prompt listlengths 2 2 | label dict | metadata dict |
|---|---|---|
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sinx-\\frac{2}{3}\\sin^{3}x+\\frac{1}{5}\\sin^{5}x+C",
"budget": 634
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006392",
"normalized_example_id": "ex_006392",
"source_idx": 6392,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1056,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sinx-\\frac{2}{3}\\sin^{3}x+\\frac{1}{5}\\sin^{5}x+C",
"budget": 845
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006392",
"normalized_example_id": "ex_006392",
"source_idx": 6392,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1056,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sinx-\\frac{2}{3}\\sin^{3}x+\\frac{1}{5}\\sin^{5}x+C",
"budget": 1056
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006392",
"normalized_example_id": "ex_006392",
"source_idx": 6392,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1056,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6125;6375;4625;4875;5216;5736;5264;5784",
"budget": 5953
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006395",
"normalized_example_id": "ex_006395",
"source_idx": 6395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9922,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6125;6375;4625;4875;5216;5736;5264;5784",
"budget": 7938
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006395",
"normalized_example_id": "ex_006395",
"source_idx": 6395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9922,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6125;6375;4625;4875;5216;5736;5264;5784",
"budget": 9922
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006395",
"normalized_example_id": "ex_006395",
"source_idx": 6395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9922,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1/3,1/3,1/3),(0,0,1),(0,1,0),(2/3,-1/3,2/3),(1,0,0),(-1,1,1)",
"budget": 3838
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006397",
"normalized_example_id": "ex_006397",
"source_idx": 6397,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6397,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1/3,1/3,1/3),(0,0,1),(0,1,0),(2/3,-1/3,2/3),(1,0,0),(-1,1,1)",
"budget": 5118
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006397",
"normalized_example_id": "ex_006397",
"source_idx": 6397,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6397,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1/3,1/3,1/3),(0,0,1),(0,1,0),(2/3,-1/3,2/3),(1,0,0),(-1,1,1)",
"budget": 6397
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006397",
"normalized_example_id": "ex_006397",
"source_idx": 6397,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6397,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3^{n}-3\\times2^{n}+3",
"budget": 1672
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006398",
"normalized_example_id": "ex_006398",
"source_idx": 6398,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2786,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3^{n}-3\\times2^{n}+3",
"budget": 2229
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006398",
"normalized_example_id": "ex_006398",
"source_idx": 6398,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2786,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3^{n}-3\\times2^{n}+3",
"budget": 2786
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006398",
"normalized_example_id": "ex_006398",
"source_idx": 6398,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2786,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{5}{6}(\\sqrt[5]{\\frac{1+\\sqrt[3]{x^{2}}}{\\sqrt[3]{x^{2}}}})^{9}+C",
"budget": 4844
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006402",
"normalized_example_id": "ex_006402",
"source_idx": 6402,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8073,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{5}{6}(\\sqrt[5]{\\frac{1+\\sqrt[3]{x^{2}}}{\\sqrt[3]{x^{2}}}})^{9}+C",
"budget": 6458
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006402",
"normalized_example_id": "ex_006402",
"source_idx": 6402,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8073,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{5}{6}(\\sqrt[5]{\\frac{1+\\sqrt[3]{x^{2}}}{\\sqrt[3]{x^{2}}}})^{9}+C",
"budget": 8073
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006402",
"normalized_example_id": "ex_006402",
"source_idx": 6402,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8073,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{\\frac{4S^{2}}{b^{2}\\sin^{2}\\alpha}+b^{2}-4S\\cot\\alpha}",
"budget": 5219
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006404",
"normalized_example_id": "ex_006404",
"source_idx": 6404,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8698,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{\\frac{4S^{2}}{b^{2}\\sin^{2}\\alpha}+b^{2}-4S\\cot\\alpha}",
"budget": 6958
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006404",
"normalized_example_id": "ex_006404",
"source_idx": 6404,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8698,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{\\frac{4S^{2}}{b^{2}\\sin^{2}\\alpha}+b^{2}-4S\\cot\\alpha}",
"budget": 8698
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006404",
"normalized_example_id": "ex_006404",
"source_idx": 6404,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8698,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "44",
"budget": 1424
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006405",
"normalized_example_id": "ex_006405",
"source_idx": 6405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2373,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "44",
"budget": 1898
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006405",
"normalized_example_id": "ex_006405",
"source_idx": 6405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2373,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "44",
"budget": 2373
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006405",
"normalized_example_id": "ex_006405",
"source_idx": 6405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2373,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3\\pi}{2}",
"budget": 3965
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006407",
"normalized_example_id": "ex_006407",
"source_idx": 6407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6608,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3\\pi}{2}",
"budget": 5286
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006407",
"normalized_example_id": "ex_006407",
"source_idx": 6407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6608,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3\\pi}{2}",
"budget": 6608
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006407",
"normalized_example_id": "ex_006407",
"source_idx": 6407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6608,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2592",
"budget": 4366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006410",
"normalized_example_id": "ex_006410",
"source_idx": 6410,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7276,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2592",
"budget": 5821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006410",
"normalized_example_id": "ex_006410",
"source_idx": 6410,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7276,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2592",
"budget": 7276
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006410",
"normalized_example_id": "ex_006410",
"source_idx": 6410,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7276,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A=20,B=30,C=23,D=19",
"budget": 641
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006411",
"normalized_example_id": "ex_006411",
"source_idx": 6411,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1069,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A=20,B=30,C=23,D=19",
"budget": 855
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006411",
"normalized_example_id": "ex_006411",
"source_idx": 6411,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1069,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A=20,B=30,C=23,D=19",
"budget": 1069
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006411",
"normalized_example_id": "ex_006411",
