11 players.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Celtic F.C.",
"Association football"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4110,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
77707
|
Reece Mastin peaked at No. 2 in the Austrian music charts; then peaked at No. 1 in the Oceanian music charts.
|
{
"evidence": [
"Reece Mastin (album)_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:\nReece Mastin peaked at No. 2 in the Austrian music charts; then peaked at No. 1 in the Oceanian music charts.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Reece Mastin (album)_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4111,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "2.501",
"value": "?search="
},
{
"operation": "search",
"time": "446.504",
"value": "Reece Mastin"
},
{
"operation": "Now on",
"time": "448.746",
"value": "Reece Mastin"
},
{
"operation": "Highlighting",
"time": "592.976",
"value": "Reece Mastin_sentence_0"
},
{
"operation": "Highlighting",
"time": "592.977",
"value": "Reece Mastin_title"
},
{
"operation": "Highlighting deleted",
"time": "791.457",
"value": "Reece Mastin_sentence_0"
},
{
"operation": "Highlighting deleted",
"time": "791.46",
"value": "Reece Mastin_title"
},
{
"operation": "hyperlink",
"time": "932.465",
"value": "Reece Mastin (album)"
},
{
"operation": "Now on",
"time": "934.133",
"value": "Reece Mastin (album)"
},
{
"operation": "Highlighting",
"time": "971.217",
"value": "Reece Mastin (album)_sentence_1"
},
{
"operation": "finish",
"time": "1003.312",
"value": "finish"
}
]
}
|
80374
|
Raymond Carver appeared in "Will You Please Be Quiet, Please?", enrolled in the library science and he relocated to Palo Alto.
|
{
"evidence": [
"Raymond Carver_sentence_36",
"Raymond Carver_sentence_38",
"Raymond Carver_sentence_39"
],
"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:\nRaymond Carver appeared in \"Will You Please Be Quiet, Please?\", enrolled in the library science and he relocated to Palo Alto.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Raymond Carver_sentence_36",
"Raymond Carver_sentence_38",
"Raymond Carver_sentence_39"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4112,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.727",
"value": "?search="
},
{
"operation": "search",
"time": "20.658",
"value": "Raymond Carver"
},
{
"operation": "Now on",
"time": "21.504",
"value": "Raymond Carver"
},
{
"operation": "Page search",
"time": "43.483",
"value": "Will you please"
},
{
"operation": "Highlighting",
"time": "92.045",
"value": "Raymond Carver_sentence_36"
},
{
"operation": "Highlighting",
"time": "114.913",
"value": "Raymond Carver_sentence_38"
},
{
"operation": "Highlighting",
"time": "116.223",
"value": "Raymond Carver_sentence_39"
},
{
"operation": "finish",
"time": "146.753",
"value": "finish"
}
]
}
|
exfever_6511
|
Montreal, the second-most populous city in Canada, is named after a large intrusive rock hill or small mountain in the city of Montreal, immediately west of Downtown Montreal, Quebec, Canada.
|
{
"evidence": [
"Montreal",
"Mount Royal"
],
"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:\nMontreal, the second-most populous city in Canada, is named after a large intrusive rock hill or small mountain in the city of Montreal, immediately west of Downtown Montreal, Quebec, Canada.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Montreal",
"Mount Royal"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4113,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5738
|
Lost Highway is a 1999 neo-noir film directed by an American painter.
|
{
"evidence": [
"Lost Highway (film)",
"David Lynch"
],
"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:\nLost Highway is a 1999 neo-noir film directed by an American painter.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Lost Highway (film)",
"David Lynch"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4114,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
18324
|
The 2007 Vuelta al Táchira was held in Chile and Manuel Medina won the mountains classification.
|
{
"evidence": [
"2007 Vuelta al Táchira_sentence_0"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe 2007 Vuelta al Táchira was held in Chile and Manuel Medina won the mountains classification.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"2007 Vuelta al Táchira_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4115,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.63",
"value": "?search="
},
{
"operation": "search",
"time": "12.686",
"value": "2007 Vuelta al Táchira"
},
{
"operation": "Now on",
"time": "13.443",
"value": "2007 Vuelta al Táchira"
},
{
"operation": "Highlighting",
"time": "17.575",
"value": "2007 Vuelta al Táchira_sentence_0"
},
{
"operation": "finish",
"time": "26.725",
"value": "finish"
}
]
}
|
24803
|
Anastasia Tambovtseva (born August 11, 1982), a Russian luger and bobsledder, competed from 2001 to 2006.
|
{
"evidence": [
"Anastasia Tambovtseva_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:\nAnastasia Tambovtseva (born August 11, 1982), a Russian luger and bobsledder, competed from 2001 to 2006.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Anastasia Tambovtseva_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4116,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.058",
"value": "?search="
},
{
"operation": "search",
"time": "14.988",
"value": "Anastasia Tambovtseva"
},
{
"operation": "Now on",
"time": "15.903",
"value": "Anastasia Tambovtseva"
},
{
"operation": "Highlighting",
"time": "24.786",
"value": "Anastasia Tambovtseva_sentence_0"
},
{
"operation": "finish",
"time": "48.435",
"value": "finish"
}
]
}
|
34249
|
Jennifer Zamparelli (born April 9, 1980) is an Irish television presenter that also stars in a sitcom.
|
{
"evidence": [
"Jennifer Zamparelli_sentence_0",
"Jennifer Zamparelli_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:\nJennifer Zamparelli (born April 9, 1980) is an Irish television presenter that also stars in a sitcom.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jennifer Zamparelli_sentence_0",
"Jennifer Zamparelli_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4117,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.929",
"value": "?search="
},
{
"operation": "search",
"time": "10.881",
"value": "Jennifer Zamparelli"
},
{
"operation": "Now on",
"time": "11.729",
"value": "Jennifer Zamparelli"
},
{
"operation": "Highlighting",
"time": "14.879",
"value": "Jennifer Zamparelli_sentence_0"
},
{
"operation": "Highlighting",
"time": "20.252",
"value": "Jennifer Zamparelli_sentence_2"
},
{
"operation": "finish",
"time": "30.253",
"value": "finish"
}
]
}
|
exfever_3506
|
Jeffrey Nero Hardy was the most famous American professional wrestler.
|
{
"evidence": [
"Jeff Hardy",
"WWE"
],
"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:\nJeffrey Nero Hardy was the most famous American professional wrestler.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Jeff Hardy",
"WWE"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4118,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
3488
|
Yauyos Province, home to the small ethnic minority who speak the indigenous Jaqaru/Kawki language, has a population of less than 20,000 inhabitants as of 2002.
|
{
"evidence": [
"Yauyos Province_sentence_10"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nYauyos Province, home to the small ethnic minority who speak the indigenous Jaqaru/Kawki language, has a population of less than 20,000 inhabitants as of 2002.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Yauyos Province_sentence_10"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4119,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "19.478",
"value": "Yauyos Province"
},
{
"operation": "Highlighting",
"time": "36.308",
"value": "Yauyos Province_sentence_11"
},
{
"operation": "hyperlink",
"time": "57.615",
"value": "5 Demographics Yauyos Province_section_4"
},
{
"operation": "Highlighting",
"time": "65.698",
"value": "Yauyos Province_sentence_10"
},
{
"operation": "Highlighting deleted",
"time": "67.131",
"value": "Yauyos Province_sentence_11"
},
{
"operation": "finish",
"time": "96.023",
"value": "finish"
}
]
}
|
43148
|
European financial institutions could not easily lend to the workers, rendering labor immobile because of capital market imperfections; so to address this imperfection, the Virginia Company never allows laborers to borrow against their future earnings.
|
{
"evidence": [
"Indentured servitude in British America_sentence_48",
"Indentured servitude in British America_sentence_49"
],
"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:\nEuropean financial institutions could not easily lend to the workers, rendering labor immobile because of capital market imperfections; so to address this imperfection, the Virginia Company never allows laborers to borrow against their future earnings.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Indentured servitude in British America_sentence_48",
"Indentured servitude in British America_sentence_49"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4120,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.403",
"value": "?search="
},
{
"operation": "search",
"time": "24.508",
"value": "Virginia Company"
},
{
"operation": "Now on",
"time": "25.438",
"value": "Virginia Company"
},
{
"operation": "search",
"time": "44.7",
"value": "Indentured servitude in British America"
},
{
"operation": "Now on",
"time": "45.589",
"value": "Indentured servitude in British America"
},
{
"operation": "Page search",
"time": "69.188",
"value": "European financial institutions could not easily lend to the workers"
},
{
"operation": "Highlighting",
"time": "74.929",
"value": "Indentured servitude in British America_sentence_48"
},
{
"operation": "Highlighting",
"time": "90.172",
"value": "Indentured servitude in British America_sentence_49"
},
{
"operation": "finish",
"time": "233.827",
"value": "finish"
}
]
}
|
exfever_2124
|
Music is the art of arranging sounds using elements from the tune and the backing support that provides the rhythmic and harmonic sound.
|
{
"evidence": [
"Music",
"Melody",
"Accompaniment"
],
"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:\nMusic is the art of arranging sounds using elements from the tune and the backing support that provides the rhythmic and harmonic sound.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Music",
"Melody",
"Accompaniment"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4121,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_5222
|
Gunday was directed by an Indian film director.
|
{
"evidence": [
"Gunday",
"Ali Abbas Zafar"
],
"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:\nGunday was directed by an Indian film director.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Gunday",
"Ali Abbas Zafar"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4122,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
15662
|
John Scott Trotter, who arranged orchestrations for Pennies from Heaven, a 1936 American musical comedy film, is professionally associated with Crosby and was asked by Johnny Burke to do orchestrations for a film.
|
{
"evidence": [
"John Scott Trotter_sentence_9",
"Pennies from Heaven (1936 film)_sentence_0",
"John Scott Trotter_sentence_10",
"John Scott Trotter_sentence_12"
],
"label": "SUPPORT"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nJohn Scott Trotter, who arranged orchestrations for Pennies from Heaven, a 1936 American musical comedy film, is professionally associated with Crosby and was asked by Johnny Burke to do orchestrations for a film.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"John Scott Trotter_sentence_9",
"Pennies from Heaven (1936 film)_sentence_0",
"John Scott Trotter_sentence_10",
"John Scott Trotter_sentence_12"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4123,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.554",
"value": "?search="
},
{
"operation": "search",
"time": "11.482",
"value": "John Scott Trotter"
},
{
"operation": "Now on",
"time": "12.189",
"value": "John Scott Trotter"
},
{
"operation": "Highlighting",
"time": "52.64",
"value": "John Scott Trotter_sentence_9"
},
{
"operation": "hyperlink",
"time": "55.496",
"value": "Pennies from Heaven"
},
{
"operation": "Now on",
"time": "56.076",
"value": "Pennies from Heaven (1936 film)"
},
{
"operation": "Highlighting",
"time": "59.982",
"value": "Pennies from Heaven (1936 film)_sentence_0"
},
{
"operation": "back-button-clicked",
"time": "64.509",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "64.615",
"value": "John Scott Trotter"
},
{
"operation": "Highlighting",
"time": "67.784",
"value": "John Scott Trotter_sentence_10"
},
{
"operation": "Highlighting",
"time": "73.984",
"value": "John Scott Trotter_sentence_12"
},
{
"operation": "finish",
"time": "85.154",
"value": "finish"
}
]
}
|
exfever_5032
|
The Muse is Sharon Stone's debut film.
|
{
"evidence": [
"The Muse (1999 film)",
"Albert Brooks"
],
"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 Muse is Sharon Stone's debut film.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Muse (1999 film)",
"Albert Brooks"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4124,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
41705
|
Matsya is an avatar of Vishnu who appears a half fish/half man; he saves the world from cosmic deluge with the help of a boat made from knowledge, on which he rescues all living beings.
