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": "f(x)=\\frac{x+1}{x-1}",
"budget": 4452
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004348",
"normalized_example_id": "ex_004348",
"source_idx": 4348,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5565,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{x+1}{x-1}",
"budget": 5565
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004348",
"normalized_example_id": "ex_004348",
"source_idx": 4348,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5565,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "89",
"budget": 1635
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004349",
"normalized_example_id": "ex_004349",
"source_idx": 4349,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2725,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "89",
"budget": 2180
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004349",
"normalized_example_id": "ex_004349",
"source_idx": 4349,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2725,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "89",
"budget": 2725
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004349",
"normalized_example_id": "ex_004349",
"source_idx": 4349,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2725,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4398
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004352",
"normalized_example_id": "ex_004352",
"source_idx": 4352,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7330,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5864
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004352",
"normalized_example_id": "ex_004352",
"source_idx": 4352,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7330,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7330
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004352",
"normalized_example_id": "ex_004352",
"source_idx": 4352,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7330,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "T(-\\frac{\\pi}{4}+2k\\pi,\\frac{1}{2}\\ln2)",
"budget": 4655
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004353",
"normalized_example_id": "ex_004353",
"source_idx": 4353,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7759,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "T(-\\frac{\\pi}{4}+2k\\pi,\\frac{1}{2}\\ln2)",
"budget": 6207
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004353",
"normalized_example_id": "ex_004353",
"source_idx": 4353,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7759,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "T(-\\frac{\\pi}{4}+2k\\pi,\\frac{1}{2}\\ln2)",
"budget": 7759
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004353",
"normalized_example_id": "ex_004353",
"source_idx": 4353,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7759,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2873
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004357",
"normalized_example_id": "ex_004357",
"source_idx": 4357,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4788,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3830
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004357",
"normalized_example_id": "ex_004357",
"source_idx": 4357,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4788,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4788
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004357",
"normalized_example_id": "ex_004357",
"source_idx": 4357,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4788,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "432",
"budget": 5474
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004358",
"normalized_example_id": "ex_004358",
"source_idx": 4358,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9124,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "432",
"budget": 7299
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004358",
"normalized_example_id": "ex_004358",
"source_idx": 4358,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9124,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "432",
"budget": 9124
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004358",
"normalized_example_id": "ex_004358",
"source_idx": 4358,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9124,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\sqrt{2}",
"budget": 5624
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004359",
"normalized_example_id": "ex_004359",
"source_idx": 4359,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9374,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\sqrt{2}",
"budget": 7499
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004359",
"normalized_example_id": "ex_004359",
"source_idx": 4359,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9374,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\sqrt{2}",
"budget": 9374
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004359",
"normalized_example_id": "ex_004359",
"source_idx": 4359,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9374,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4195
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004360",
"normalized_example_id": "ex_004360",
"source_idx": 4360,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6992,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5594
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004360",
"normalized_example_id": "ex_004360",
"source_idx": 4360,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6992,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6992
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004360",
"normalized_example_id": "ex_004360",
"source_idx": 4360,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6992,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1577
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004363",
"normalized_example_id": "ex_004363",
"source_idx": 4363,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2629,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2103
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004363",
"normalized_example_id": "ex_004363",
"source_idx": 4363,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2629,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2629
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004363",
"normalized_example_id": "ex_004363",
"source_idx": 4363,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2629,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A=5,O=3,B=8,M=4,E=6,P=1",
"budget": 2738
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004364",
"normalized_example_id": "ex_004364",
"source_idx": 4364,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4564,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A=5,O=3,B=8,M=4,E=6,P=1",
"budget": 3651
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004364",
"normalized_example_id": "ex_004364",
"source_idx": 4364,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4564,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A=5,O=3,B=8,M=4,E=6,P=1",
"budget": 4564
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004364",
"normalized_example_id": "ex_004364",
"source_idx": 4364,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4564,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(B)}",
"budget": 4021
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004365",
"normalized_example_id": "ex_004365",
"source_idx": 4365,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6702,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(B)}",
"budget": 5362
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004365",
"normalized_example_id": "ex_004365",
"source_idx": 4365,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6702,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(B)}",
"budget": 6702
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004365",
"normalized_example_id": "ex_004365",
