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": "\\frac{2}{e}",
"budget": 4487
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005605",
"normalized_example_id": "ex_005605",
"source_idx": 5605,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4487,
... |
[
{
"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": "9",
"budget": 4223
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005608",
"normalized_example_id": "ex_005608",
"source_idx": 5608,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7039,
... |
[
{
"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": "9",
"budget": 5631
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005608",
"normalized_example_id": "ex_005608",
"source_idx": 5608,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7039,
... |
[
{
"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": "9",
"budget": 7039
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005608",
"normalized_example_id": "ex_005608",
"source_idx": 5608,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7039,
... |
[
{
"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": "675",
"budget": 2040
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005609",
"normalized_example_id": "ex_005609",
"source_idx": 5609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3400,
... |
[
{
"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": "675",
"budget": 2720
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005609",
"normalized_example_id": "ex_005609",
"source_idx": 5609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3400,
... |
[
{
"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": "675",
"budget": 3400
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005609",
"normalized_example_id": "ex_005609",
"source_idx": 5609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3400,
... |
[
{
"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",
"budget": 1595
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005611",
"normalized_example_id": "ex_005611",
"source_idx": 5611,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2659,
... |
[
{
"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",
"budget": 2127
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005611",
"normalized_example_id": "ex_005611",
"source_idx": 5611,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2659,
... |
[
{
"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",
"budget": 2659
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005611",
"normalized_example_id": "ex_005611",
"source_idx": 5611,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2659,
... |
[
{
"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{\\sin(\\cos3)}{4\\sin^{2}2x}",
"budget": 1668
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005613",
"normalized_example_id": "ex_005613",
"source_idx": 5613,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2780,
... |
[
{
"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{\\sin(\\cos3)}{4\\sin^{2}2x}",
"budget": 2224
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005613",
"normalized_example_id": "ex_005613",
"source_idx": 5613,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2780,
... |
[
{
"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{\\sin(\\cos3)}{4\\sin^{2}2x}",
"budget": 2780
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005613",
"normalized_example_id": "ex_005613",
"source_idx": 5613,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2780,
... |
[
{
"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}{2}",
"budget": 1381
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005616",
"normalized_example_id": "ex_005616",
"source_idx": 5616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2301,
... |
[
{
"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}{2}",
"budget": 1841
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005616",
"normalized_example_id": "ex_005616",
"source_idx": 5616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2301,
... |
[
{
"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}{2}",
"budget": 2301
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005616",
"normalized_example_id": "ex_005616",
"source_idx": 5616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2301,
... |
[
{
"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": "2008",
"budget": 2275
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005623",
"normalized_example_id": "ex_005623",
"source_idx": 5623,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3792,
... |
[
{
"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": "2008",
"budget": 3034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005623",
"normalized_example_id": "ex_005623",
"source_idx": 5623,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3792,
... |
[
{
"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": "2008",
"budget": 3792
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005623",
"normalized_example_id": "ex_005623",
"source_idx": 5623,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3792,
... |
[
{
"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",
"budget": 4766
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005624",
"normalized_example_id": "ex_005624",
"source_idx": 5624,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7944,
... |
[
{
"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",
"budget": 6355
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005624",
"normalized_example_id": "ex_005624",
"source_idx": 5624,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7944,
... |
[
{
"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",
"budget": 7944
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005624",
"normalized_example_id": "ex_005624",
"source_idx": 5624,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7944,
... |
[
{
"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": "781",
"budget": 1003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005627",
"normalized_example_id": "ex_005627",
"source_idx": 5627,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1672,
... |
[
{
"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": "781",
"budget": 1338
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005627",
"normalized_example_id": "ex_005627",
"source_idx": 5627,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1672,
... |
[
{
"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": "781",
"budget": 1672
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005627",
"normalized_example_id": "ex_005627",
"source_idx": 5627,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1672,
... |
[
{
"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": "9801",