|
{
"evidence": [
"Matsya_sentence_1",
"Matsya_sentence_2",
"Matsya_sentence_4",
"Matsya_sentence_3",
"Matsya_sentence_72",
"Matsya_sentence_73",
"Matsya_sentence_74"
],
"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:\nMatsya is an avatar of Vishnu who appears a half fish/half man; he saves the world from cosmic deluge with the help of a boat made from knowledge, on which he rescues all living beings.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Matsya_sentence_1",
"Matsya_sentence_2",
"Matsya_sentence_4",
"Matsya_sentence_3",
"Matsya_sentence_72",
"Matsya_sentence_73",
"Matsya_sentence_74"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4125,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.713",
"value": "?search="
},
{
"operation": "search",
"time": "9.396",
"value": "Matsya"
},
{
"operation": "Now on",
"time": "10.544",
"value": "Matsya"
},
{
"operation": "Highlighting",
"time": "12.953",
"value": "Matsya_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "14.458",
"value": "Matsya_sentence_2"
},
{
"operation": "Highlighting",
"time": "15.755",
"value": "Matsya_sentence_1"
},
{
"operation": "Highlighting",
"time": "16.302",
"value": "Matsya_sentence_2"
},
{
"operation": "Highlighting",
"time": "27.351",
"value": "Matsya_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "33.119",
"value": "Matsya_sentence_4"
},
{
"operation": "Page search",
"time": "55.18",
"value": "half"
},
{
"operation": "Highlighting",
"time": "80.87",
"value": "Matsya_sentence_159"
},
{
"operation": "Highlighting",
"time": "80.872",
"value": "Matsya_section_7"
},
{
"operation": "Page search",
"time": "130.69",
"value": "cosmic"
},
{
"operation": "Page search",
"time": "163.089",
"value": "boat"
},
{
"operation": "Highlighting",
"time": "172.159",
"value": "Matsya_sentence_39"
},
{
"operation": "Highlighting",
"time": "172.161",
"value": "Matsya_section_2"
},
{
"operation": "Highlighting deleted",
"time": "173.069",
"value": "Matsya_sentence_39"
},
{
"operation": "Highlighting deleted",
"time": "173.074",
"value": "Matsya_section_2"
},
{
"operation": "Page search",
"time": "242.63",
"value": "knowledge"
},
{
"operation": "Highlighting",
"time": "309.126",
"value": "Matsya_sentence_97"
},
{
"operation": "Highlighting",
"time": "309.128",
"value": "Matsya_section_4"
},
{
"operation": "Highlighting",
"time": "313.732",
"value": "Matsya_sentence_98"
},
{
"operation": "Highlighting",
"time": "334.714",
"value": "Matsya_sentence_100"
},
{
"operation": "Highlighting",
"time": "336.728",
"value": "Matsya_sentence_101"
},
{
"operation": "Highlighting deleted",
"time": "338.07",
"value": "Matsya_sentence_101"
},
{
"operation": "Highlighting",
"time": "356.038",
"value": "Matsya_sentence_102"
},
{
"operation": "Highlighting",
"time": "357.525",
"value": "Matsya_sentence_101"
},
{
"operation": "Page search",
"time": "361.709",
"value": "deluge"
},
{
"operation": "Highlighting",
"time": "427.424",
"value": "Matsya_sentence_54"
},
{
"operation": "Highlighting",
"time": "433.834",
"value": "Matsya_sentence_59"
},
{
"operation": "Highlighting",
"time": "452.637",
"value": "Matsya_sentence_61"
},
{
"operation": "Highlighting deleted",
"time": "454.721",
"value": "Matsya_sentence_61"
},
{
"operation": "Highlighting",
"time": "459.648",
"value": "Matsya_sentence_60"
},
{
"operation": "Highlighting",
"time": "460.875",
"value": "Matsya_sentence_61"
},
{
"operation": "Highlighting",
"time": "470.124",
"value": "Matsya_sentence_62"
},
{
"operation": "Highlighting deleted",
"time": "490.566",
"value": "Matsya_sentence_54"
},
{
"operation": "Highlighting deleted",
"time": "491.564",
"value": "Matsya_sentence_59"
},
{
"operation": "Highlighting deleted",
"time": "492.126",
"value": "Matsya_sentence_60"
},
{
"operation": "Highlighting deleted",
"time": "492.647",
"value": "Matsya_sentence_61"
},
{
"operation": "Highlighting deleted",
"time": "494.14",
"value": "Matsya_sentence_62"
},
{
"operation": "Highlighting",
"time": "495.092",
"value": "Matsya_sentence_59"
},
{
"operation": "Highlighting",
"time": "503.117",
"value": "Matsya_sentence_72"
},
{
"operation": "Highlighting",
"time": "517.723",
"value": "Matsya_sentence_73"
},
{
"operation": "Highlighting",
"time": "520.173",
"value": "Matsya_sentence_74"
},
{
"operation": "Highlighting",
"time": "526.445",
"value": "Matsya_sentence_75"
},
{
"operation": "Page search",
"time": "650.245",
"value": "ship"
},
{
"operation": "Highlighting",
"time": "727.074",
"value": "Matsya_sentence_46"
},
{
"operation": "Highlighting",
"time": "727.075",
"value": "Matsya_section_2"
},
{
"operation": "search",
"time": "855.901",
"value": "help of a boat made from knowledge"
},
{
"operation": "Now on",
"time": "860.064",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "868.651",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "868.743",
"value": "Matsya"
},
{
"operation": "hyperlink",
"time": "872.749",
"value": "Manu"
},
{
"operation": "Now on",
"time": "873.414",
"value": "Manu"
},
{
"operation": "back-button-clicked",
"time": "883.756",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "883.836",
"value": "Matsya"
},
{
"operation": "hyperlink",
"time": "893.456",
"value": "Shatapatha Brahmana"
},
{
"operation": "Now on",
"time": "894.199",
"value": "Shatapatha Brahmana"
},
{
"operation": "back-button-clicked",
"time": "901.514",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "901.599",
"value": "Matsya"
},
{
"operation": "Page search",
"time": "915.116",
"value": "knowledge"
},
{
"operation": "Page search",
"time": "915.87",
"value": "knowledge"
},
{
"operation": "Highlighting",
"time": "1002.637",
"value": "Matsya_sentence_1"
},
{
"operation": "Highlighting",
"time": "1003.238",
"value": "Matsya_sentence_2"
},
{
"operation": "Highlighting",
"time": "1009.223",
"value": "Matsya_sentence_4"
},
{
"operation": "Highlighting",
"time": "1017.775",
"value": "Matsya_sentence_3"
},
{
"operation": "Highlighting",
"time": "1059.193",
"value": "Matsya_sentence_29"
},
{
"operation": "Highlighting",
"time": "1059.194",
"value": "Matsya_section_2"
},
{
"operation": "Highlighting",
"time": "1101.39",
"value": "Matsya_sentence_33"
},
{
"operation": "Highlighting deleted",
"time": "1113.667",
"value": "Matsya_sentence_29"
},
{
"operation": "Highlighting deleted",
"time": "1114.421",
"value": "Matsya_sentence_33"
},
{
"operation": "Highlighting deleted",
"time": "1114.425",
"value": "Matsya_section_2"
},
{
"operation": "Highlighting",
"time": "1139.383",
"value": "Matsya_sentence_59"
},
{
"operation": "Highlighting",
"time": "1143.42",
"value": "Matsya_sentence_60"
},
{
"operation": "Highlighting",
"time": "1145.104",
"value": "Matsya_sentence_61"
},
{
"operation": "Highlighting",
"time": "1146.482",
"value": "Matsya_sentence_62"
},
{
"operation": "Highlighting deleted",
"time": "1157.521",
"value": "Matsya_sentence_62"
},
{
"operation": "Highlighting deleted",
"time": "1158.425",
"value": "Matsya_sentence_61"
},
{
"operation": "Highlighting deleted",
"time": "1159.845",
"value": "Matsya_sentence_59"
},
{
"operation": "Highlighting deleted",
"time": "1160.319",
"value": "Matsya_sentence_60"
},
{
"operation": "Highlighting",
"time": "1170.715",
"value": "Matsya_sentence_72"
},
{
"operation": "Highlighting",
"time": "1184.992",
"value": "Matsya_sentence_73"
},
{
"operation": "Highlighting",
"time": "1188.396",
"value": "Matsya_sentence_74"
},
{
"operation": "finish",
"time": "1236.039",
"value": "finish"
}
]
}
|
49850
|
Troy Sneed an American gospel singer, (a genre of Christian music) whose fifth album, In Due Season, was released by his record label on August 25, 2009, and the subsequent album, My Heart Says Yes, was released on May 10, 2011.
|
{
"evidence": [
"Troy Sneed_sentence_0",
"Troy Sneed_sentence_11",
"Troy Sneed_sentence_12",
"Black Gospel music_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:\nTroy Sneed an American gospel singer, (a genre of Christian music) whose fifth album, In Due Season, was released by his record label on August 25, 2009, and the subsequent album, My Heart Says Yes, was released on May 10, 2011.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Troy Sneed_sentence_0",
"Troy Sneed_sentence_11",
"Troy Sneed_sentence_12",
"Black Gospel music_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4126,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.643",
"value": "?search="
},
{
"operation": "search",
"time": "15.499",
"value": "Troy Sneed"
},
{
"operation": "Now on",
"time": "16.038",
"value": "Troy Sneed"
},
{
"operation": "Highlighting",
"time": "22.683",
"value": "Troy Sneed_sentence_0"
},
{
"operation": "Highlighting",
"time": "43.562",
"value": "Troy Sneed_header_cell_1_6_0"
},
{
"operation": "Highlighting",
"time": "43.563",
"value": "Troy Sneed_section_4"
},
{
"operation": "Highlighting deleted",
"time": "67.29",
"value": "Troy Sneed_header_cell_1_6_0"
},
{
"operation": "Highlighting deleted",
"time": "67.292",
"value": "Troy Sneed_section_4"
},
{
"operation": "Highlighting",
"time": "70.85",
"value": "Troy Sneed_sentence_11"
},
{
"operation": "Highlighting",
"time": "77.25",
"value": "Troy Sneed_sentence_12"
},
{
"operation": "hyperlink",
"time": "91.842",
"value": "US\nGos"
},
{
"operation": "Now on",
"time": "93.062",
"value": "Billboard charts"
},
{
"operation": "search",
"time": "103.055",
"value": "American gospel"
},
{
"operation": "Now on",
"time": "104.555",
"value": "undefined"
},
{
"operation": "search",
"time": "117.947",
"value": "Contains...Gospel music"
},
{
"operation": "Now on",
"time": "118.71",
"value": "undefined"
},
{
"operation": "search",
"time": "138.443",
"value": "genre gospel music"
},
{
"operation": "Now on",
"time": "139.614",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "147.125",
"value": "Black Gospel music"
},
{
"operation": "Now on",
"time": "147.77",
"value": "Black Gospel music"
},
{
"operation": "Highlighting",
"time": "159.829",
"value": "Black Gospel music_sentence_1"
},
{
"operation": "hyperlink",
"time": "167.939",
"value": "African-American Christian music"
},
{
"operation": "Now on",
"time": "169.468",
"value": "African-American music#Christian"
},
{
"operation": "search",
"time": "183.188",
"value": "Contains...Christian music"
},
{
"operation": "Now on",
"time": "184.2",
"value": "undefined"
},
{
"operation": "search",
"time": "194.019",
"value": "Christian gospel music"
},
{
"operation": "Now on",
"time": "194.722",
"value": "undefined"
},
{
"operation": "search",
"time": "204.74",
"value": "Troy Sneed"
},
{
"operation": "Now on",
"time": "205.49",
"value": "Troy Sneed"
},
{
"operation": "Page search",
"time": "224.892",
"value": "Christian"
},
{
"operation": "hyperlink",
"time": "234.787",
"value": "CCM"
},
{
"operation": "Now on",
"time": "235.358",
"value": "Contemporary Christian music"
},
{
"operation": "Page search",
"time": "245.852",
"value": "gospel"
},
{
"operation": "finish",
"time": "308.801",
"value": "finish"
}
]
}
|
39651
|
Lophocampa albiguttata was treated as an antonym of Lophocampa alternata (fly of the family Erebidae) by Allan Watson and David T. Goodger and therefore raised from synonymy in 2001.
|
{
"evidence": [
"Lophocampa albiguttata_sentence_3",
"Lophocampa albiguttata_sentence_5"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nLophocampa albiguttata was treated as an antonym of Lophocampa alternata (fly of the family Erebidae) by Allan Watson and David T. Goodger and therefore raised from synonymy in 2001.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Lophocampa albiguttata_sentence_3",
"Lophocampa albiguttata_sentence_5"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4127,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.865",
"value": "?search="
},
{
"operation": "search",
"time": "28.654",
"value": "Lophocampa albiguttata"
},
{
"operation": "Now on",
"time": "29.321",
"value": "Lophocampa albiguttata"
},
{
"operation": "Highlighting",
"time": "36.085",
"value": "Lophocampa albiguttata_sentence_3"
},
{
"operation": "Highlighting",
"time": "44.261",
"value": "Lophocampa albiguttata_sentence_5"
},
{
"operation": "finish",
"time": "62.236",
"value": "finish"
}
]
}
|
11754
|
Harvard & Smithsonian, which was established in 1973, and with headquarters in Cambridge, California, is among the largest astronomical research institutes in the world.
