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": "D",
"budget": 6907
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006910",
"normalized_example_id": "ex_006910",
"source_idx": 6910,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6907,
... |
[
{
"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": "x \\in\\{\\pi / 2+m \\pi, \\pi / 4+m \\pi / 2, \\pi / 6+m \\pi / 3 \\mid m \\in \\mathbb{Z}\\}",
"budget": 2133
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006911",
"normalized_example_id": "ex_006911",
"source_idx": 6911,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3555,
... |
[
{
"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": "x \\in\\{\\pi / 2+m \\pi, \\pi / 4+m \\pi / 2, \\pi / 6+m \\pi / 3 \\mid m \\in \\mathbb{Z}\\}",
"budget": 2844
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006911",
"normalized_example_id": "ex_006911",
"source_idx": 6911,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3555,
... |
[
{
"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": "x \\in\\{\\pi / 2+m \\pi, \\pi / 4+m \\pi / 2, \\pi / 6+m \\pi / 3 \\mid m \\in \\mathbb{Z}\\}",
"budget": 3555
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006911",
"normalized_example_id": "ex_006911",
"source_idx": 6911,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3555,
... |
[
{
"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": "f(x) = -\\frac{5}{2}",
"budget": 3902
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006913",
"normalized_example_id": "ex_006913",
"source_idx": 6913,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6504,
... |
[
{
"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": "f(x) = -\\frac{5}{2}",
"budget": 5203
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006913",
"normalized_example_id": "ex_006913",
"source_idx": 6913,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6504,
... |
[
{
"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": "f(x) = -\\frac{5}{2}",
"budget": 6504
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006913",
"normalized_example_id": "ex_006913",
"source_idx": 6913,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6504,
... |
[
{
"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": "504",
"budget": 2323
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006914",
"normalized_example_id": "ex_006914",
"source_idx": 6914,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3872,
... |
[
{
"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": "504",
"budget": 3098
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006914",
"normalized_example_id": "ex_006914",
"source_idx": 6914,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3872,
... |
[
{
"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": "504",
"budget": 3872
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006914",
"normalized_example_id": "ex_006914",
"source_idx": 6914,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3872,
... |
[
{
"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": "10.5",
"budget": 3725
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006917",
"normalized_example_id": "ex_006917",
"source_idx": 6917,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6208,
... |
[
{
"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": "10.5",
"budget": 4966
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006917",
"normalized_example_id": "ex_006917",
"source_idx": 6917,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6208,
... |
[
{
"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": "10.5",
"budget": 6208
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006917",
"normalized_example_id": "ex_006917",
"source_idx": 6917,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6208,
... |
[
{
"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": "637",
"budget": 2056
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006923",
"normalized_example_id": "ex_006923",
"source_idx": 6923,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3426,
... |
[
{
"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": "637",
"budget": 2741
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006923",
"normalized_example_id": "ex_006923",
"source_idx": 6923,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3426,
... |
[
{
"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": "637",
"budget": 3426
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006923",
"normalized_example_id": "ex_006923",
"source_idx": 6923,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3426,
... |
[
{
"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": "27",
"budget": 1879
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006928",
"normalized_example_id": "ex_006928",
"source_idx": 6928,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3131,
... |
[
{
"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": "27",
"budget": 2505
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006928",
"normalized_example_id": "ex_006928",
"source_idx": 6928,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3131,
... |
[
{
"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": "27",
"budget": 3131
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006928",
"normalized_example_id": "ex_006928",
"source_idx": 6928,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3131,
... |
[
{
"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": "2.5",
"budget": 3875
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006929",
"normalized_example_id": "ex_006929",
"source_idx": 6929,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6458,
... |
[
{
"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": "2.5",
"budget": 5166
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006929",
"normalized_example_id": "ex_006929",
"source_idx": 6929,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6458,
... |
[
{
"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": "2.5",
"budget": 6458
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006929",
"normalized_example_id": "ex_006929",
"source_idx": 6929,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6458,
... |
[
{
"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": "16",
"budget": 722
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006932",
"normalized_example_id": "ex_006932",
"source_idx": 6932,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1204,
... |
[
{
"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": "16",
"budget": 963
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006932",
"normalized_example_id": "ex_006932",
"source_idx": 6932,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1204,
... |
[
{
"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": "16",
"budget": 1204