"budget": 3263
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005631",
"normalized_example_id": "ex_005631",
"source_idx": 5631,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5438,
... |
[
{
"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": "9801",
"budget": 4350
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005631",
"normalized_example_id": "ex_005631",
"source_idx": 5631,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5438,
... |
[
{
"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": "9801",
"budget": 5438
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005631",
"normalized_example_id": "ex_005631",
"source_idx": 5631,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5438,
... |
[
{
"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": "3.75\\sqrt{7}\\mathrm{~}^{2}",
"budget": 2471
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005632",
"normalized_example_id": "ex_005632",
"source_idx": 5632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4118,
... |
[
{
"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": "3.75\\sqrt{7}\\mathrm{~}^{2}",
"budget": 3294
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005632",
"normalized_example_id": "ex_005632",
"source_idx": 5632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4118,
... |
[
{
"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": "3.75\\sqrt{7}\\mathrm{~}^{2}",
"budget": 4118
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005632",
"normalized_example_id": "ex_005632",
"source_idx": 5632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4118,
... |
[
{
"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": 631
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005633",
"normalized_example_id": "ex_005633",
"source_idx": 5633,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1051,
... |
[
{
"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": 841
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005633",
"normalized_example_id": "ex_005633",
"source_idx": 5633,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1051,
... |
[
{
"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": 1051
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005633",
"normalized_example_id": "ex_005633",
"source_idx": 5633,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1051,
... |
[
{
"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": "(1,0,2)",
"budget": 5019
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005634",
"normalized_example_id": "ex_005634",
"source_idx": 5634,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8365,
... |
[
{
"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": "(1,0,2)",
"budget": 6692
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005634",
"normalized_example_id": "ex_005634",
"source_idx": 5634,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8365,
... |
[
{
"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": "(1,0,2)",
"budget": 8365
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005634",
"normalized_example_id": "ex_005634",
"source_idx": 5634,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8365,
... |
[
{
"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": "25",
"budget": 2576
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005635",
"normalized_example_id": "ex_005635",
"source_idx": 5635,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4294,
... |
[
{
"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": "25",
"budget": 3435
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005635",
"normalized_example_id": "ex_005635",
"source_idx": 5635,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4294,
... |
[
{
"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": "25",
"budget": 4294
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005635",
"normalized_example_id": "ex_005635",
"source_idx": 5635,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4294,
... |
[
{
"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}{1-x}",
"budget": 1808
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005636",
"normalized_example_id": "ex_005636",
"source_idx": 5636,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3013,
... |
[
{
"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}{1-x}",
"budget": 2410
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005636",
"normalized_example_id": "ex_005636",
"source_idx": 5636,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3013,
... |
[
{
"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}{1-x}",
"budget": 3013
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005636",
"normalized_example_id": "ex_005636",
"source_idx": 5636,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3013,
... |
[
{
"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{4}{5}",
"budget": 2035
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005637",
"normalized_example_id": "ex_005637",
"source_idx": 5637,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3391,
... |
[
{
"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{4}{5}",
"budget": 2713
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005637",
"normalized_example_id": "ex_005637",
"source_idx": 5637,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3391,
... |
[
{
"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{4}{5}",
"budget": 3391
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005637",
"normalized_example_id": "ex_005637",
"source_idx": 5637,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3391,
... |
[
{
"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_{n}=n!(1-\\frac{1}{1!}+\\frac{1}{2!}+\\cdots+\\frac{(-1)^{n}}{n!})",
"budget": 1939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005638",
"normalized_example_id": "ex_005638",
"source_idx": 5638,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3231,
... |
[
{
"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_{n}=n!(1-\\frac{1}{1!}+\\frac{1}{2!}+\\cdots+\\frac{(-1)^{n}}{n!})",
"budget": 2585
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005638",
"normalized_example_id": "ex_005638",
"source_idx": 5638,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3231,
... |
[
{
"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_{n}=n!(1-\\frac{1}{1!}+\\frac{1}{2!}+\\cdots+\\frac{(-1)^{n}}{n!})",
"budget": 3231
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005638",
"normalized_example_id": "ex_005638",
"source_idx": 5638,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3231,
... |
[
{
"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": "Omar",
"budget": 1334
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005641",