"source_idx": 4365,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6702,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 3244
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004366",
"normalized_example_id": "ex_004366",
"source_idx": 4366,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5407,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 4326
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004366",
"normalized_example_id": "ex_004366",
"source_idx": 4366,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5407,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 5407
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004366",
"normalized_example_id": "ex_004366",
"source_idx": 4366,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5407,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:2",
"budget": 3147
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004369",
"normalized_example_id": "ex_004369",
"source_idx": 4369,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5245,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:2",
"budget": 4196
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004369",
"normalized_example_id": "ex_004369",
"source_idx": 4369,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5245,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:2",
"budget": 5245
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004369",
"normalized_example_id": "ex_004369",
"source_idx": 4369,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5245,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "68",
"budget": 2906
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004370",
"normalized_example_id": "ex_004370",
"source_idx": 4370,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4844,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "68",
"budget": 3875
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004370",
"normalized_example_id": "ex_004370",
"source_idx": 4370,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4844,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "68",
"budget": 4844
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004370",
"normalized_example_id": "ex_004370",
"source_idx": 4370,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4844,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2537
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004371",
"normalized_example_id": "ex_004371",
"source_idx": 4371,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3383
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004371",
"normalized_example_id": "ex_004371",
"source_idx": 4371,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4229
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004371",
"normalized_example_id": "ex_004371",
"source_idx": 4371,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5184",
"budget": 5297
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004373",
"normalized_example_id": "ex_004373",
"source_idx": 4373,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8829,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5184",
"budget": 7063
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004373",
"normalized_example_id": "ex_004373",
"source_idx": 4373,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8829,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5184",
"budget": 8829
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004373",
"normalized_example_id": "ex_004373",
"source_idx": 4373,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8829,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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} - 1",
"budget": 3530
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004379",
"normalized_example_id": "ex_004379",
"source_idx": 4379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5883,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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} - 1",
"budget": 4706
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004379",
"normalized_example_id": "ex_004379",
"source_idx": 4379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5883,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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} - 1",
"budget": 5883
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004379",
"normalized_example_id": "ex_004379",
"source_idx": 4379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5883,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 733
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004380",
"normalized_example_id": "ex_004380",
"source_idx": 4380,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 977
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004380",
"normalized_example_id": "ex_004380",
"source_idx": 4380,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1221
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004380",
"normalized_example_id": "ex_004380",
"source_idx": 4380,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "51",
"budget": 3158
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004382",
"normalized_example_id": "ex_004382",
"source_idx": 4382,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5263,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "51",
"budget": 4210
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004382",
"normalized_example_id": "ex_004382",
"source_idx": 4382,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5263,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "51",
"budget": 5263
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004382",
"normalized_example_id": "ex_004382",
"source_idx": 4382,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5263,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3440
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004383",
"normalized_example_id": "ex_004383",
"source_idx": 4383,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5733,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4586
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004383",
"normalized_example_id": "ex_004383",
"source_idx": 4383,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5733,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5733
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004383",
"normalized_example_id": "ex_004383",
"source_idx": 4383,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5733,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004386",
"normalized_example_id": "ex_004386",
"source_idx": 4386,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3097,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2478
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004386",
"normalized_example_id": "ex_004386",
"source_idx": 4386,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3097,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3097
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004386",
"normalized_example_id": "ex_004386",
"source_idx": 4386,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3097,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 1081
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004389",
"normalized_example_id": "ex_004389",
"source_idx": 4389,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1801,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 1441
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004389",
"normalized_example_id": "ex_004389",
"source_idx": 4389,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1801,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 1801
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004389",
"normalized_example_id": "ex_004389",
"source_idx": 4389,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1801,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "131",
"budget": 4127
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004391",
"normalized_example_id": "ex_004391",