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006932",
"normalized_example_id": "ex_006932",
"source_idx": 6932,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1204,
... |
[
{
"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}{2}",
"budget": 4329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006933",
"normalized_example_id": "ex_006933",
"source_idx": 6933,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7215,
... |
[
{
"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}{2}",
"budget": 5772
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006933",
"normalized_example_id": "ex_006933",
"source_idx": 6933,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7215,
... |
[
{
"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}{2}",
"budget": 7215
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006933",
"normalized_example_id": "ex_006933",
"source_idx": 6933,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7215,
... |
[
{
"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{7}{8}",
"budget": 2726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006934",
"normalized_example_id": "ex_006934",
"source_idx": 6934,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4543,
... |
[
{
"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{7}{8}",
"budget": 3634
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006934",
"normalized_example_id": "ex_006934",
"source_idx": 6934,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4543,
... |
[
{
"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{7}{8}",
"budget": 4543
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006934",
"normalized_example_id": "ex_006934",
"source_idx": 6934,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4543,
... |
[
{
"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": "x - \\frac{1}{4} \\sin 2x - \\frac{1}{8} \\sin 4x + \\frac{4}{3} \\sin^3 x + C",
"budget": 3616
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006935",
"normalized_example_id": "ex_006935",
"source_idx": 6935,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6027,
... |
[
{
"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": "x - \\frac{1}{4} \\sin 2x - \\frac{1}{8} \\sin 4x + \\frac{4}{3} \\sin^3 x + C",
"budget": 4822
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006935",
"normalized_example_id": "ex_006935",
"source_idx": 6935,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6027,
... |
[
{
"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": "x - \\frac{1}{4} \\sin 2x - \\frac{1}{8} \\sin 4x + \\frac{4}{3} \\sin^3 x + C",
"budget": 6027
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006935",
"normalized_example_id": "ex_006935",
"source_idx": 6935,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6027,
... |
[
{
"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": "-2006",
"budget": 5743
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006936",
"normalized_example_id": "ex_006936",
"source_idx": 6936,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9571,
... |
[
{
"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": "-2006",
"budget": 7657
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006936",
"normalized_example_id": "ex_006936",
"source_idx": 6936,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9571,
... |
[
{
"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": "-2006",
"budget": 9571
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006936",
"normalized_example_id": "ex_006936",
"source_idx": 6936,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9571,
... |
[
{
"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{1}{2}",
"budget": 2635
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006937",
"normalized_example_id": "ex_006937",
"source_idx": 6937,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4392,
... |
[
{
"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{1}{2}",
"budget": 3514
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006937",
"normalized_example_id": "ex_006937",
"source_idx": 6937,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4392,
... |
[
{
"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{1}{2}",
"budget": 4392
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006937",
"normalized_example_id": "ex_006937",
"source_idx": 6937,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4392,
... |
[
{
"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": "192",
"budget": 2687
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006938",
"normalized_example_id": "ex_006938",
"source_idx": 6938,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4479,
... |
[
{
"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": "192",
"budget": 3583
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006938",
"normalized_example_id": "ex_006938",
"source_idx": 6938,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4479,
... |
[
{
"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": "192",
"budget": 4479
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006938",
"normalized_example_id": "ex_006938",
"source_idx": 6938,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4479,
... |
[
{
"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": "5",
"budget": 5836
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006941",
"normalized_example_id": "ex_006941",
"source_idx": 6941,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9727,
... |
[
{
"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": "5",
"budget": 7782
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006941",
"normalized_example_id": "ex_006941",
"source_idx": 6941,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9727,
... |
[
{
"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": "5",
"budget": 9727
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006941",
"normalized_example_id": "ex_006941",
"source_idx": 6941,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9727,
... |
[
{
"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": "175",
"budget": 865
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006942",
"normalized_example_id": "ex_006942",
"source_idx": 6942,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1441,
... |
[
{
"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": "175",
"budget": 1153
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006942",
"normalized_example_id": "ex_006942",
"source_idx": 6942,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1441,
... |
[
{
"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": "175",
"budget": 1441
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006942",
"normalized_example_id": "ex_006942",
"source_idx": 6942,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1441,
... |
[
{
"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": "2030112.5",