"normalized_example_id": "ex_005641",
"source_idx": 5641,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2224,
... |
[
{
"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": "Omar",
"budget": 1779
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005641",
"normalized_example_id": "ex_005641",
"source_idx": 5641,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2224,
... |
[
{
"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": "Omar",
"budget": 2224
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005641",
"normalized_example_id": "ex_005641",
"source_idx": 5641,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2224,
... |
[
{
"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": "8",
"budget": 3288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005642",
"normalized_example_id": "ex_005642",
"source_idx": 5642,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5480,
... |
[
{
"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": "8",
"budget": 4384
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005642",
"normalized_example_id": "ex_005642",
"source_idx": 5642,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5480,
... |
[
{
"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": "8",
"budget": 5480
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005642",
"normalized_example_id": "ex_005642",
"source_idx": 5642,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5480,
... |
[
{
"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{4}{3}",
"budget": 3435
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005643",
"normalized_example_id": "ex_005643",
"source_idx": 5643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5725,
... |
[
{
"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{4}{3}",
"budget": 4580
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005643",
"normalized_example_id": "ex_005643",
"source_idx": 5643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5725,
... |
[
{
"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{4}{3}",
"budget": 5725
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005643",
"normalized_example_id": "ex_005643",
"source_idx": 5643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5725,
... |
[
{
"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\\sqrt{2}",
"budget": 3388
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005645",
"normalized_example_id": "ex_005645",
"source_idx": 5645,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5646,
... |
[
{
"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\\sqrt{2}",
"budget": 4517
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005645",
"normalized_example_id": "ex_005645",
"source_idx": 5645,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5646,
... |
[
{
"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\\sqrt{2}",
"budget": 5646
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005645",
"normalized_example_id": "ex_005645",
"source_idx": 5645,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5646,
... |
[
{
"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": 2452
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005646",
"normalized_example_id": "ex_005646",
"source_idx": 5646,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4087,
... |
[
{
"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": 3270
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005646",
"normalized_example_id": "ex_005646",
"source_idx": 5646,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4087,
... |
[
{
"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": 4087
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005646",
"normalized_example_id": "ex_005646",
"source_idx": 5646,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4087,
... |
[
{
"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=1\\cdot6=2\\cdot3",
"budget": 3434
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005649",
"normalized_example_id": "ex_005649",
"source_idx": 5649,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5723,
... |
[
{
"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=1\\cdot6=2\\cdot3",
"budget": 4578
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005649",
"normalized_example_id": "ex_005649",
"source_idx": 5649,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5723,
... |
[
{
"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=1\\cdot6=2\\cdot3",
"budget": 5723
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005649",
"normalized_example_id": "ex_005649",
"source_idx": 5649,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5723,
... |
[
{
"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": 3236
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005650",
"normalized_example_id": "ex_005650",
"source_idx": 5650,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5394,
... |
[
{
"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": 4315
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005650",
"normalized_example_id": "ex_005650",
"source_idx": 5650,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5394,
... |
[
{
"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": 5394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005650",
"normalized_example_id": "ex_005650",
"source_idx": 5650,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5394,
... |
[
{
"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": 4327
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005652",
"normalized_example_id": "ex_005652",
"source_idx": 5652,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7212,
... |
[
{
"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": 5770
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005652",
"normalized_example_id": "ex_005652",
"source_idx": 5652,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7212,
... |
[
{
"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": 7212
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005652",
"normalized_example_id": "ex_005652",
"source_idx": 5652,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7212,
... |
[
{
"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": "14",
"budget": 1043
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005653",
"normalized_example_id": "ex_005653",
"source_idx": 5653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1738,
... |
[
{
"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": "14",
"budget": 1390
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005653",
"normalized_example_id": "ex_005653",
"source_idx": 5653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1738,
... |
[
{
"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": "14",