|
{
"evidence": [
"Harvard–Smithsonian Center for Astrophysics_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:\nHarvard & Smithsonian, which was established in 1973, and with headquarters in Cambridge, California, is among the largest astronomical research institutes in the world.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Harvard–Smithsonian Center for Astrophysics_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4128,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.506",
"value": "?search="
},
{
"operation": "search",
"time": "12.511",
"value": "Harvard & Smithsonian"
},
{
"operation": "Now on",
"time": "13.727",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "21.089",
"value": "Harvard–Smithsonian Center for Astrophysics"
},
{
"operation": "Now on",
"time": "21.735",
"value": "Harvard–Smithsonian Center for Astrophysics"
},
{
"operation": "Highlighting",
"time": "28.523",
"value": "Harvard–Smithsonian Center for Astrophysics_cell_0_1_1"
},
{
"operation": "Highlighting",
"time": "28.527",
"value": "Harvard–Smithsonian Center for Astrophysics_header_cell_0_1_0"
},
{
"operation": "Highlighting deleted",
"time": "32.888",
"value": "Harvard–Smithsonian Center for Astrophysics_cell_0_1_1"
},
{
"operation": "Highlighting deleted",
"time": "32.893",
"value": "Harvard–Smithsonian Center for Astrophysics_header_cell_0_1_0"
},
{
"operation": "Highlighting",
"time": "33.737",
"value": "Harvard–Smithsonian Center for Astrophysics_sentence_0"
},
{
"operation": "Highlighting",
"time": "34.3",
"value": "Harvard–Smithsonian Center for Astrophysics_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "34.741",
"value": "Harvard–Smithsonian Center for Astrophysics_sentence_0"
},
{
"operation": "Page search",
"time": "49.147",
"value": "largest"
},
{
"operation": "Highlighting",
"time": "52.091",
"value": "Harvard–Smithsonian Center for Astrophysics_sentence_3"
},
{
"operation": "Highlighting",
"time": "59.713",
"value": "Harvard–Smithsonian Center for Astrophysics_cell_0_0_1"
},
{
"operation": "Highlighting",
"time": "59.716",
"value": "Harvard–Smithsonian Center for Astrophysics_header_cell_0_0_0"
},
{
"operation": "Highlighting deleted",
"time": "72.743",
"value": "Harvard–Smithsonian Center for Astrophysics_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "74.573",
"value": "Harvard–Smithsonian Center for Astrophysics_cell_0_0_1"
},
{
"operation": "Highlighting deleted",
"time": "74.578",
"value": "Harvard–Smithsonian Center for Astrophysics_header_cell_0_0_0"
},
{
"operation": "finish",
"time": "87.661",
"value": "finish"
}
]
}
|
42567
|
Alistair Petrie joined the National Theatre in 2005 before appearing in Marc Munden's The Mark of Cain.
|
{
"evidence": [
"Alistair Petrie_sentence_8",
"Alistair Petrie_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:\nAlistair Petrie joined the National Theatre in 2005 before appearing in Marc Munden's The Mark of Cain.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Alistair Petrie_sentence_8",
"Alistair Petrie_sentence_9"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4129,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.69",
"value": "?search="
},
{
"operation": "search",
"time": "10.835",
"value": "Contains...Allstair Petrie"
},
{
"operation": "Now on",
"time": "12.22",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "14.32",
"value": "Alistair Petrie"
},
{
"operation": "Now on",
"time": "15.012",
"value": "Alistair Petrie"
},
{
"operation": "Page search",
"time": "19.678",
"value": "national theatre"
},
{
"operation": "Highlighting",
"time": "25.053",
"value": "Alistair Petrie_sentence_8"
},
{
"operation": "Highlighting",
"time": "34.302",
"value": "Alistair Petrie_sentence_9"
},
{
"operation": "finish",
"time": "63.129",
"value": "finish"
}
]
}
|
61980
|
Palazzo Grimani di San Luca was built in the mid-16th century for procurator Gerolamo Grimani by architect Michele Sanmicheli (who regularised the Piazza Brà, opening up a vista to the Arena) with a classical plan and a central atrium.
|
{
"evidence": [
"Palazzo Grimani di San Luca_sentence_1",
"Michele Sanmicheli_sentence_15",
"Palazzo Grimani di San Luca_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:\nPalazzo Grimani di San Luca was built in the mid-16th century for procurator Gerolamo Grimani by architect Michele Sanmicheli (who regularised the Piazza Brà, opening up a vista to the Arena) with a classical plan and a central atrium.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Palazzo Grimani di San Luca_sentence_1",
"Michele Sanmicheli_sentence_15",
"Palazzo Grimani di San Luca_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4130,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "4.081",
"value": "undefined"
},
{
"operation": "search",
"time": "11.378",
"value": "Palazzo Grimani di San Luca"
},
{
"operation": "Now on",
"time": "12.176",
"value": "Palazzo Grimani di San Luca"
},
{
"operation": "Highlighting",
"time": "19.674",
"value": "Palazzo Grimani di San Luca_sentence_1"
},
{
"operation": "hyperlink",
"time": "33.727",
"value": "Michele Sanmicheli"
},
{
"operation": "Now on",
"time": "34.468",
"value": "Michele Sanmicheli"
},
{
"operation": "Page search",
"time": "45.631",
"value": "Piazza Brà"
},
{
"operation": "Highlighting",
"time": "57.263",
"value": "Michele Sanmicheli_sentence_15"
},
{
"operation": "back-button-clicked",
"time": "62.624",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "62.86",
"value": "Palazzo Grimani di San Luca"
},
{
"operation": "Highlighting",
"time": "67.592",
"value": "Palazzo Grimani di San Luca_sentence_2"
},
{
"operation": "finish",
"time": "75.127",
"value": "finish"
}
]
}
|
exfever_6344
|
To Kill a Mockingbird is a 1962 American film directed by Robert Mulligan, whose category of narrative fiction is intended to be more serious than humorous in tone.
|
{
"evidence": [
"To Kill a Mockingbird (film)",
"Drama (film and television)"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nTo Kill a Mockingbird is a 1962 American film directed by Robert Mulligan, whose category of narrative fiction is intended to be more serious than humorous in tone.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"To Kill a Mockingbird (film)",
"Drama (film and television)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4131,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_3069
|
A medical school is funded by private individuals.
|
{
"evidence": [
"Medical school",
"Doctor of Philosophy"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nA medical school is funded by private individuals.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Medical school",
"Doctor of Philosophy"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4132,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
86301
|
Wioletta Kryza, also known as Violetta Kryza, is a Polish long-distance marathon runner that has multiple first place wins from 1992 to 2007.
|
{
"evidence": [
"Wioletta Kryza_sentence_0",
"Wioletta Kryza_sentence_2",
"Wioletta Kryza_sentence_3",
"Wioletta Kryza_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:\nWioletta Kryza, also known as Violetta Kryza, is a Polish long-distance marathon runner that has multiple first place wins from 1992 to 2007.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Wioletta Kryza_sentence_0",
"Wioletta Kryza_sentence_2",
"Wioletta Kryza_sentence_3",
"Wioletta Kryza_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4133,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.002",
"value": "?search="
},
{
"operation": "search",
"time": "14.175",
"value": "Wioletta Kryza"
},
{
"operation": "Now on",
"time": "15.075",
"value": "Wioletta Kryza"
},
{
"operation": "Highlighting",
"time": "18.658",
"value": "Wioletta Kryza_sentence_0"
},
{
"operation": "Highlighting",
"time": "34.225",
"value": "Wioletta Kryza_sentence_2"
},
{
"operation": "Highlighting",
"time": "38.286",
"value": "Wioletta Kryza_sentence_3"
},
{
"operation": "Highlighting",
"time": "47.57",
"value": "Wioletta Kryza_sentence_5"
},
{
"operation": "Highlighting",
"time": "54.161",
"value": "Wioletta Kryza_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "61.758",
"value": "Wioletta Kryza_sentence_5"
},
{
"operation": "finish",
"time": "79.094",
"value": "finish"
}
]
}
|
43322
|
Speed skating in 2007 included the Fall World Cup Qualifier which featured five events for both men and women.
|
{
"evidence": [
"2006–07 ISU Speed Skating World Cup_sentence_0",
"2006–07 ISU Speed Skating World Cup_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:\nSpeed skating in 2007 included the Fall World Cup Qualifier which featured five events for both men and women.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"2006–07 ISU Speed Skating World Cup_sentence_0",
"2006–07 ISU Speed Skating World Cup_sentence_1"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4134,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.834",
"value": "?search="
},
{
"operation": "search",
"time": "14.366",
"value": "Speed skating in 2007"
},
{
"operation": "Now on",
"time": "16.042",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "21.228",
"value": "2007 World Cup"
},
{
"operation": "Now on",
"time": "22.456",
"value": "2007 World Cup"
},
{
"operation": "search",
"time": "39.789",
"value": "2007 Fall World Cup Qualifier"
},
{
"operation": "Now on",
"time": "41.228",
"value": "undefined"
},
{
"operation": "search",
"time": "73.884",
"value": "Speed skating at 2007 Fall World Cup"
},
{
"operation": "Now on",
"time": "75.041",
"value": "undefined"
},
{
"operation": "search",
"time": "95.593",
"value": "speed skating 2007"
},
{
"operation": "Now on",
"time": "96.525",
"value": "undefined"
},
{
"operation": "search",
"time": "113.245",
"value": "2007 Fall World Cup Qualifier"
},
{
"operation": "Now on",
"time": "113.78",
"value": "undefined"
},
{
"operation": "search",
"time": "132.349",
"value": "speed skating"
},
{
"operation": "Now on",
"time": "133.422",
"value": "Speed skating"
},
{
"operation": "Page search",
"time": "138.786",
"value": "2007"
},
{
"operation": "search",
"time": "170.09",
"value": "Fall World Cup 2007"
},
{
"operation": "Now on",
"time": "171.184",
"value": "undefined"
},
{
"operation": "search",
"time": "194.886",
"value": "SPeed skating at 2007 world cup"
},
{
"operation": "Now on",
"time": "195.861",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "199.616",
"value": "2007 World Cup"
},
{
"operation": "Now on",
"time": "200.017",
"value": "2007 World Cup"
},
{
"operation": "hyperlink",
"time": "204.45",
"value": "2007 Speed Skating World Cup"
},
{
"operation": "Now on",
"time": "205.011",
"value": "2006–07 ISU Speed Skating World Cup"
},
{
"operation": "hyperlink",
"time": "230.054",
"value": "ISU Speed Skating World Cup"
},
{
"operation": "Now on",
"time": "232.169",
"value": "ISU Speed Skating World Cup"
},
{
"operation": "hyperlink",
"time": "244.158",
"value": "2006–07"
},
{
"operation": "Now on",
"time": "244.94",
"value": "2006–07 ISU Speed Skating World Cup"
},
{
"operation": "Highlighting",
"time": "313.162",
"value": "2006–07 ISU Speed Skating World Cup_sentence_0"
},
{
"operation": "Highlighting",
"time": "314.609",
"value": "2006–07 ISU Speed Skating World Cup_sentence_1"
},
{
"operation": "finish",
"time": "321.568",
"value": "finish"
}
]
}
|
2472
|
Hassanat Akinwande started her career in the 1980s and eventually starred in over 50 videos but was arrested in 2006 for possession illegal substance.
|
{
"evidence": [
"Hassanat Akinwande_sentence_2",
"Hassanat Akinwande_sentence_3",
"Hassanat Akinwande_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:\nHassanat Akinwande started her career in the 1980s and eventually starred in over 50 videos but was arrested in 2006 for possession illegal substance.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Hassanat Akinwande_sentence_2",
"Hassanat Akinwande_sentence_3",
"Hassanat Akinwande_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4135,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "8.987",
"value": "Hassanat Akinwande"
},
{
"operation": "Highlighting",
"time": "20.017",
"value": "Hassanat Akinwande_sentence_2"
},
{
"operation": "Highlighting",
"time": "33.747",
"value": "Hassanat Akinwande_sentence_3"
},
{
"operation": "Highlighting",
"time": "37.026",
"value": "Hassanat Akinwande_sentence_4"
},
{
"operation": "finish",
"time": "56.768",
"value": "finish"
}
]
}
|
47686
|
Wolff Schoemaker designed the Trade Fair Center, it has a cross-shaped floor plan and was designed in a modern style.
|
{
"evidence": [
"Charles Prosper Wolff Schoemaker_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:\nWolff Schoemaker designed the Trade Fair Center, it has a cross-shaped floor plan and was designed in a modern style.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Charles Prosper Wolff Schoemaker_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4136,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.329",
"value": "?search="
},
{
"operation": "search",
"time": "9.752",
"value": "Wolff Schoemaker"
},
{
"operation": "Now on",
"time": "11.416",
"value": "Charles Prosper Wolff Schoemaker"
},
{
"operation": "Highlighting",
"time": "25.697",
"value": "Charles Prosper Wolff Schoemaker_sentence_0"
},
{
"operation": "hyperlink",
"time": "29.656",
"value": "Wolff Schoemaker"
},
{
"operation": "Now on",
"time": "30.933",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "36.582",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "37.333",
"value": "Charles Prosper Wolff Schoemaker"
},
{
"operation": "Highlighting deleted",
"time": "43.118",
"value": "Charles Prosper Wolff Schoemaker_sentence_0"
},
{
"operation": "search",
"time": "48.504",
"value": "Wolff Schoemaker"
},
{
"operation": "Now on",
"time": "49.505",
"value": "Wolff Schoemaker"
},
{
"operation": "Highlighting",
"time": "56.719",
"value": "Charles Prosper Wolff Schoemaker_sentence_0"
},
{
"operation": "Page search",
"time": "69.399",
"value": "trade"
},
{
"operation": "Page search",
"time": "69.582",
"value": "trade"
},
{
"operation": "Page search",
"time": "69.741",
"value": "trade"
},
{
"operation": "search",
"time": "92.527",
"value": "trade fair center"
},
{
"operation": "Now on",
"time": "94.713",
"value": "undefined"
},
{
"operation": "search",
"time": "116.614",
"value": "Contains...trade fair center"
},
{
"operation": "Now on",
"time": "117.398",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "119.473",
"value": "Charlottenburg-Wilmersdorf"
},
{
"operation": "Now on",
"time": "120.457",
"value": "Charlottenburg-Wilmersdorf"
},
{
"operation": "Page search",
"time": "133.159",
"value": "trade"
},
{
"operation": "back-button-clicked",
"time": "151.648",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "152.595",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "153.507",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "153.54",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "154.421",
"value": "undefined"
},
{
"operation": "back-button-clicked",
"time": "155.191",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "155.221",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "155.738",
"value": "Charles Prosper Wolff Schoemaker"
},
{
"operation": "Highlighting",
"time": "160.065",
"value": "Charles Prosper Wolff Schoemaker_sentence_0"
},
{
"operation": "Page search",
"time": "176.034",
"value": "trade"
},
{
"operation": "Page search",
"time": "176.5",
"value": "trade"
},
{
"operation": "Page search",
"time": "176.704",
"value": "trade"
},
{
"operation": "Highlighting",
"time": "231.691",
"value": "Charles Prosper Wolff Schoemaker_sentence_13Charles Prosper Wolff Schoemaker_sentence_14"
},
{
"operation": "Highlighting",
"time": "231.696",
"value": "Charles Prosper Wolff Schoemaker_section_1"
},
{
"operation": "Highlighting deleted",
"time": "402.676",
"value": "Charles Prosper Wolff Schoemaker_sentence_13Charles Prosper Wolff Schoemaker_sentence_14"
},
{
"operation": "Highlighting deleted",
"time": "402.682",
"value": "Charles Prosper Wolff Schoemaker_section_1"
},
{
"operation": "finish",
"time": "408.597",
"value": "finish"
}
]
}
|
exfever_5334
|
Lake Powell is an artificial reservoir on the Colorado River in Utah and the 6th largest and the 14th most populous of the 52 states.