"budget": 3316
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006945",
"normalized_example_id": "ex_006945",
"source_idx": 6945,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5526,
... |
[
{
"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": "2030112.5",
"budget": 4421
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006945",
"normalized_example_id": "ex_006945",
"source_idx": 6945,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5526,
... |
[
{
"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": "2030112.5",
"budget": 5526
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006945",
"normalized_example_id": "ex_006945",
"source_idx": 6945,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5526,
... |
[
{
"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",
"budget": 2199
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006950",
"normalized_example_id": "ex_006950",
"source_idx": 6950,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3665,
... |
[
{
"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",
"budget": 2932
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006950",
"normalized_example_id": "ex_006950",
"source_idx": 6950,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3665,
... |
[
{
"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",
"budget": 3665
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006950",
"normalized_example_id": "ex_006950",
"source_idx": 6950,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3665,
... |
[
{
"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": "f(x)=x",
"budget": 5446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006951",
"normalized_example_id": "ex_006951",
"source_idx": 6951,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9077,
... |
[
{
"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": "f(x)=x",
"budget": 7262
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006951",
"normalized_example_id": "ex_006951",
"source_idx": 6951,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9077,
... |
[
{
"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": "f(x)=x",
"budget": 9077
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006951",
"normalized_example_id": "ex_006951",
"source_idx": 6951,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9077,
... |
[
{
"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",
"budget": 1162
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006952",
"normalized_example_id": "ex_006952",
"source_idx": 6952,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1936,
... |
[
{
"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",
"budget": 1549
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006952",
"normalized_example_id": "ex_006952",
"source_idx": 6952,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1936,
... |
[
{
"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",
"budget": 1936
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006952",
"normalized_example_id": "ex_006952",
"source_idx": 6952,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1936,
... |
[
{
"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": "47",
"budget": 1563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006953",
"normalized_example_id": "ex_006953",
"source_idx": 6953,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2605,
... |
[
{
"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": "47",
"budget": 2084
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006953",
"normalized_example_id": "ex_006953",
"source_idx": 6953,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2605,
... |
[
{
"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": "47",
"budget": 2605
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006953",
"normalized_example_id": "ex_006953",
"source_idx": 6953,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2605,
... |
[
{
"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": "P(x) = ax",
"budget": 2806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006955",
"normalized_example_id": "ex_006955",
"source_idx": 6955,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4677,
... |
[
{
"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": "P(x) = ax",
"budget": 3742
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006955",
"normalized_example_id": "ex_006955",
"source_idx": 6955,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4677,
... |
[
{
"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": "P(x) = ax",
"budget": 4677
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006955",
"normalized_example_id": "ex_006955",
"source_idx": 6955,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4677,
... |
[
{
"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": "n\\geq6400",
"budget": 3148
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006957",
"normalized_example_id": "ex_006957",
"source_idx": 6957,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5246,
... |
[
{
"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": "n\\geq6400",
"budget": 4197
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006957",
"normalized_example_id": "ex_006957",
"source_idx": 6957,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5246,
... |
[
{
"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": "n\\geq6400",
"budget": 5246
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006957",
"normalized_example_id": "ex_006957",
"source_idx": 6957,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5246,
... |
[
{
"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": "4",
"budget": 2705
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006960",
"normalized_example_id": "ex_006960",
"source_idx": 6960,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4508,
... |
[
{
"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": "4",
"budget": 3606
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006960",
"normalized_example_id": "ex_006960",
"source_idx": 6960,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4508,
... |
[
{
"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": "4",
"budget": 4508
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006960",
"normalized_example_id": "ex_006960",
"source_idx": 6960,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4508,
... |
[
{
"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": "x=3, y=1, z=4",
"budget": 2222
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006964",
"normalized_example_id": "ex_006964",
"source_idx": 6964,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3704,
... |
[
{
"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": "x=3, y=1, z=4",
"budget": 2963
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006964",
"normalized_example_id": "ex_006964",