"budget": 1738
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005653",
"normalized_example_id": "ex_005653",
"source_idx": 5653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1738,
... |
[
{
"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": "9\\cdot2^{n}",
"budget": 3898
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005655",
"normalized_example_id": "ex_005655",
"source_idx": 5655,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6497,
... |
[
{
"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": "9\\cdot2^{n}",
"budget": 5198
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005655",
"normalized_example_id": "ex_005655",
"source_idx": 5655,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6497,
... |
[
{
"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": "9\\cdot2^{n}",
"budget": 6497
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005655",
"normalized_example_id": "ex_005655",
"source_idx": 5655,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6497,
... |
[
{
"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",
"budget": 790
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005660",
"normalized_example_id": "ex_005660",
"source_idx": 5660,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1317,
... |
[
{
"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",
"budget": 1054
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005660",
"normalized_example_id": "ex_005660",
"source_idx": 5660,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1317,
... |
[
{
"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",
"budget": 1317
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005660",
"normalized_example_id": "ex_005660",
"source_idx": 5660,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1317,
... |
[
{
"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": "8 \\text{ and } 20",
"budget": 3872
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005663",
"normalized_example_id": "ex_005663",
"source_idx": 5663,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6454,
... |
[
{
"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": "8 \\text{ and } 20",
"budget": 5163
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005663",
"normalized_example_id": "ex_005663",
"source_idx": 5663,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6454,
... |
[
{
"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": "8 \\text{ and } 20",
"budget": 6454
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005663",
"normalized_example_id": "ex_005663",
"source_idx": 5663,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6454,
... |
[
{
"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": "0",
"budget": 2604
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005664",
"normalized_example_id": "ex_005664",
"source_idx": 5664,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4340,
... |
[
{
"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": "0",
"budget": 3472
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005664",
"normalized_example_id": "ex_005664",
"source_idx": 5664,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4340,
... |
[
{
"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": "0",
"budget": 4340
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005664",
"normalized_example_id": "ex_005664",
"source_idx": 5664,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4340,
... |
[
{
"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",
"budget": 1016
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005667",
"normalized_example_id": "ex_005667",
"source_idx": 5667,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1693,
... |
[
{
"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",
"budget": 1354
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005667",
"normalized_example_id": "ex_005667",
"source_idx": 5667,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1693,
... |
[
{
"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",
"budget": 1693
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005667",
"normalized_example_id": "ex_005667",
"source_idx": 5667,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1693,
... |
[
{
"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": "\\lfloor\\frac{n^2}{4}\\rfloor",
"budget": 2636
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005668",
"normalized_example_id": "ex_005668",
"source_idx": 5668,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4394,
... |
[
{
"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": "\\lfloor\\frac{n^2}{4}\\rfloor",
"budget": 3515
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005668",
"normalized_example_id": "ex_005668",
"source_idx": 5668,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4394,
... |
[
{
"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": "\\lfloor\\frac{n^2}{4}\\rfloor",
"budget": 4394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005668",
"normalized_example_id": "ex_005668",
"source_idx": 5668,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4394,
... |
[
{
"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",
"budget": 2531
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005669",
"normalized_example_id": "ex_005669",
"source_idx": 5669,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4219,
... |
[
{
"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",
"budget": 3375
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005669",
"normalized_example_id": "ex_005669",
"source_idx": 5669,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4219,
... |
[
{
"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",
"budget": 4219
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005669",
"normalized_example_id": "ex_005669",
"source_idx": 5669,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4219,
... |
[
{
"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": "157",
"budget": 3654
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005671",
"normalized_example_id": "ex_005671",
"source_idx": 5671,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6090,
... |
[
{
"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": "157",
"budget": 4872
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005671",
"normalized_example_id": "ex_005671",
"source_idx": 5671,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6090,
... |
[
{
"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": "157",
"budget": 6090
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005671",
"normalized_example_id": "ex_005671",
"source_idx": 5671,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6090,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.