|
{
"evidence": [
"Lake Powell",
"Arizona"
],
"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:\nLake Powell is an artificial reservoir on the Colorado River in Utah and the 6th largest and the 14th most populous of the 52 states.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Lake Powell",
"Arizona"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4137,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7657
|
The Champ is a 1979 American neo-noir drama sports film starring an American author who received many accolades, including an Academy Award.
|
{
"evidence": [
"The Champ (1979 film)",
"Faye Dunaway"
],
"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 Champ is a 1979 American neo-noir drama sports film starring an American author who received many accolades, including an Academy Award.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"The Champ (1979 film)",
"Faye Dunaway"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4138,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
82757
|
The Administration for Native Americans (ANA) is a program office formed in 1974 within the United States Department of Health and Human Services, that oversees the Native Hawaiian Revolving Loan Fund and aims to promote the goal of self-sufficiency and cultural preservation by providing social and economic development opportunities through financial assistance, training, and technical assistance to eligible tribes and Native American communities.
|
{
"evidence": [
"Administration for Native Americans_sentence_0",
"Administration for Native Americans_sentence_2",
"Administration for Native Americans_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:\nThe Administration for Native Americans (ANA) is a program office formed in 1974 within the United States Department of Health and Human Services, that oversees the Native Hawaiian Revolving Loan Fund and aims to promote the goal of self-sufficiency and cultural preservation by providing social and economic development opportunities through financial assistance, training, and technical assistance to eligible tribes and Native American communities.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Administration for Native Americans_sentence_0",
"Administration for Native Americans_sentence_2",
"Administration for Native Americans_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4139,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.173",
"value": "undefined"
},
{
"operation": "search",
"time": "16.419",
"value": "Administration for Native Americans"
},
{
"operation": "Now on",
"time": "17.92",
"value": "Administration for Native Americans"
},
{
"operation": "Highlighting",
"time": "28.076",
"value": "Administration for Native Americans_sentence_0"
},
{
"operation": "Highlighting",
"time": "49.965",
"value": "Administration for Native Americans_sentence_2"
},
{
"operation": "Highlighting",
"time": "70.335",
"value": "Administration for Native Americans_sentence_1"
},
{
"operation": "finish",
"time": "105.334",
"value": "finish"
}
]
}
|
exfever_3574
|
Back to the Future Part II is an Indian science fiction film directed by Robert Zemeckis and starring an American actress best known for her role in the movie The Karate Kid.
|
{
"evidence": [
"Back to the Future Part II",
"Elisabeth Shue"
],
"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:\nBack to the Future Part II is an Indian science fiction film directed by Robert Zemeckis and starring an American actress best known for her role in the movie The Karate Kid.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Back to the Future Part II",
"Elisabeth Shue"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4140,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
40503
|
An artist, who was born in a notable family in Uruguay, enjoyed poems, stories and organizing poetry gatherings.
|
{
"evidence": [
"Juan Zorrilla de San Martín_sentence_0",
"Juan Zorrilla de San Martín_sentence_1",
"Juan Zorrilla de San Martín_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:\nAn artist, who was born in a notable family in Uruguay, enjoyed poems, stories and organizing poetry gatherings.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Juan Zorrilla de San Martín_sentence_0",
"Juan Zorrilla de San Martín_sentence_1",
"Juan Zorrilla de San Martín_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4141,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.276",
"value": "?search="
},
{
"operation": "search",
"time": "63.91",
"value": "Uruguay artist"
},
{
"operation": "Now on",
"time": "65.825",
"value": "undefined"
},
{
"operation": "Page search",
"time": "75.158",
"value": "poetry"
},
{
"operation": "search",
"time": "94.005",
"value": "Uruguay poet"
},
{
"operation": "Now on",
"time": "95.664",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "102.075",
"value": "Líber Falco"
},
{
"operation": "Now on",
"time": "102.808",
"value": "Líber Falco"
},
{
"operation": "Page search",
"time": "115.089",
"value": "notable"
},
{
"operation": "back-button-clicked",
"time": "118.237",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "119.056",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "120.563",
"value": "Juan Zorrilla de San Martín"
},
{
"operation": "Now on",
"time": "121.67",
"value": "Juan Zorrilla de San Martín"
},
{
"operation": "Page search",
"time": "125.613",
"value": "notable"
},
{
"operation": "Highlighting",
"time": "147.275",
"value": "Juan Zorrilla de San Martín_sentence_0"
},
{
"operation": "Highlighting",
"time": "150.836",
"value": "Juan Zorrilla de San Martín_sentence_1"
},
{
"operation": "Highlighting",
"time": "152.754",
"value": "Juan Zorrilla de San Martín_sentence_3"
},
{
"operation": "back-button-clicked",
"time": "172.234",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "173.045",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "176.046",
"value": "Libertango"
},
{
"operation": "Now on",
"time": "178.524",
"value": "Libertango"
},
{
"operation": "Page search",
"time": "182.926",
"value": "notable"
},
{
"operation": "back-button-clicked",
"time": "195.422",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "196.224",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "198.911",
"value": "Salvador Bécquer Puig"
},
{
"operation": "Now on",
"time": "199.64",
"value": "Salvador Bécquer Puig"
},
{
"operation": "back-button-clicked",
"time": "207.946",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "208.799",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "212.481",
"value": "Emilio Oribe"
},
{
"operation": "Now on",
"time": "213.226",
"value": "Emilio Oribe"
},
{
"operation": "back-button-clicked",
"time": "218.622",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "219.912",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "222.551",
"value": "Horacio Quiroga"
},
{
"operation": "Now on",
"time": "223.637",
"value": "Horacio Quiroga"
},
{
"operation": "back-button-clicked",
"time": "235.878",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "236.676",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "239.751",
"value": "Rafael Barradas"
},
{
"operation": "Now on",
"time": "240.469",
"value": "Rafael Barradas"
},
{
"operation": "back-button-clicked",
"time": "247.307",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "249.327",
"value": "undefined"
},
{
"operation": "finish",
"time": "283.828",
"value": "finish"
}
]
}
|
51584
|
Riverton Bridge is a two lane traffic bridge in New Zealand, it was originally built in 1911 and by the 1930s the bridge had fallen into disrepair.
|
{
"evidence": [
"Riverton Bridge_sentence_2"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nRiverton Bridge is a two lane traffic bridge in New Zealand, it was originally built in 1911 and by the 1930s the bridge had fallen into disrepair.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Riverton Bridge_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4142,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.988",
"value": "?search="
},
{
"operation": "search",
"time": "24.546",
"value": "Riverton Bridge"
},
{
"operation": "Now on",
"time": "27.498",
"value": "Riverton Bridge"
},
{
"operation": "Highlighting",
"time": "55.898",
"value": "Riverton Bridge_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "59.936",
"value": "Riverton Bridge_sentence_3"
},
{
"operation": "Highlighting",
"time": "60.37",
"value": "Riverton Bridge_sentence_2"
},
{
"operation": "Highlighting",
"time": "60.956",
"value": "Riverton Bridge_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "63.996",
"value": "Riverton Bridge_sentence_3"
},
{
"operation": "finish",
"time": "98.271",
"value": "finish"
}
]
}
|
25213
|
Operation Choke Point was the focus of the hearing held by the House Financial Services Committee—a US House of Representatives’ committee that oversees all the financial services industry—on April 2014 wherein four months after, a bill that limits the means of law enforcement to restrict access to banking system was introduced as an opposing response.
|
{
"evidence": [
"Operation Choke Point_sentence_22",
"Operation Choke Point_sentence_21",
"United States House Committee on Financial Services_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:\nOperation Choke Point was the focus of the hearing held by the House Financial Services Committee—a US House of Representatives’ committee that oversees all the financial services industry—on April 2014 wherein four months after, a bill that limits the means of law enforcement to restrict access to banking system was introduced as an opposing response.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Operation Choke Point_sentence_22",
"Operation Choke Point_sentence_21",
"United States House Committee on Financial Services_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4143,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.849",
"value": "?search="
},
{
"operation": "search",
"time": "25.385",
"value": "Operation Choke Point"
},
{
"operation": "Now on",
"time": "26.12",
"value": "Operation Choke Point"
},
{
"operation": "Page search",
"time": "62.087",
"value": "house financial services committee"
},
{
"operation": "Highlighting",
"time": "76.542",
"value": "Operation Choke Point_sentence_22"
},
{
"operation": "Page search",
"time": "167.747",
"value": "four months after"
},
{
"operation": "Highlighting",
"time": "179.747",
"value": "Operation Choke Point_sentence_21"
},
{
"operation": "hyperlink",
"time": "189.402",
"value": "House Financial Services Committee"
},
{
"operation": "Now on",
"time": "189.976",
"value": "United States House Committee on Financial Services"
},
{
"operation": "Highlighting",
"time": "201.034",
"value": "United States House Committee on Financial Services_sentence_0"
},
{
"operation": "finish",
"time": "239.433",
"value": "finish"
}
]
}
|
exfever_5463
|
Drake is the greatest Canadian rapper.
|
{
"evidence": [
"Views (album)",
"PartyNextDoor",
"PartyNextDoor Two"
],
"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:\nDrake is the greatest Canadian rapper.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Views (album)",
"PartyNextDoor",
"PartyNextDoor Two"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4144,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
65353
|
Rachid Baba Ahmed (20 August 1946 – 15 February 1995) was a Algerian record producer, composer, and singerinvolved in the regional genre known as raï and dubbed as the ‘Jean-Michel Jarre of raï’
|
{
"evidence": [
"Rachid Baba Ahmed_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:\nRachid Baba Ahmed (20 August 1946 – 15 February 1995) was a Algerian record producer, composer, and singerinvolved in the regional genre known as raï and dubbed as the ‘Jean-Michel Jarre of raï’\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Rachid Baba Ahmed_sentence_0"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4145,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.904",
"value": "undefined"
},
{
"operation": "search",
"time": "14.416",
"value": "Rachid Baba Ahmed"
},
{
"operation": "Now on",
"time": "16.815",
"value": "Rachid Baba Ahmed"
},
{
"operation": "Highlighting",
"time": "21.439",
"value": "Rachid Baba Ahmed_sentence_0"
},
{
"operation": "hyperlink",
"time": "45.303",
"value": "raï"
},
{
"operation": "Now on",
"time": "49.172",
"value": "Raï"
},
{
"operation": "Page search",
"time": "54.848",
"value": "dubbed"
},
{
"operation": "Page search",
"time": "76.101",
"value": "jarre"
},
{
"operation": "back-button-clicked",
"time": "88.798",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "88.957",
"value": "Rachid Baba Ahmed"
},
{
"operation": "finish",
"time": "239.129",
"value": "finish"
}
]
}
|
exfever_2978
|
Kanye West gained recognition as a producer for an American record label and music management company.
|
{
"evidence": [
"Kanye West",
"Roc-A-Fella Records"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nKanye West gained recognition as a producer for an American record label and music management company.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Kanye West",
"Roc-A-Fella Records"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4146,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
83232
|
Uldis Sesks studied at Liepāja School, he graduated from the Latvian Academy of Agriculture in Jelgava and was chief of the transport department.