"source_idx": 6411,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1069,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{16\\sqrt{6}}{7}",
"budget": 3812
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006412",
"normalized_example_id": "ex_006412",
"source_idx": 6412,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6354,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{16\\sqrt{6}}{7}",
"budget": 5083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006412",
"normalized_example_id": "ex_006412",
"source_idx": 6412,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6354,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{16\\sqrt{6}}{7}",
"budget": 6354
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006412",
"normalized_example_id": "ex_006412",
"source_idx": 6412,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6354,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "150",
"budget": 3013
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006413",
"normalized_example_id": "ex_006413",
"source_idx": 6413,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "150",
"budget": 4018
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006413",
"normalized_example_id": "ex_006413",
"source_idx": 6413,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "150",
"budget": 5022
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006413",
"normalized_example_id": "ex_006413",
"source_idx": 6413,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 3523
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006414",
"normalized_example_id": "ex_006414",
"source_idx": 6414,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5872,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 4698
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006414",
"normalized_example_id": "ex_006414",
"source_idx": 6414,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5872,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 5872
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006414",
"normalized_example_id": "ex_006414",
"source_idx": 6414,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5872,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 1126
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006417",
"normalized_example_id": "ex_006417",
"source_idx": 6417,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1876,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 1501
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006417",
"normalized_example_id": "ex_006417",
"source_idx": 6417,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1876,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 1876
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006417",
"normalized_example_id": "ex_006417",
"source_idx": 6417,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1876,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50^{\\circ}",
"budget": 2527
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006419",
"normalized_example_id": "ex_006419",
"source_idx": 6419,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4212,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50^{\\circ}",
"budget": 3370
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006419",
"normalized_example_id": "ex_006419",
"source_idx": 6419,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4212,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50^{\\circ}",
"budget": 4212
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006419",
"normalized_example_id": "ex_006419",
"source_idx": 6419,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4212,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 1588
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006420",
"normalized_example_id": "ex_006420",
"source_idx": 6420,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2647,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 2118
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006420",
"normalized_example_id": "ex_006420",
"source_idx": 6420,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2647,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 2647
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006420",
"normalized_example_id": "ex_006420",
"source_idx": 6420,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2647,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 1688
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006421",
"normalized_example_id": "ex_006421",
"source_idx": 6421,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2813,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 2250
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006421",
"normalized_example_id": "ex_006421",
"source_idx": 6421,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2813,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 2813
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006421",
"normalized_example_id": "ex_006421",
"source_idx": 6421,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2813,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 4131
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006422",
"normalized_example_id": "ex_006422",
"source_idx": 6422,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6885,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 5508
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006422",
"normalized_example_id": "ex_006422",
"source_idx": 6422,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6885,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 6885
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006422",
"normalized_example_id": "ex_006422",
"source_idx": 6422,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6885,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7\\sqrt{6}",
"budget": 2030
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006424",
"normalized_example_id": "ex_006424",
"source_idx": 6424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3383,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7\\sqrt{6}",
"budget": 2706
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006424",
"normalized_example_id": "ex_006424",
"source_idx": 6424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3383,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7\\sqrt{6}",
"budget": 3383
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006424",
"normalized_example_id": "ex_006424",
"source_idx": 6424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3383,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "63",
"budget": 2020
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006429",
"normalized_example_id": "ex_006429",
"source_idx": 6429,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3366,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "63",
"budget": 2693
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006429",
"normalized_example_id": "ex_006429",
"source_idx": 6429,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3366,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "63",
"budget": 3366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006429",
"normalized_example_id": "ex_006429",
"source_idx": 6429,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3366,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9}{2}",
"budget": 1688
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006430",
"normalized_example_id": "ex_006430",
"source_idx": 6430,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2813,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9}{2}",
"budget": 2250
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006430",
"normalized_example_id": "ex_006430",
"source_idx": 6430,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2813,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9}{2}",
"budget": 2813
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006430",
"normalized_example_id": "ex_006430",
"source_idx": 6430,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2813,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "280",
"budget": 1211
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006431",
"normalized_example_id": "ex_006431",
"source_idx": 6431,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2019,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "280",
"budget": 1615
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006431",
"normalized_example_id": "ex_006431",