"source_idx": 6964,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3704,
... |
[
{
"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": "x=3, y=1, z=4",
"budget": 3704
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006964",
"normalized_example_id": "ex_006964",
"source_idx": 6964,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3704,
... |
[
{
"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": "12",
"budget": 6020
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006966",
"normalized_example_id": "ex_006966",
"source_idx": 6966,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10034,
... |
[
{
"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": "12",
"budget": 8027
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006966",
"normalized_example_id": "ex_006966",
"source_idx": 6966,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10034,
... |
[
{
"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": "12",
"budget": 10034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006966",
"normalized_example_id": "ex_006966",
"source_idx": 6966,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10034,
... |
[
{
"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": "48;80;12;12",
"budget": 941
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006970",
"normalized_example_id": "ex_006970",
"source_idx": 6970,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1568,
... |
[
{
"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": "48;80;12;12",
"budget": 1254
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006970",
"normalized_example_id": "ex_006970",
"source_idx": 6970,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1568,
... |
[
{
"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": "48;80;12;12",
"budget": 1568
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006970",
"normalized_example_id": "ex_006970",
"source_idx": 6970,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1568,
... |
[
{
"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": "20(1-\\sqrt{\\frac{3}{4}})",
"budget": 2468
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006973",
"normalized_example_id": "ex_006973",
"source_idx": 6973,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4113,
... |
[
{
"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": "20(1-\\sqrt{\\frac{3}{4}})",
"budget": 3290
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006973",
"normalized_example_id": "ex_006973",
"source_idx": 6973,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4113,
... |
[
{
"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": "20(1-\\sqrt{\\frac{3}{4}})",
"budget": 4113
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006973",
"normalized_example_id": "ex_006973",
"source_idx": 6973,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4113,
... |
[
{
"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": 2138
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006978",
"normalized_example_id": "ex_006978",
"source_idx": 6978,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3563,
... |
[
{
"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": 2850
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006978",
"normalized_example_id": "ex_006978",
"source_idx": 6978,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3563,
... |
[
{
"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": 3563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006978",
"normalized_example_id": "ex_006978",
"source_idx": 6978,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3563,
... |
[
{
"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": "f(x)=x-1",
"budget": 2882
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006979",
"normalized_example_id": "ex_006979",
"source_idx": 6979,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4803,
... |
[
{
"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": "f(x)=x-1",
"budget": 3842
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006979",
"normalized_example_id": "ex_006979",
"source_idx": 6979,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4803,
... |
[
{
"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": "f(x)=x-1",
"budget": 4803
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006979",
"normalized_example_id": "ex_006979",
"source_idx": 6979,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4803,
... |
[
{
"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": "12504",
"budget": 1210
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006981",
"normalized_example_id": "ex_006981",
"source_idx": 6981,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2017,
... |
[
{
"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": "12504",
"budget": 1614
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006981",
"normalized_example_id": "ex_006981",
"source_idx": 6981,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2017,
... |
[
{
"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": "12504",
"budget": 2017
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006981",
"normalized_example_id": "ex_006981",
"source_idx": 6981,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2017,
... |
[
{
"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": "30",
"budget": 3998
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006982",
"normalized_example_id": "ex_006982",
"source_idx": 6982,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6664,
... |
[
{
"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": "30",
"budget": 5331
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006982",
"normalized_example_id": "ex_006982",
"source_idx": 6982,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6664,
... |
[
{
"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": "30",
"budget": 6664
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006982",
"normalized_example_id": "ex_006982",
"source_idx": 6982,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6664,
... |
[
{
"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": 763
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006983",
"normalized_example_id": "ex_006983",
"source_idx": 6983,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1272,
... |
[
{
"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": 1018
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006983",
"normalized_example_id": "ex_006983",
"source_idx": 6983,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1272,
... |
[
{
"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": 1272
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006983",
"normalized_example_id": "ex_006983",
"source_idx": 6983,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1272,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.