|
{
"evidence": [
"Uldis Sesks_sentence_2",
"Uldis Sesks_sentence_3",
"Uldis Sesks_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:\nUldis Sesks studied at Liepāja School, he graduated from the Latvian Academy of Agriculture in Jelgava and was chief of the transport department.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Uldis Sesks_sentence_2",
"Uldis Sesks_sentence_3",
"Uldis Sesks_sentence_4"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4147,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.718",
"value": "?search="
},
{
"operation": "search",
"time": "12.098",
"value": "Uldis Sesks"
},
{
"operation": "Now on",
"time": "12.812",
"value": "Uldis Sesks"
},
{
"operation": "Highlighting",
"time": "20.305",
"value": "Uldis Sesks_sentence_2"
},
{
"operation": "Highlighting",
"time": "23.51",
"value": "Uldis Sesks_sentence_3"
},
{
"operation": "Highlighting",
"time": "30.265",
"value": "Uldis Sesks_sentence_4"
},
{
"operation": "finish",
"time": "36.606",
"value": "finish"
}
]
}
|
7593
|
Académie royale de peinture et de sculpture office reverted to his predecessor Chancellor Séguier who named Jean-Baptiste Colbert (29 August 1619 – 6 September 1683)as Vice-protecteur.
|
{
"evidence": [
"Académie royale de peinture et de sculpture_sentence_19",
"Académie royale de peinture et de sculpture_sentence_20",
"Jean-Baptiste Colbert_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:\nAcadémie royale de peinture et de sculpture office reverted to his predecessor Chancellor Séguier who named Jean-Baptiste Colbert (29 August 1619 – 6 September 1683)as Vice-protecteur.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Académie royale de peinture et de sculpture_sentence_19",
"Académie royale de peinture et de sculpture_sentence_20",
"Jean-Baptiste Colbert_sentence_0"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4148,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.881",
"value": "?search="
},
{
"operation": "search",
"time": "34.699",
"value": "Académie royale de peinture et de sculpture"
},
{
"operation": "Now on",
"time": "35.71",
"value": "Académie royale de peinture et de sculpture"
},
{
"operation": "Page search",
"time": "56.388",
"value": "Chancellor Séguier"
},
{
"operation": "Highlighting",
"time": "61.57",
"value": "Académie royale de peinture et de sculpture_sentence_19"
},
{
"operation": "Highlighting",
"time": "71.514",
"value": "Académie royale de peinture et de sculpture_sentence_20"
},
{
"operation": "hyperlink",
"time": "74.779",
"value": "Jean-Baptiste Colbert"
},
{
"operation": "Now on",
"time": "75.852",
"value": "Jean-Baptiste Colbert"
},
{
"operation": "Highlighting",
"time": "77.309",
"value": "Jean-Baptiste Colbert_sentence_0"
},
{
"operation": "finish",
"time": "86.33",
"value": "finish"
}
]
}
|
14359
|
Hittite phonology has ten consonant pronouns and m (The bilabial nasal occurs in English) is a Labial Nasal pronoun.
|
{
"evidence": [
"Voiced bilabial nasal_sentence_2",
"Voiced bilabial nasal_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:\nHittite phonology has ten consonant pronouns and m (The bilabial nasal occurs in English) is a Labial Nasal pronoun.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Voiced bilabial nasal_sentence_2",
"Voiced bilabial nasal_sentence_3"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4149,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.466",
"value": "?search="
},
{
"operation": "search",
"time": "15.111",
"value": "Hittite"
},
{
"operation": "Now on",
"time": "16.449",
"value": "Hittite"
},
{
"operation": "hyperlink",
"time": "20.998",
"value": "Hittite language"
},
{
"operation": "Now on",
"time": "22.035",
"value": "Hittite language"
},
{
"operation": "search",
"time": "64.026",
"value": "\"Hittite\" \"consonant\" \"pronoun\" \"nasal\""
},
{
"operation": "Now on",
"time": "64.927",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "85.723",
"value": "Hittite Indo-European copula_section_27"
},
{
"operation": "Now on",
"time": "87.693",
"value": "Indo-European copula#Hittite Indo-European copula section 27"
},
{
"operation": "Page search",
"time": "129.765",
"value": "consonant"
},
{
"operation": "search",
"time": "324.68",
"value": "Contains...bilabial nasal occurs in English"
},
{
"operation": "Now on",
"time": "326.595",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "351.76",
"value": "Voiced bilabial nasal"
},
{
"operation": "Now on",
"time": "353.179",
"value": "Voiced bilabial nasal"
},
{
"operation": "search",
"time": "400.788",
"value": "Hittite phonology has ten consonant pronouns"
},
{
"operation": "Now on",
"time": "402.113",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "421.552",
"value": "Anatolian languages"
},
{
"operation": "Now on",
"time": "422.648",
"value": "Anatolian languages"
},
{
"operation": "Page search",
"time": "429.609",
"value": "pronoun"
},
{
"operation": "search",
"time": "512.447",
"value": "Labial Nasal pronoun"
},
{
"operation": "Now on",
"time": "513.577",
"value": "undefined"
},
{
"operation": "search",
"time": "534.973",
"value": "\"m\" \"nasal\" \"bilabial\""
},
{
"operation": "Now on",
"time": "535.806",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "554.752",
"value": "Sumerian language"
},
{
"operation": "Now on",
"time": "556.377",
"value": "Sumerian language"
},
{
"operation": "back-button-clicked",
"time": "557.123",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "557.853",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "586.805",
"value": "Voiced bilabial nasal"
},
{
"operation": "Now on",
"time": "587.52",
"value": "Voiced bilabial nasal"
},
{
"operation": "Highlighting",
"time": "625.437",
"value": "Voiced bilabial nasal_sentence_2"
},
{
"operation": "Highlighting",
"time": "627.043",
"value": "Voiced bilabial nasal_sentence_3"
},
{
"operation": "finish",
"time": "635.624",
"value": "finish"
}
]
}
|
73808
|
A Jewish journalist who was born in London in 1937, worked as a secretary of the a Congress and as a member of an political organization to promote the Zionist program of one of its members.
|
{
"evidence": [
"Jacob de Haas_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:\nA Jewish journalist who was born in London in 1937, worked as a secretary of the a Congress and as a member of an political organization to promote the Zionist program of one of its members.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Jacob de Haas_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4150,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.979",
"value": "?search="
},
{
"operation": "search",
"time": "21.999",
"value": "Secretary of the Congress"
},
{
"operation": "Now on",
"time": "25.621",
"value": "undefined"
},
{
"operation": "search",
"time": "42.372",
"value": "Jewish journalist 1937"
},
{
"operation": "Now on",
"time": "44.211",
"value": "undefined"
},
{
"operation": "search",
"time": "61.048",
"value": "Zionist program"
},
{
"operation": "Now on",
"time": "62.342",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "72.962",
"value": "Jacob de Haas"
},
{
"operation": "Now on",
"time": "73.475",
"value": "Jacob de Haas"
},
{
"operation": "Highlighting",
"time": "75.932",
"value": "Jacob de Haas_sentence_0"
},
{
"operation": "finish",
"time": "105.834",
"value": "finish"
}
]
}
|
37152
|
Dicoronylene is a by-products in petroleum processing formed when three or more ovalene molecules fuse.
|
{
"evidence": [
"Dicoronylene_sentence_14"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nDicoronylene is a by-products in petroleum processing formed when three or more ovalene molecules fuse.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Dicoronylene_sentence_14"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4151,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.577",
"value": "?search="
},
{
"operation": "search",
"time": "6.796",
"value": "Dicoronylene"
},
{
"operation": "Now on",
"time": "7.332",
"value": "Dicoronylene"
},
{
"operation": "Page search",
"time": "15.326",
"value": "by-pro"
},
{
"operation": "Highlighting",
"time": "18.967",
"value": "Dicoronylene_sentence_13"
},
{
"operation": "Highlighting deleted",
"time": "34.916",
"value": "Dicoronylene_sentence_13"
},
{
"operation": "Highlighting",
"time": "35.548",
"value": "Dicoronylene_sentence_14"
},
{
"operation": "Page search",
"time": "47.382",
"value": "molecule"
},
{
"operation": "finish",
"time": "68.615",
"value": "finish"
}
]
}
|
exfever_2721
|
American Idiot is the seventh studio album by American rock band Green Day, released on September 21, 2004, by an American record label founded in 1960 by Frank Sinatra.
|
{
"evidence": [
"American Idiot",
"Reprise Records"
],
"label": "SUPPORT"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAmerican Idiot is the seventh studio album by American rock band Green Day, released on September 21, 2004, by an American record label founded in 1960 by Frank Sinatra.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"American Idiot",
"Reprise Records"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4152,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
49973
|
Trang Province was once a part of the Srivijaya empire and was one of 12 satellite towns that existed almost a thousand years ago according to cultural records.
|
{
"evidence": [
"Trang Province_sentence_18",
"Trang Province_sentence_19"
],
"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:\nTrang Province was once a part of the Srivijaya empire and was one of 12 satellite towns that existed almost a thousand years ago according to cultural records.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Trang Province_sentence_18",
"Trang Province_sentence_19"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4153,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.667",
"value": "?search="
},
{
"operation": "search",
"time": "14.685",
"value": "Trang Province"
},
{
"operation": "Now on",
"time": "15.79",
"value": "Trang Province"
},
{
"operation": "Page search",
"time": "30.109",
"value": "Srivijaya"
},
{
"operation": "Highlighting",
"time": "35.772",
"value": "Trang Province_sentence_18"
},
{
"operation": "Highlighting",
"time": "41.268",
"value": "Trang Province_sentence_19"
},
{
"operation": "finish",
"time": "55.251",
"value": "finish"
}
]
}
|
508
|
Jon Beason was drafted in the first round of the 2007 NFL Draft by the New York Giants who went on to finish the season with a 7-9 record.
|
{
"evidence": [
"Jon Beason_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:\nJon Beason was drafted in the first round of the 2007 NFL Draft by the New York Giants who went on to finish the season with a 7-9 record.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jon Beason_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4154,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "18.246",
"value": "Jon Beason"
},
{
"operation": "Highlighting",
"time": "34.89",
"value": "Jon Beason_sentence_1"
},
{
"operation": "finish",
"time": "65.808",
"value": "finish"
}
]
}
|
exfever_4623
|
Amsterdam is the capital and most populous city of the country, located in Northwestern Europe with overseas territories in the Caribbean.
|
{
"evidence": [
"Amsterdam",
"Netherlands"
],
"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:\nAmsterdam is the capital and most populous city of the country, located in Northwestern Europe with overseas territories in the Caribbean.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Amsterdam",
"Netherlands"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4155,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
11434
|
All of the fifty Sm2 units built between 1975 and 1981 by Valmet in Tampere were partially renovated between 2000 and 2011.
|
{
"evidence": [
"VR Class Sm2_sentence_2"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nAll of the fifty Sm2 units built between 1975 and 1981 by Valmet in Tampere were partially renovated between 2000 and 2011.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"VR Class Sm2_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4156,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.718",
"value": "?search="
},
{
"operation": "search",
"time": "10.422",
"value": "fifty Sm2"
},
{
"operation": "Now on",
"time": "11.638",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "21.505",
"value": "VR Class Sm2"
},
{
"operation": "Now on",
"time": "21.996",
"value": "VR Class Sm2"
},
{
"operation": "search",
"time": "47.607",
"value": "Sm2"
},
{
"operation": "Now on",
"time": "48.302",
"value": "SM2"
},
{
"operation": "search",
"time": "55.63",
"value": "Sm2 units"
},
{
"operation": "Now on",
"time": "57.146",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "61.529",
"value": "VR Class Sm2"
},
{
"operation": "Now on",
"time": "61.826",
"value": "VR Class Sm2"
},
{
"operation": "Highlighting",
"time": "71.682",
"value": "VR Class Sm2_sentence_1"
},
{
"operation": "Highlighting",
"time": "74.257",
"value": "VR Class Sm2_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "88.894",
"value": "VR Class Sm2_sentence_1"
},
{
"operation": "Highlighting",
"time": "91.333",
"value": "VR Class Sm2_sentence_1"
},
{
"operation": "Highlighting deleted",
"time": "92.708",
"value": "VR Class Sm2_sentence_2"
},
{
"operation": "Highlighting",
"time": "93.542",
"value": "VR Class Sm2_sentence_2"
},
{
"operation": "Highlighting deleted",
"time": "97.676",
"value": "VR Class Sm2_sentence_1"
},
{
"operation": "finish",
"time": "105.19",
"value": "finish"
}
]
}
|
exfever_3572
|
Saif Ali Khan is the most successful Indian actor.
|
{
"evidence": [
"Saif Ali Khan",
"Yash Chopra"
],
"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:\nSaif Ali Khan is the most successful Indian actor.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Saif Ali Khan",
"Yash Chopra"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4157,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
34009
|
The Taipei Medical University was established in 2000, has over 6,112 students and was 10th place in overall national ranking.
|
{
"evidence": [
"Taipei Medical University_sentence_1"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Taipei Medical University was established in 2000, has over 6,112 students and was 10th place in overall national ranking.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Taipei Medical University_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4158,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.219",
"value": "?search="
},
{
"operation": "search",
"time": "13.781",
"value": "Taipei Medical University"
},
{
"operation": "Now on",
"time": "15.113",
"value": "Taipei Medical University"
},
{
"operation": "Highlighting",
"time": "33.977",
"value": "Taipei Medical University_sentence_1"
},
{
"operation": "finish",
"time": "93.665",
"value": "finish"
}
]
}
|
82001
|
A number of prostitutes dance in adult night clubs and a percentage of them are from other countries, who work in the more sophisticated night clubs in Kingston, which cater mainly to tourists, foreign workers, diplomats and affluent locals.