"source_idx": 6431,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2019,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "280",
"budget": 2019
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006431",
"normalized_example_id": "ex_006431",
"source_idx": 6431,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2019,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 6007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006438",
"normalized_example_id": "ex_006438",
"source_idx": 6438,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10011,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 8009
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006438",
"normalized_example_id": "ex_006438",
"source_idx": 6438,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10011,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 10011
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006438",
"normalized_example_id": "ex_006438",
"source_idx": 6438,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10011,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-2",
"budget": 1225
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006439",
"normalized_example_id": "ex_006439",
"source_idx": 6439,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2041,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-2",
"budget": 1633
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006439",
"normalized_example_id": "ex_006439",
"source_idx": 6439,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2041,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-2",
"budget": 2041
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006439",
"normalized_example_id": "ex_006439",
"source_idx": 6439,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2041,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "61",
"budget": 2084
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006445",
"normalized_example_id": "ex_006445",
"source_idx": 6445,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3473,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "61",
"budget": 2778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006445",
"normalized_example_id": "ex_006445",
"source_idx": 6445,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3473,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "61",
"budget": 3473
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006445",
"normalized_example_id": "ex_006445",
"source_idx": 6445,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3473,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "846",
"budget": 1031
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006446",
"normalized_example_id": "ex_006446",
"source_idx": 6446,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1718,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "846",
"budget": 1374
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006446",
"normalized_example_id": "ex_006446",
"source_idx": 6446,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1718,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "846",
"budget": 1718
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006446",
"normalized_example_id": "ex_006446",
"source_idx": 6446,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1718,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 5871
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006449",
"normalized_example_id": "ex_006449",
"source_idx": 6449,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 7828
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006449",
"normalized_example_id": "ex_006449",
"source_idx": 6449,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 9785
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006449",
"normalized_example_id": "ex_006449",
"source_idx": 6449,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{S\\sqrt{S}}{3}",
"budget": 3692
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006450",
"normalized_example_id": "ex_006450",
"source_idx": 6450,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6153,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{S\\sqrt{S}}{3}",
"budget": 4922
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006450",
"normalized_example_id": "ex_006450",
"source_idx": 6450,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6153,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{S\\sqrt{S}}{3}",
"budget": 6153
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006450",
"normalized_example_id": "ex_006450",
"source_idx": 6450,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6153,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1+\\sqrt{2}",
"budget": 1202
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006451",
"normalized_example_id": "ex_006451",
"source_idx": 6451,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1+\\sqrt{2}",
"budget": 1602
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006451",
"normalized_example_id": "ex_006451",
"source_idx": 6451,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1+\\sqrt{2}",
"budget": 2003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006451",
"normalized_example_id": "ex_006451",
"source_idx": 6451,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{3}",
"budget": 2272
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006452",
"normalized_example_id": "ex_006452",
"source_idx": 6452,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3787,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{3}",
"budget": 3030
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006452",
"normalized_example_id": "ex_006452",
"source_idx": 6452,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3787,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{3}",
"budget": 3787
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006452",
"normalized_example_id": "ex_006452",
"source_idx": 6452,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3787,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "226",
"budget": 1897
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006453",
"normalized_example_id": "ex_006453",
"source_idx": 6453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3161,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "226",
"budget": 2529
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006453",
"normalized_example_id": "ex_006453",
"source_idx": 6453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3161,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "226",
"budget": 3161
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006453",
"normalized_example_id": "ex_006453",
"source_idx": 6453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3161,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{3}+\\frac{\\ln2}{36}",
"budget": 2216
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006455",
"normalized_example_id": "ex_006455",
"source_idx": 6455,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3693,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{3}+\\frac{\\ln2}{36}",
"budget": 2954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006455",
"normalized_example_id": "ex_006455",
"source_idx": 6455,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3693,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{3}+\\frac{\\ln2}{36}",
"budget": 3693
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006455",
"normalized_example_id": "ex_006455",
"source_idx": 6455,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3693,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 919
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006456",
"normalized_example_id": "ex_006456",
"source_idx": 6456,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1531,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 1225
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006456",
"normalized_example_id": "ex_006456",
"source_idx": 6456,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1531,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 1531
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006456",
"normalized_example_id": "ex_006456",
"source_idx": 6456,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1531,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3,5,13",
"budget": 2590
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006457",
"normalized_example_id": "ex_006457",
"source_idx": 6457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4316,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.