"source_idx": 4391,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6878,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "131",
"budget": 5502
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004391",
"normalized_example_id": "ex_004391",
"source_idx": 4391,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6878,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "131",
"budget": 6878
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004391",
"normalized_example_id": "ex_004391",
"source_idx": 4391,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6878,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "528624",
"budget": 2796
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004392",
"normalized_example_id": "ex_004392",
"source_idx": 4392,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "528624",
"budget": 3728
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004392",
"normalized_example_id": "ex_004392",
"source_idx": 4392,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "528624",
"budget": 4660
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004392",
"normalized_example_id": "ex_004392",
"source_idx": 4392,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\pi}",
"budget": 1034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004393",
"normalized_example_id": "ex_004393",
"source_idx": 4393,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1723,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\pi}",
"budget": 1378
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004393",
"normalized_example_id": "ex_004393",
"source_idx": 4393,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1723,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\pi}",
"budget": 1723
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004393",
"normalized_example_id": "ex_004393",
"source_idx": 4393,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1723,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "64",
"budget": 863
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004395",
"normalized_example_id": "ex_004395",
"source_idx": 4395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1439,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "64",
"budget": 1151
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004395",
"normalized_example_id": "ex_004395",
"source_idx": 4395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1439,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "64",
"budget": 1439
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004395",
"normalized_example_id": "ex_004395",
"source_idx": 4395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1439,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1532
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004398",
"normalized_example_id": "ex_004398",
"source_idx": 4398,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2553,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2042
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004398",
"normalized_example_id": "ex_004398",
"source_idx": 4398,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2553,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2553
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004398",
"normalized_example_id": "ex_004398",
"source_idx": 4398,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2553,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln(6^{2}\\cdot7^{2})",
"budget": 1837
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004399",
"normalized_example_id": "ex_004399",
"source_idx": 4399,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3062,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln(6^{2}\\cdot7^{2})",
"budget": 2450
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004399",
"normalized_example_id": "ex_004399",
"source_idx": 4399,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3062,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln(6^{2}\\cdot7^{2})",
"budget": 3062
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004399",
"normalized_example_id": "ex_004399",
"source_idx": 4399,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3062,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 6008
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004401",
"normalized_example_id": "ex_004401",
"source_idx": 4401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10014,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 8011
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004401",
"normalized_example_id": "ex_004401",
"source_idx": 4401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10014,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 10014
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004401",
"normalized_example_id": "ex_004401",
"source_idx": 4401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10014,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2133
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004403",
"normalized_example_id": "ex_004403",
"source_idx": 4403,
"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": "4",
"budget": 2844
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004403",
"normalized_example_id": "ex_004403",
"source_idx": 4403,
"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": "4",
"budget": 3555
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004403",
"normalized_example_id": "ex_004403",
"source_idx": 4403,
"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": "1",
"budget": 1629
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004405",
"normalized_example_id": "ex_004405",
"source_idx": 4405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2172
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004405",
"normalized_example_id": "ex_004405",
"source_idx": 4405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2715
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004405",
"normalized_example_id": "ex_004405",
"source_idx": 4405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(a^{\\frac{2}{3}}+b^{\\frac{2}{3}}\\right)^{\\frac{3}{2}}",
"budget": 2813
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004407",
"normalized_example_id": "ex_004407",
"source_idx": 4407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4688,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(a^{\\frac{2}{3}}+b^{\\frac{2}{3}}\\right)^{\\frac{3}{2}}",
"budget": 3750
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004407",
"normalized_example_id": "ex_004407",
"source_idx": 4407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4688,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(a^{\\frac{2}{3}}+b^{\\frac{2}{3}}\\right)^{\\frac{3}{2}}",
"budget": 4688
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004407",
"normalized_example_id": "ex_004407",
"source_idx": 4407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4688,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln 2",
"budget": 1801
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004408",
"normalized_example_id": "ex_004408",
"source_idx": 4408,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln 2",
"budget": 2401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004408",
"normalized_example_id": "ex_004408",
"source_idx": 4408,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln 2",
"budget": 3001
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004408",
"normalized_example_id": "ex_004408",
"source_idx": 4408,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{105}{16}",
"budget": 2521
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004409",
"normalized_example_id": "ex_004409",
"source_idx": 4409,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4201,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{105}{16}",
"budget": 3361
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004409",
"normalized_example_id": "ex_004409",
"source_idx": 4409,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4201,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.