|
{
"evidence": [
"Prostitution in Jamaica_sentence_7",
"Prostitution in Jamaica_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:\nA number of prostitutes dance in adult night clubs and a percentage of them are from other countries, who work in the more sophisticated night clubs in Kingston, which cater mainly to tourists, foreign workers, diplomats and affluent locals.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Prostitution in Jamaica_sentence_7",
"Prostitution in Jamaica_sentence_8"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4159,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.548",
"value": "undefined"
},
{
"operation": "search",
"time": "177.562",
"value": "Prostitution in Jamaica"
},
{
"operation": "Now on",
"time": "178.457",
"value": "Prostitution in Jamaica"
},
{
"operation": "Highlighting",
"time": "210.231",
"value": "Prostitution in Jamaica_sentence_7"
},
{
"operation": "Highlighting",
"time": "222.724",
"value": "Prostitution in Jamaica_sentence_8"
},
{
"operation": "finish",
"time": "249.477",
"value": "finish"
}
]
}
|
exfever_432
|
See You on the Other Side is the eighth studio album by an American nu metal band from Bakersfield, California, formed in 1993.
|
{
"evidence": [
"See You on the Other Side (Korn album)",
"Korn"
],
"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:\nSee You on the Other Side is the eighth studio album by an American nu metal band from Bakersfield, California, formed in 1993.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"See You on the Other Side (Korn album)",
"Korn"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4160,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
50089
|
The Durham Light Infantry would send 22 battalions overseas and lose 12006 other ranks during the course of the war, and the regiment's territorial components formed duplicate second line battalions, though rejected the idea of a third one, of progressively lower fitness men.
|
{
"evidence": [
"List of battalions of the Durham Light Infantry_sentence_13"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Durham Light Infantry would send 22 battalions overseas and lose 12006 other ranks during the course of the war, and the regiment's territorial components formed duplicate second line battalions, though rejected the idea of a third one, of progressively lower fitness men.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"List of battalions of the Durham Light Infantry_sentence_13"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4161,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.999",
"value": "?search="
},
{
"operation": "search",
"time": "26.897",
"value": "The Durham Light Infantry"
},
{
"operation": "Now on",
"time": "28.734",
"value": "Durham Light Infantry"
},
{
"operation": "Page search",
"time": "88.635",
"value": "22"
},
{
"operation": "Page search",
"time": "116.935",
"value": "22 battalions overseas"
},
{
"operation": "Page search",
"time": "146.365",
"value": "during the course of the war"
},
{
"operation": "Highlighting",
"time": "171.291",
"value": "Durham Light Infantry_table_caption_1"
},
{
"operation": "Highlighting",
"time": "171.292",
"value": "Durham Light Infantry_title"
},
{
"operation": "Highlighting",
"time": "171.292",
"value": "Durham Light Infantry_section_1"
},
{
"operation": "Highlighting",
"time": "171.292",
"value": "Durham Light Infantry_section_5"
},
{
"operation": "hyperlink",
"time": "209.458",
"value": "List of battalions of the Durham Light Infantry § First World War"
},
{
"operation": "hyperlink",
"time": "213.801",
"value": "List of battalions of the Durham Light Infantry § First World War"
},
{
"operation": "Now on",
"time": "215.187",
"value": "List of battalions of the Durham Light Infantry#First World War"
},
{
"operation": "Highlighting",
"time": "259.056",
"value": "List of battalions of the Durham Light Infantry_sentence_12"
},
{
"operation": "Highlighting",
"time": "272.192",
"value": "List of battalions of the Durham Light Infantry_sentence_13"
},
{
"operation": "Highlighting deleted",
"time": "296.207",
"value": "List of battalions of the Durham Light Infantry_sentence_12"
},
{
"operation": "finish",
"time": "301.311",
"value": "finish"
}
]
}
|
77340
|
The 2016 Men's US Junior Squash Championships (December 16 – 19, 2016) is the men's edition of the 2016 US Junior Open squash championship and Mexico's Leonel Cárdenas won his fourth US Junior Open title, defeating Adhitya Raghavan of India in the Boys' Under 19 final.
|
{
"evidence": [
"2017 US Junior Open Squash Championships_sentence_2"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe 2016 Men's US Junior Squash Championships (December 16 – 19, 2016) is the men's edition of the 2016 US Junior Open squash championship and Mexico's Leonel Cárdenas won his fourth US Junior Open title, defeating Adhitya Raghavan of India in the Boys' Under 19 final.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"2017 US Junior Open Squash Championships_sentence_2"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4162,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.471",
"value": "?search="
},
{
"operation": "search",
"time": "47.548",
"value": "2016 Men's US Junior Squash Championships"
},
{
"operation": "Now on",
"time": "49.908",
"value": "undefined"
},
{
"operation": "search",
"time": "118.016",
"value": "Junior Squash Championships"
},
{
"operation": "Now on",
"time": "118.712",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "148.451",
"value": "2016 Men's World Junior Team Squash Championships"
},
{
"operation": "Now on",
"time": "149.323",
"value": "2016 Men's World Junior Team Squash Championships"
},
{
"operation": "hyperlink",
"time": "158.65",
"value": "United States"
},
{
"operation": "Now on",
"time": "159.2",
"value": "United States men's national squash team"
},
{
"operation": "back-button-clicked",
"time": "196.196",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "196.273",
"value": "2016 Men's World Junior Team Squash Championships"
},
{
"operation": "hyperlink",
"time": "204.501",
"value": "2016 Men's World Junior Squash Championships"
},
{
"operation": "Now on",
"time": "204.961",
"value": "2016 Men's World Junior Squash Championships"
},
{
"operation": "back-button-clicked",
"time": "256.87",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "256.944",
"value": "2016 Men's World Junior Team Squash Championships"
},
{
"operation": "hyperlink",
"time": "260.064",
"value": "United States"
},
{
"operation": "Now on",
"time": "260.361",
"value": "United States men's national squash team"
},
{
"operation": "search",
"time": "314.509",
"value": "is the men's edition of the 2016 US Junior Open squash championship"
},
{
"operation": "Now on",
"time": "316.473",
"value": "undefined"
},
{
"operation": "search",
"time": "325.746",
"value": "\"is the men's edition of the 2016 US Junior Open squash championship\""
},
{
"operation": "Now on",
"time": "326.044",
"value": "undefined"
},
{
"operation": "search",
"time": "346.154",
"value": "is the men's edition of the 2016 United States Open"
},
{
"operation": "Now on",
"time": "349.582",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "375.738",
"value": "Men's United States Open (squash) 2016"
},
{
"operation": "Now on",
"time": "376.26",
"value": "Men's United States Open (squash) 2016"
},
{
"operation": "search",
"time": "412.191",
"value": "Leonel Cárdenas"
},
{
"operation": "Now on",
"time": "412.728",
"value": "Leonel Cárdenas"
},
{
"operation": "search",
"time": "465.189",
"value": "\"Leonel Cárdenas\""
},
{
"operation": "Now on",
"time": "466.291",
"value": "Leonel Cárdenas"
},
{
"operation": "search",
"time": "470.021",
"value": "\"Leonel Cárdenas\""
},
{
"operation": "Now on",
"time": "471.289",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "490.992",
"value": "2017 US Junior Open Squash Championships"
},
{
"operation": "Now on",
"time": "491.498",
"value": "2017 US Junior Open Squash Championships"
},
{
"operation": "hyperlink",
"time": "495.626",
"value": "US Junior Open squash championship"
},
{
"operation": "Now on",
"time": "496.75",
"value": "US Junior Open squash championship"
},
{
"operation": "Highlighting",
"time": "547.456",
"value": "US Junior Open squash championship_cell_1_18_0"
},
{
"operation": "Highlighting",
"time": "547.459",
"value": "US Junior Open squash championship_title"
},
{
"operation": "Highlighting",
"time": "547.46",
"value": "US Junior Open squash championship_section_0"
},
{
"operation": "Highlighting",
"time": "547.466",
"value": "US Junior Open squash championship_header_cell_1_0_0"
},
{
"operation": "search",
"time": "605.2",
"value": "adhitya Raghavan"
},
{
"operation": "Now on",
"time": "605.817",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "612.271",
"value": "2017 US Junior Open Squash Championships"
},
{
"operation": "Now on",
"time": "612.568",
"value": "2017 US Junior Open Squash Championships"
},
{
"operation": "Highlighting",
"time": "618.05",
"value": "2017 US Junior Open Squash Championships_sentence_2"
},
{
"operation": "finish",
"time": "659.27",
"value": "finish"
}
]
}
|
exfever_253
|
The Wars of the Roses were the second series of civil wars fought over control of the English throne in the mid-to-late fifteenth century.
|
{
"evidence": [
"Wars of the Roses",
"Cadet branch",
"Europe"
],
"label": "NOT ENOUGH INFO"
}
|
exfever
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe Wars of the Roses were the second series of civil wars fought over control of the English throne in the mid-to-late fifteenth century.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Wars of the Roses",
"Cadet branch",
"Europe"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4163,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
71487
|
Canadian Douglas Cardinal, who is considered one of America's most influential contemporary Indigenous architects, is an alumni of both the University of British Columbia and University of Texas at Austin.
|
{
"evidence": [
"Douglas Cardinal_sentence_4"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nCanadian Douglas Cardinal, who is considered one of America's most influential contemporary Indigenous architects, is an alumni of both the University of British Columbia and University of Texas at Austin.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Douglas Cardinal_sentence_4"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4164,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.089",
"value": "?search="
},
{
"operation": "search",
"time": "17.927",
"value": "Douglas Cardinal"
},
{
"operation": "Now on",
"time": "18.97",
"value": "Douglas Cardinal"
},
{
"operation": "Highlighting",
"time": "37.699",
"value": "Douglas Cardinal_sentence_0"
},
{
"operation": "Highlighting",
"time": "60.387",
"value": "Douglas Cardinal_sentence_4"
},
{
"operation": "Highlighting deleted",
"time": "75.607",
"value": "Douglas Cardinal_sentence_0"
},
{
"operation": "Highlighting",
"time": "91.42",
"value": "Douglas Cardinal_header_cell_0_2_0"
},
{
"operation": "Highlighting",
"time": "91.856",
"value": "Douglas Cardinal_cell_0_2_1"
},
{
"operation": "Highlighting",
"time": "91.859",
"value": "Douglas Cardinal_header_cell_0_2_0"
},
{
"operation": "Highlighting",
"time": "91.859",
"value": "Douglas Cardinal_header_cell_0_0_0"
},
{
"operation": "Page search",
"time": "97.771",
"value": "american"
},
{
"operation": "finish",
"time": "155.034",
"value": "finish"
}
]
}
|
84921
|
Marco Anelli's publications include works on architecture and classical music, and in 2010 he carried out Portraits in the Presence of Marina Abramovic (a Serbian conceptual and performance artist, philanthrophist, writer, and filmmaker).
|
{
"evidence": [
"Marco Anelli_sentence_3",
"Marco Anelli_sentence_4",
"Marina Abramović_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:\nMarco Anelli's publications include works on architecture and classical music, and in 2010 he carried out Portraits in the Presence of Marina Abramovic (a Serbian conceptual and performance artist, philanthrophist, writer, and filmmaker).\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Marco Anelli_sentence_3",
"Marco Anelli_sentence_4",
"Marina Abramović_sentence_1"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4165,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.81",
"value": "?search="
},
{
"operation": "search",
"time": "91.31",
"value": "Marco Anelli"
},
{
"operation": "Now on",
"time": "92.024",
"value": "Marco Anelli"
},
{
"operation": "Highlighting",
"time": "103.071",
"value": "Marco Anelli_sentence_3"
},
{
"operation": "Highlighting",
"time": "111.546",
"value": "Marco Anelli_sentence_4"
},
{
"operation": "hyperlink",
"time": "143.355",
"value": "Marina Abramovic"
},
{
"operation": "Now on",
"time": "144.493",
"value": "Marina Abramović"
},
{
"operation": "Highlighting",
"time": "148.438",
"value": "Marina Abramović_sentence_1"
},
{
"operation": "back-button-clicked",
"time": "151.707",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "151.797",
"value": "Marco Anelli"
},
{
"operation": "finish",
"time": "165.677",
"value": "finish"
}
]
}
|
76891
|
The second Island Queen (destroyed in 1948) was finished by the Coney Island Company in Cincinnati on April 18, 1925, and measured 285 feet long and could carry 4,000 people.
