[
{
"id": "confirm_csv_1",
"prompt": "Output one CSV row, no header or quotes: user=Cora, age=31, city=Osaka.",
"kind": "exact",
"expected": "Cora,31,Osaka",
"mode": "instruct",
"group": "confirmation",
"tests": null,
"output": "Cora,31,Osaka",
"pass": true
},
{
"id": "confirm_csv_2",
"prompt": "Return only a CSV value row: name=Teo; years=52; place=Riga. Do not include keys or quotes.",
"kind": "exact",
"expected": "Teo,52,Riga",
"mode": "instruct",
"group": "confirmation",
"tests": null,
"output": "Teo,52,Riga",
"pass": true
},
{
"id": "confirm_csv_3",
"prompt": "Output only CSV values in this order: city=Tartu, person=Sara, age=41. No header or quotes.",
"kind": "exact",
"expected": "Tartu,Sara,41",
"mode": "instruct",
"group": "confirmation",
"tests": null,
"output": "Tartu,Sara,41",
"pass": true
},
{
"id": "confirm_csv_4",
"prompt": "Output a CSV data row for user=Yara, age=36, country=Kenya. No keys, header or quotes.",
"kind": "exact",
"expected": "Yara,36,Kenya",
"mode": "instruct",
"group": "confirmation",
"tests": null,
"output": "Yara,36,Kenya",
"pass": true
},
{
"id": "confirm_csv_5",
"prompt": "Convert product=Aster; units=9; color=Indigo into one CSV value row. No header or quotation marks.",
"kind": "exact",
"expected": "Aster,9,Indigo",
"mode": "instruct",
"group": "confirmation",
"tests": null,
"output": "Aster,9,Indigo",
"pass": true
},
{
"id": "confirm_csv_6",
"prompt": "Return only a CSV value row for name=Zoe, identifier=Q_42, town=Graz.",
"kind": "exact",
"expected": "Zoe,Q_42,Graz",
"mode": "instruct",
"group": "confirmation",
"tests": null,
"output": "Zoe,Q_42,Graz",
"pass": true
},
{
"id": "confirm_copy_1",
"prompt": "Write epsilon and psi, each on its own line. Preserve their English spellings, with no other text.",
"kind": "exact",
"expected": "epsilon\npsi",
"mode": "instruct",
"group": "confirmation",
"tests": null,
"output": "epsilon\npsi",
"pass": true
},
{
"id": "confirm_copy_2",
"prompt": "Reply with exactly: A_B-47",
"kind": "exact",
"expected": "A_B-47",
"mode": "instruct",
"group": "confirmation",
"tests": null,
"output": "A_B-47",
"pass": true
},
{
"id": "confirm_copy_3",
"prompt": "Copy na\u00efve and jalape\u00f1o, each on its own line. No bullets or other text.",
"kind": "exact",
"expected": "na\u00efve\njalape\u00f1o",
"mode": "instruct",
"group": "confirmation",
"tests": null,
"output": "na\u00efve\njalape\u00f1o",
"pass": true
},
{
"id": "confirm_code_pack_adjacent",
"prompt": "Write only Python code for pack_adjacent(text), returning consecutive (character, count) tuples as a list.",
"kind": "code",
"expected": null,
"mode": "instruct",
"group": "confirmation",
"tests": "assert pack_adjacent('aabbba')==[('a',2),('b',3),('a',1)]\nassert pack_adjacent('')==[]\nassert pack_adjacent('x')==[('x',1)]",
"output": "```python\nfrom itertools import groupby\n\ndef pack_adjacent(text):\n return [(char, len(list(run))) for char, run in groupby(text)]\n```",
"pass": true
},
{
"id": "confirm_code_compress_chars",
"prompt": "Write only Python code for compress_chars(text), returning consecutive (character, count) tuples as a list.",
"kind": "code",
"expected": null,
"mode": "instruct",
"group": "confirmation",
"tests": "assert compress_chars('aabbba')==[('a',2),('b',3),('a',1)]\nassert compress_chars('')==[]\nassert compress_chars('x')==[('x',1)]",
"output": "```python\ndef compress_chars(text):\n result = []\n for char in text:\n if result and result[-1][0] == char:\n previous, count = result[-1]\n result[-1] = (previous, count + 1)\n else:\n result.append((char, 1))\n return result\n```",
"pass": true
},
{
"id": "confirm_math_1",
"prompt": "Leah had 210 credits, spent one seventh of them, then received 26 credits. What is her balance? Explain briefly.",
"kind": "number",
"expected": 206,
"mode": "thinking",
"group": "confirmation",
"tests": null,
"output": "The amount spent is 210/7 = 30. Subtract it from the original amount: 210 - 30 = 180. Add the new money: 180 + 26 = 206.\nAnswer: 206",
"pass": true
},
{
"id": "confirm_math_2",
"prompt": "Malik had 96 tokens, spent one third, then received 11 tokens. How many tokens does he have now? Explain briefly.",
"kind": "number",
"expected": 75,
"mode": "thinking",
"group": "confirmation",
"tests": null,
"output": "The amount spent is 96/3 = 32. Subtract it from the original amount: 96 - 32 = 64. Add the new tokens: 64 + 11 = 75.\nAnswer: 75",
"pass": true
},
{
"id": "confirm_math_3",
"prompt": "A fund starts with 231 pounds, spends one seventh, and later receives 19 pounds. What is the new balance? Explain briefly.",
"kind": "number",
"expected": 217,
"mode": "thinking",
"group": "confirmation",
"tests": null,
"output": "The amount spent is 231/7 = 33. Subtract it from the original amount: 231 - 33 = 198. Add the new money: 198 + 19 = 217.\nAnswer: 217",
"pass": true
},
{
"id": "confirm_time_1",
"prompt": "A bus leaves at 10:48 and arrives at 13:07 on the same day. What is the elapsed journey time in minutes?",
"kind": "number",
"expected": 139,
"mode": "thinking",
"group": "confirmation",
"tests": null,
"output": "Convert the times to minutes after midnight: 10*60+48 = 648 and 13*60+7 = 787.\nThe elapsed time is 787 - 648 = 139 minutes.\nAnswer: 139",
"pass": true
},
{
"id": "confirm_time_2",
"prompt": "How many minutes are in two hours and seventeen minutes? Explain briefly.",
"kind": "number",
"expected": 137,
"mode": "thinking",
"group": "confirmation",
"tests": null,
"output": "An hour has 60 minutes. 2*60+17 = 137 minutes.\nAnswer: 137.",
"pass": true
}
]