|
{
"evidence": [
"Island Queen_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:\nThe second Island Queen (destroyed in 1948) was finished by the Coney Island Company in Cincinnati on April 18, 1925, and measured 285 feet long and could carry 4,000 people.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Island Queen_sentence_3"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4166,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.147",
"value": "?search="
},
{
"operation": "search",
"time": "11.976",
"value": "second Island Queen"
},
{
"operation": "Now on",
"time": "14.837",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "81.072",
"value": "Second Island Queen Island Queen_section_1"
},
{
"operation": "Now on",
"time": "82.506",
"value": "Island Queen#Second Island Queen Island Queen section 1"
},
{
"operation": "Highlighting",
"time": "96.14",
"value": "Island Queen_sentence_23"
},
{
"operation": "Highlighting",
"time": "96.142",
"value": "Island Queen_section_1"
},
{
"operation": "Highlighting",
"time": "152.931",
"value": "Island Queen_sentence_3"
},
{
"operation": "Highlighting deleted",
"time": "154.869",
"value": "Island Queen_sentence_23"
},
{
"operation": "Highlighting deleted",
"time": "154.874",
"value": "Island Queen_section_1"
},
{
"operation": "finish",
"time": "159.752",
"value": "finish"
}
]
}
|
5072
|
American Vladimir Alekseyevich Mikhaylov is a former professional football player and coach from 1976 to 1988, recently managing Moscow-based FC Asmaral Moscow.
|
{
"evidence": [
"Vladimir Alekseyevich Mikhaylov_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:\nAmerican Vladimir Alekseyevich Mikhaylov is a former professional football player and coach from 1976 to 1988, recently managing Moscow-based FC Asmaral Moscow.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Vladimir Alekseyevich Mikhaylov_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4167,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "search",
"time": "9.192",
"value": "Vladimir Alekseyevich Mikhaylov"
},
{
"operation": "Highlighting",
"time": "15.827",
"value": "Vladimir Alekseyevich Mikhaylov_sentence_0"
},
{
"operation": "finish",
"time": "62.544",
"value": "finish"
}
]
}
|
33327
|
Yehudit completed an elementary school in Rehovot, she grew up in urban city and boys listened to her singing.
|
{
"evidence": [
"Yehudit Harari_sentence_15"
],
"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:\nYehudit completed an elementary school in Rehovot, she grew up in urban city and boys listened to her singing.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Yehudit Harari_sentence_15"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4168,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.973",
"value": "?search="
},
{
"operation": "search",
"time": "10.183",
"value": "Yehudit"
},
{
"operation": "Now on",
"time": "11.335",
"value": "Book of Judith"
},
{
"operation": "hyperlink",
"time": "16.992",
"value": "Judith (disambiguation)"
},
{
"operation": "Now on",
"time": "17.901",
"value": "Judith (disambiguation)"
},
{
"operation": "hyperlink",
"time": "24.869",
"value": "8 Music Judith (disambiguation)_section_7"
},
{
"operation": "search",
"time": "50.173",
"value": "Contains...\"completed an elementary school in Rehovot\""
},
{
"operation": "Now on",
"time": "50.856",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "52.703",
"value": "Yehudit Harari"
},
{
"operation": "Now on",
"time": "53.866",
"value": "Yehudit Harari"
},
{
"operation": "Page search",
"time": "60.648",
"value": "completed an elementary school in Rehovot"
},
{
"operation": "Highlighting",
"time": "64.549",
"value": "Yehudit Harari_sentence_14"
},
{
"operation": "Highlighting",
"time": "67.559",
"value": "Yehudit Harari_sentence_15"
},
{
"operation": "Highlighting deleted",
"time": "73.663",
"value": "Yehudit Harari_sentence_14"
},
{
"operation": "Highlighting",
"time": "76.61",
"value": "Yehudit Harari_sentence_17"
},
{
"operation": "Highlighting deleted",
"time": "80.9",
"value": "Yehudit Harari_sentence_17"
},
{
"operation": "finish",
"time": "95.993",
"value": "finish"
}
]
}
|
34933
|
Sheila Minor first worked for the US Fish & Wildlife Service’s Mammal Division in 1970 before getting hired by the Federal Energy Regulatory Commission as a GS-7/9 Research Technician in 1972.
|
{
"evidence": [
"Sheila Minor_sentence_19"
],
"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:\nSheila Minor first worked for the US Fish & Wildlife Service’s Mammal Division in 1970 before getting hired by the Federal Energy Regulatory Commission as a GS-7/9 Research Technician in 1972.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Sheila Minor_sentence_19"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4169,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.055",
"value": "?search="
},
{
"operation": "search",
"time": "17.184",
"value": "Sheila Minor"
},
{
"operation": "Now on",
"time": "18.269",
"value": "Sheila Minor"
},
{
"operation": "Highlighting",
"time": "33.061",
"value": "Sheila Minor_sentence_3"
},
{
"operation": "Highlighting",
"time": "71.346",
"value": "Sheila Minor_sentence_16"
},
{
"operation": "Highlighting",
"time": "89.573",
"value": "Sheila Minor_sentence_19"
},
{
"operation": "Highlighting deleted",
"time": "102.694",
"value": "Sheila Minor_sentence_16"
},
{
"operation": "Highlighting deleted",
"time": "113.111",
"value": "Sheila Minor_sentence_3"
},
{
"operation": "finish",
"time": "134.45",
"value": "finish"
}
]
}
|
76471
|
Whatlington is a village and civil parish in the Rother district of East Sussex and is located seven miles north of Hastings, a seaside town and borough in East Sussex.
|
{
"evidence": [
"Whatlington_sentence_0",
"Whatlington_sentence_1",
"Hastings_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:\nWhatlington is a village and civil parish in the Rother district of East Sussex and is located seven miles north of Hastings, a seaside town and borough in East Sussex.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Whatlington_sentence_0",
"Whatlington_sentence_1",
"Hastings_sentence_2"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4170,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.793",
"value": "?search="
},
{
"operation": "search",
"time": "5.883",
"value": "Whatlington"
},
{
"operation": "Now on",
"time": "6.566",
"value": "Whatlington"
},
{
"operation": "Highlighting",
"time": "9.04",
"value": "Whatlington_sentence_0"
},
{
"operation": "Highlighting",
"time": "12.887",
"value": "Whatlington_sentence_1"
},
{
"operation": "hyperlink",
"time": "18.827",
"value": "Hastings"
},
{
"operation": "Now on",
"time": "19.772",
"value": "Hastings"
},
{
"operation": "Highlighting",
"time": "26.579",
"value": "Hastings_sentence_2"
},
{
"operation": "finish",
"time": "37.007",
"value": "finish"
}
]
}
|
88326
|
Zacco platypus, also known as pale bleak or fresh-water sprat, has a moderately large head with moderately large eyes and has an elongated body that is more compressed at the posterior end.
|
{
"evidence": [
"Zacco platypus_sentence_0",
"Zacco platypus_sentence_4",
"Zacco platypus_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:\nZacco platypus, also known as pale bleak or fresh-water sprat, has a moderately large head with moderately large eyes and has an elongated body that is more compressed at the posterior end.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Zacco platypus_sentence_0",
"Zacco platypus_sentence_4",
"Zacco platypus_sentence_6"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4171,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.324",
"value": "?search="
},
{
"operation": "search",
"time": "32.981",
"value": "Zacco platypus"
},
{
"operation": "Now on",
"time": "33.748",
"value": "Zacco platypus"
},
{
"operation": "Highlighting",
"time": "45.355",
"value": "Zacco platypus_sentence_0"
},
{
"operation": "Highlighting",
"time": "62.602",
"value": "Zacco platypus_sentence_4"
},
{
"operation": "Highlighting",
"time": "81.395",
"value": "Zacco platypus_sentence_6"
},
{
"operation": "finish",
"time": "121.539",
"value": "finish"
}
]
}
|
exfever_6260
|
James Cromwell is an American actor and activist best known for the films including a 1997 American magical realism drama film written and directed by Frank Darabont and based on Stephen King's 1996 novel.
|
{
"evidence": [
"James Cromwell",
"The Green Mile (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:\nJames Cromwell is an American actor and activist best known for the films including a 1997 American magical realism drama film written and directed by Frank Darabont and based on Stephen King's 1996 novel.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"James Cromwell",
"The Green Mile (film)"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4172,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
52175
|
Wataru Ishijima is just a regular pre-schooler with no scientific knowledge.
|
{
"evidence": [
"Wataru Ishijima_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:\nWataru Ishijima is just a regular pre-schooler with no scientific knowledge.\n",
"role": "user"
}
] |
Entity Disambiguation
|
{
"ground_truth": {
"evidence": [
"Wataru Ishijima_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4173,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.013",
"value": "?search="
},
{
"operation": "search",
"time": "24.627",
"value": "Wataru Ishijima"
},
{
"operation": "Now on",
"time": "25.175",
"value": "Wataru Ishijima"
},
{
"operation": "Page search",
"time": "37.082",
"value": "pre"
},
{
"operation": "search",
"time": "72.331",
"value": "Wataru Ishijima"
},
{
"operation": "Now on",
"time": "73.393",
"value": "Wataru Ishijima"
},
{
"operation": "search",
"time": "131.475",
"value": "Ishijima"
},
{
"operation": "Now on",
"time": "132.001",
"value": "Ishijima"
},
{
"operation": "search",
"time": "178.434",
"value": "Wataru"
},
{
"operation": "Now on",
"time": "179.118",
"value": "Wataru"
},
{
"operation": "search",
"time": "210.426",
"value": "pre-schooler scientific"
},
{
"operation": "Now on",
"time": "211.965",
"value": "undefined"
},
{
"operation": "search",
"time": "240.82",
"value": "Wataru Ishijima"
},
{
"operation": "Now on",
"time": "241.586",
"value": "Wataru Ishijima"
},
{
"operation": "Highlighting",
"time": "243.787",
"value": "Wataru Ishijima_sentence_0"
},
{
"operation": "finish",
"time": "254.394",
"value": "finish"
}
]
}
|
exfever_7102
|
Samuel Leroy Jackson is one of the most widely recognized American actors of his generation who starred in the 1992 American action thriller film directed by Phillip Noyce and based on Tom Clancy's 1987 novel of the same name.
|
{
"evidence": [
"Samuel L. Jackson",
"Patriot Games (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:\nSamuel Leroy Jackson is one of the most widely recognized American actors of his generation who starred in the 1992 American action thriller film directed by Phillip Noyce and based on Tom Clancy's 1987 novel of the same name.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Samuel L. Jackson",
"Patriot Games (film)"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4174,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_2475
|
This Sporting Life is Rachel Robert's first movie.
|
{
"evidence": [
"This Sporting Life",
"Richard Harris"
],
"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:\nThis Sporting Life is Rachel Robert's first movie.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"This Sporting Life",
"Richard Harris"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4175,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
7768
|
John Cougar Concentration Camp, formed in January 1993 after a pun on John Cougar Mellencamp, played their first show at the Casbah on January 31, 1994.
|
{
"evidence": [
"Jon Cougar Concentration Camp_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:\nJohn Cougar Concentration Camp, formed in January 1993 after a pun on John Cougar Mellencamp, played their first show at the Casbah on January 31, 1994.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Jon Cougar Concentration Camp_sentence_1"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4176,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.953",
"value": "?search="
},
{
"operation": "search",
"time": "12.365",
"value": "Contains...John Cougar Concentration Camp"
},
{
"operation": "Now on",
"time": "13.402",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "15.406",
"value": "Jon Cougar Concentration Camp"
},
{
"operation": "Now on",
"time": "15.952",
"value": "Jon Cougar Concentration Camp"
},
{
"operation": "Page search",
"time": "30.449",
"value": "form"
},
{
"operation": "Highlighting",
"time": "32.373",
"value": "Jon Cougar Concentration Camp_sentence_1"
},
{
"operation": "finish",
"time": "150.139",
"value": "finish"
}
]
}
|
70610
|
China started a bandy development programme by organising educational days in Ürümqi in June 2009, but they did not come as planned to the 2011 Asian Winter Games.
|
{
"evidence": [
"Ürümqi_sentence_154"
],
"label": "NOT ENOUGH INFO"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nChina started a bandy development programme by organising educational days in Ürümqi in June 2009, but they did not come as planned to the 2011 Asian Winter Games.\n",
"role": "user"
}
] |
Other
|
{
"ground_truth": {
"evidence": [
"Ürümqi_sentence_154"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4177,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.74",
"value": "?search="
},
{
"operation": "search",
"time": "20.126",
"value": "bandy development programme"
},
{
"operation": "Now on",
"time": "22.486",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "26.654",
"value": "Ürümqi"
},
{
"operation": "Now on",
"time": "27.719",
"value": "Ürümqi"
},
{
"operation": "Page search",
"time": "52.026",
"value": "bandy development"
},
{
"operation": "Highlighting",
"time": "63.425",
"value": "Ürümqi_sentence_154"
},
{
"operation": "Page search",
"time": "95.472",
"value": "2011 asian winter"
},
{
"operation": "search",
"time": "117.312",
"value": "2011 Asian Winter Games"
},
{
"operation": "Now on",
"time": "118.422",
"value": "2011 Asian Winter Games"
},
{
"operation": "Page search",
"time": "131",
"value": "china"
},
{
"operation": "Page search",
"time": "157.783",
"value": "did not come as planned to the 2011"
},
{
"operation": "search",
"time": "169.416",
"value": "did not come as planned to the 2011"
},
{
"operation": "Now on",
"time": "173.979",
"value": "undefined"
},
{
"operation": "Now on",
"time": "220.156",
"value": "undefined"
},
{
"operation": "finish",
"time": "229.82",
"value": "finish"
}
]
}
|
exfever_6099
|
Sarrainodu is produced by an Indian film production and distribution company.
|
{
"evidence": [
"Sarrainodu",
"Geetha Arts"
],
"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:\nSarrainodu is produced by an Indian film production and distribution company.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Sarrainodu",
"Geetha Arts"
],
"label": "SUPPORT"
},
"style": "rule"
}
|
{
"index": 4178,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
exfever_7766
|
Austria is also a landlocked country.
|
{
"evidence": [
"Coins of the Swiss franc",
"Switzerland",
"Bern"
],
"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:\nAustria is also a landlocked country.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Coins of the Swiss franc",
"Switzerland",
"Bern"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4179,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
70899
|
The highway intersects with SR 122 Connector (158 miles) before entering Lakeland where it intersects SR 11 Connector in North Pecan Street.
|
{
"evidence": [
"Georgia State Route 122_sentence_0"
],
"label": "REFUTE"
}
|
feverous
|
[
{
"content": "You are a claim-verification assistant. You MUST follow this protocol exactly:\n\n<plan>…</plan>\n- Once at the start: sketch your high-level strategy, such as claim decomposition, entity recognition, etc.\n\n<search>…</search>\n- When you need a fact: emit exactly this tag with your query.\n- To make the most of your search turns, don’t repeat identical queries.\n- You can search at most three times.\n\n<information>\n[[e_1]]: info1\n[[e_2]]: info2\n…\n</information>\n- You will be given claim related information in the format above.\n\n<think>…</think> \n- Use for every piece of reasoning; do not state your final verdict here.\n- You must conduct reasoning inside <think> and </think> first every time you get new information.\n\n<answer>\nLabel: SUPPORT / REFUTE / NOT ENOUGH INFO\nEvidence: [[e_1]], [[e_3]], ...\n</answer> \n- Emit exactly once at the end, no extra text or tags.\n- Evidence id such as e_1 will be replaced by real ids from the corpus. You must include useful real ids when answering\n- Evidence outputs must strictly enforce the format [[e_i]], [[e_j]]…\n- Answer Labels respectively stand for:\nSUPPORT: The claim is consistent with the cited evidence and the evidence is sufficient to confirm the claim.\nREFUTE: The claim contradicts the cited evidence and the evidence is sufficient to disprove the claim.\nNOT ENOUGH INFO: The available evidence is insufficient to determine whether the claim is true or false.\n\n- Note that the process should be: plan → (search → information → think) repeat until conclusion → answer\n\nVerify the claim:\nThe highway intersects with SR 122 Connector (158 miles) before entering Lakeland where it intersects SR 11 Connector in North Pecan Street.\n",
"role": "user"
}
] |
Search terms not in claim
|
{
"ground_truth": {
"evidence": [
"Georgia State Route 122_sentence_0"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4180,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.279",
"value": "?search="
},
{
"operation": "Now on",
"time": "15.406",
"value": "?search="
},
{
"operation": "search",
"time": "57.382",
"value": "highway intersects with SR 122 Connector"
},
{
"operation": "Now on",
"time": "59.896",
"value": "undefined"
},
{
"operation": "search",
"time": "90.478",
"value": "SR 122 Connector"
},
{
"operation": "Now on",
"time": "91.813",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "99.747",
"value": "Connector routes Special routes of U.S. Route 1_section_20"
},
{
"operation": "Now on",
"time": "109.916",
"value": "Special routes of U.S. Route 1#Connector routes Special routes of U.S. Route 1 section 20"
},
{
"operation": "Page search",
"time": "125.545",
"value": "SR 11"
},
{
"operation": "Page search",
"time": "171.33",
"value": "SR 122"
},
{
"operation": "search",
"time": "218.368",
"value": "ntersects SR 11 Connector in North Pecan Street."
},
{
"operation": "Now on",
"time": "219.885",
"value": "undefined"
},
{
"operation": "search",
"time": "228.438",
"value": "North Pecan Street"
},
{
"operation": "Now on",
"time": "231.754",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "241.47",
"value": "Georgia State Route 122"
},
{
"operation": "Now on",
"time": "242.559",
"value": "Georgia State Route 122"
},
{
"operation": "Page search",
"time": "249.538",
"value": "north pecan"
},
{
"operation": "Highlighting",
"time": "261.337",
"value": "Georgia State Route 122_sentence_14"
},
{
"operation": "Highlighting",
"time": "261.34",
"value": "Georgia State Route 122_section_0"
},
{
"operation": "Highlighting",
"time": "265.287",
"value": "Georgia State Route 122_sentence_15"
},
{
"operation": "hyperlink",
"time": "269.744",
"value": "SR 122 Connector"
},
{
"operation": "Now on",
"time": "270.64",
"value": "Georgia State Route 122"
},
{
"operation": "Highlighting",
"time": "297.9",
"value": "Georgia State Route 122_sentence_0"
},
{
"operation": "Highlighting",
"time": "308.005",
"value": "Georgia State Route 122_sentence_0"
},
{
"operation": "finish",
"time": "321.906",
"value": "finish"
}
]
}
|
47004
|
San Diego Padres in the California Sports Hall of Fame include Steve Garvey, an American former professional baseball player born in 1948, Tony Gwynn, Dave WInfield and Fernando Valenzuela.
|
{
"evidence": [
"Steve Garvey_sentence_1",
"Tony Gwynn_sentence_2",
"Tony Gwynn_sentence_458"
],
"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:\nSan Diego Padres in the California Sports Hall of Fame include Steve Garvey, an American former professional baseball player born in 1948, Tony Gwynn, Dave WInfield and Fernando Valenzuela.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Steve Garvey_sentence_1",
"Tony Gwynn_sentence_2",
"Tony Gwynn_sentence_458"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4181,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "1.228",
"value": "?search="
},
{
"operation": "search",
"time": "17.538",
"value": "San Diego Padres in the California Sports Hall of Fame"
},
{
"operation": "Now on",
"time": "19.856",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "75.274",
"value": "San Diego Hall of Champions San Diego Padres_section_16"
},
{
"operation": "Now on",
"time": "76.205",
"value": "San Diego Padres#San Diego Hall of Champions San Diego Padres section 16"
},
{
"operation": "Highlighting",
"time": "89.226",
"value": "San Diego Padres_cell_4_0_0"
},
{
"operation": "Highlighting",
"time": "89.227",
"value": "San Diego Padres_title"
},
{
"operation": "Highlighting",
"time": "89.228",
"value": "San Diego Padres_section_9"
},
{
"operation": "Highlighting",
"time": "89.228",
"value": "San Diego Padres_section_15"
},
{
"operation": "Highlighting deleted",
"time": "93.321",
"value": "San Diego Padres_cell_4_0_0"
},
{
"operation": "Highlighting deleted",
"time": "93.322",
"value": "San Diego Padres_title"
},
{
"operation": "Highlighting deleted",
"time": "93.324",
"value": "San Diego Padres_section_9"
},
{
"operation": "Highlighting deleted",
"time": "93.325",
"value": "San Diego Padres_section_15"
},
{
"operation": "search",
"time": "108.528",
"value": "California Sports Hall of Fame"
},
{
"operation": "Now on",
"time": "110.381",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "120.897",
"value": "Ben Lyons"
},
{
"operation": "Now on",
"time": "121.65",
"value": "Ben Lyons"
},
{
"operation": "back-button-clicked",
"time": "132.986",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "133.685",
"value": "undefined"
},
{
"operation": "hyperlink",
"time": "139.96",
"value": "Christian Okoye"
},
{
"operation": "Now on",
"time": "140.699",
"value": "Christian Okoye"
},
{
"operation": "back-button-clicked",
"time": "162.217",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "162.441",
"value": "back-button-clicked"
},
{
"operation": "back-button-clicked",
"time": "162.443",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "162.578",
"value": "San Diego Padres#San Diego Hall of Champions San Diego Padres section 16"
},
{
"operation": "hyperlink",
"time": "217.176",
"value": "Baseball Hall of Fame"
},
{
"operation": "Now on",
"time": "218.017",
"value": "National Baseball Hall of Fame and Museum"
},
{
"operation": "back-button-clicked",
"time": "219.913",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "220.044",
"value": "San Diego Padres#San Diego Hall of Champions San Diego Padres section 16"
},
{
"operation": "Page search",
"time": "243.668",
"value": "California Sports Hall of Fame"
},
{
"operation": "Page search",
"time": "260.17",
"value": "steve garvey"
},
{
"operation": "search",
"time": "295.703",
"value": "Steve Garvey"
},
{
"operation": "Now on",
"time": "296.665",
"value": "Steve Garvey"
},
{
"operation": "Highlighting",
"time": "303.961",
"value": "Steve Garvey_sentence_1"
},
{
"operation": "Page search",
"time": "332.552",
"value": "california"
},
{
"operation": "search",
"time": "402.175",
"value": "Tony Gwynn"
},
{
"operation": "Now on",
"time": "406.161",
"value": "Tony Gwynn"
},
{
"operation": "Highlighting",
"time": "420.952",
"value": "Tony Gwynn_sentence_2"
},
{
"operation": "Page search",
"time": "431.733",
"value": "california"
},
{
"operation": "Highlighting",
"time": "472.713",
"value": "Tony Gwynn_sentence_458"
},
{
"operation": "search",
"time": "497.239",
"value": "Dave WInfield"
},
{
"operation": "Now on",
"time": "498.414",
"value": "Dave Winfield"
},
{
"operation": "Page search",
"time": "506.544",
"value": "californai"
},
{
"operation": "Page search",
"time": "510.152",
"value": "california"
},
{
"operation": "hyperlink",
"time": "521.24",
"value": "2.6 Honors and awards Dave Winfield_section_7"
},
{
"operation": "finish",
"time": "541.487",
"value": "finish"
}
]
}
|
exfever_3939
|
Breaking Bad is an American neo-Western crime drama television series created and produced by Vince Gilligan, starring Bryan Cranston as Walter White, an underpaid, overqualified, and dispirited high-school coach who teaches about the scientific study of the properties and behavior of matter.
|
{
"evidence": [
"Breaking Bad",
"Chemistry"
],
"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:\nBreaking Bad is an American neo-Western crime drama television series created and produced by Vince Gilligan, starring Bryan Cranston as Walter White, an underpaid, overqualified, and dispirited high-school coach who teaches about the scientific study of the properties and behavior of matter.\n",
"role": "user"
}
] |
EX-FEVER
|
{
"ground_truth": {
"evidence": [
"Breaking Bad",
"Chemistry"
],
"label": "REFUTE"
},
"style": "rule"
}
|
{
"index": 4182,
"split": "train_online"
}
|
{
"annotator_operations": []
}
|
66291
|
Aminé released his songs entitled "Warm on a Cold Night" (Remix), "Redmercedes (Remix)", "Blinds", and "Blackjack (Remix)" in 2017.
|
{
"evidence": [
"Good for You (album)_sentence_0",
"Good for You (album)_sentence_3",
"Good for You (album)_sentence_1",
"Aminé (rapper)_sentence_19"
],
"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:\nAminé released his songs entitled \"Warm on a Cold Night\" (Remix), \"Redmercedes (Remix)\", \"Blinds\", and \"Blackjack (Remix)\" in 2017.\n",
"role": "user"
}
] |
Multi-hop Reasoning
|
{
"ground_truth": {
"evidence": [
"Good for You (album)_sentence_0",
"Good for You (album)_sentence_3",
"Good for You (album)_sentence_1",
"Aminé (rapper)_sentence_19"
],
"label": "NOT ENOUGH INFO"
},
"style": "rule"
}
|
{
"index": 4183,
"split": "train_online"
}
|
{
"annotator_operations": [
{
"operation": "start",
"time": "0",
"value": "start"
},
{
"operation": "Now on",
"time": "0.878",
"value": "?search="
},
{
"operation": "search",
"time": "18.83",
"value": "Aminé"
},
{
"operation": "Now on",
"time": "26.448",
"value": "Aminé"
},
{
"operation": "hyperlink",
"time": "82.174",
"value": "Good for You (album)"
},
{
"operation": "Now on",
"time": "82.926",
"value": "Good for You (album)"
},
{
"operation": "Highlighting",
"time": "86.55",
"value": "Good for You (album)_sentence_0"
},
{
"operation": "hyperlink",
"time": "130.294",
"value": "2 Singles Good for You (album)_section_1"
},
{
"operation": "Highlighting",
"time": "150.862",
"value": "Good for You (album)_sentence_3"
},
{
"operation": "Highlighting",
"time": "164.821",
"value": "Good for You (album)_sentence_1"
},
{
"operation": "back-button-clicked",
"time": "172.478",
"value": "back-button-clicked"
},
{
"operation": "Now on",
"time": "173.116",
"value": "Aminé (rapper)"
},
{
"operation": "Highlighting",
"time": "185.165",
"value": "Aminé (rapper)_sentence_19"
},
{
"operation": "finish",
"time": "239.741",
"value": "finish"
}
]
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.