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": "\\text{B}",
"budget": 5873
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002001",
"normalized_example_id": "ex_002001",
"source_idx": 2001,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5873,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10\\times20",
"budget": 1152
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002002",
"normalized_example_id": "ex_002002",
"source_idx": 2002,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1920,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10\\times20",
"budget": 1536
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002002",
"normalized_example_id": "ex_002002",
"source_idx": 2002,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1920,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10\\times20",
"budget": 1920
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002002",
"normalized_example_id": "ex_002002",
"source_idx": 2002,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1920,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 3, 7, 19",
"budget": 4567
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002003",
"normalized_example_id": "ex_002003",
"source_idx": 2003,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7611,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 3, 7, 19",
"budget": 6089
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002003",
"normalized_example_id": "ex_002003",
"source_idx": 2003,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7611,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 3, 7, 19",
"budget": 7611
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002003",
"normalized_example_id": "ex_002003",
"source_idx": 2003,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7611,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;3}",
"budget": 2854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002004",
"normalized_example_id": "ex_002004",
"source_idx": 2004,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4757,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;3}",
"budget": 3806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002004",
"normalized_example_id": "ex_002004",
"source_idx": 2004,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4757,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;3}",
"budget": 4757
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002004",
"normalized_example_id": "ex_002004",
"source_idx": 2004,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4757,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "97",
"budget": 1612
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002005",
"normalized_example_id": "ex_002005",
"source_idx": 2005,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "97",
"budget": 2149
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002005",
"normalized_example_id": "ex_002005",
"source_idx": 2005,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "97",
"budget": 2686
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002005",
"normalized_example_id": "ex_002005",
"source_idx": 2005,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "26",
"budget": 5123
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002008",
"normalized_example_id": "ex_002008",
"source_idx": 2008,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8538,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "26",
"budget": 6830
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002008",
"normalized_example_id": "ex_002008",
"source_idx": 2008,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8538,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "26",
"budget": 8538
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002008",
"normalized_example_id": "ex_002008",
"source_idx": 2008,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8538,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x)=x",
"budget": 2831
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002009",
"normalized_example_id": "ex_002009",
"source_idx": 2009,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4718,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x)=x",
"budget": 3774
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002009",
"normalized_example_id": "ex_002009",
"source_idx": 2009,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4718,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x)=x",
"budget": 4718
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002009",
"normalized_example_id": "ex_002009",
"source_idx": 2009,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4718,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5145
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002010",
"normalized_example_id": "ex_002010",
"source_idx": 2010,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8575,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6860
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002010",
"normalized_example_id": "ex_002010",
"source_idx": 2010,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8575,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8575
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002010",
"normalized_example_id": "ex_002010",
"source_idx": 2010,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8575,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 670
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002011",
"normalized_example_id": "ex_002011",
"source_idx": 2011,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1116,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002011",
"normalized_example_id": "ex_002011",
"source_idx": 2011,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1116,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 1116
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002011",
"normalized_example_id": "ex_002011",
"source_idx": 2011,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1116,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3004",
"budget": 3672
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002012",
"normalized_example_id": "ex_002012",
"source_idx": 2012,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6120,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3004",
"budget": 4896
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002012",
"normalized_example_id": "ex_002012",
"source_idx": 2012,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6120,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3004",
"budget": 6120
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002012",
"normalized_example_id": "ex_002012",
"source_idx": 2012,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6120,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{6}r",
"budget": 2572
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002013",
"normalized_example_id": "ex_002013",
"source_idx": 2013,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4287,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{6}r",
"budget": 3430
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002013",
"normalized_example_id": "ex_002013",
"source_idx": 2013,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4287,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{6}r",
"budget": 4287
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002013",
"normalized_example_id": "ex_002013",
"source_idx": 2013,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4287,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2459
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002015",
"normalized_example_id": "ex_002015",
"source_idx": 2015,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3279
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002015",
"normalized_example_id": "ex_002015",
"source_idx": 2015,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4099
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002015",
"normalized_example_id": "ex_002015",
"source_idx": 2015,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1760
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002017",
"normalized_example_id": "ex_002017",
"source_idx": 2017,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2934,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2347
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002017",
"normalized_example_id": "ex_002017",
"source_idx": 2017,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2934,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2934
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002017",
"normalized_example_id": "ex_002017",
"source_idx": 2017,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2934,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "335",
"budget": 3221
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002018",
"normalized_example_id": "ex_002018",
"source_idx": 2018,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5368,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "335",
"budget": 4294
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002018",
"normalized_example_id": "ex_002018",
"source_idx": 2018,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5368,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "335",
"budget": 5368
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002018",
"normalized_example_id": "ex_002018",
"source_idx": 2018,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5368,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3.5\\mathrm{~}",
"budget": 5197
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002021",
"normalized_example_id": "ex_002021",
"source_idx": 2021,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8662,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3.5\\mathrm{~}",
"budget": 6930
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002021",
"normalized_example_id": "ex_002021",
"source_idx": 2021,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8662,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3.5\\mathrm{~}",
"budget": 8662
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002021",
"normalized_example_id": "ex_002021",
"source_idx": 2021,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8662,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2ak",
"budget": 4250
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002023",
"normalized_example_id": "ex_002023",
"source_idx": 2023,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2ak",
"budget": 5666
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002023",
"normalized_example_id": "ex_002023",
"source_idx": 2023,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2ak",
"budget": 7083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002023",
"normalized_example_id": "ex_002023",
"source_idx": 2023,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n)=n",
"budget": 5167
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002024",
"normalized_example_id": "ex_002024",
"source_idx": 2024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8611,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n)=n",
"budget": 6889
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002024",
"normalized_example_id": "ex_002024",
"source_idx": 2024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8611,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n)=n",
"budget": 8611
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002024",
"normalized_example_id": "ex_002024",
"source_idx": 2024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8611,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}-8}{2}",
"budget": 2041
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002027",
"normalized_example_id": "ex_002027",
"source_idx": 2027,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3401,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}-8}{2}",
"budget": 2721
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002027",
"normalized_example_id": "ex_002027",
"source_idx": 2027,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3401,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}-8}{2}",
"budget": 3401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002027",
"normalized_example_id": "ex_002027",
"source_idx": 2027,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3401,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 730
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002028",
"normalized_example_id": "ex_002028",
"source_idx": 2028,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1217,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 974
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002028",
"normalized_example_id": "ex_002028",
"source_idx": 2028,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1217,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1217
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002028",
"normalized_example_id": "ex_002028",
"source_idx": 2028,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1217,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5117
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002029",
"normalized_example_id": "ex_002029",
"source_idx": 2029,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8528,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6822
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002029",
"normalized_example_id": "ex_002029",
"source_idx": 2029,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8528,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8528
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002029",
"normalized_example_id": "ex_002029",
"source_idx": 2029,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8528,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n}=10^{2-\\left(\\frac{1}{2}\\right)^{n-1}}",
"budget": 2368
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002030",
"normalized_example_id": "ex_002030",
"source_idx": 2030,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3947,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n}=10^{2-\\left(\\frac{1}{2}\\right)^{n-1}}",
"budget": 3158
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002030",
"normalized_example_id": "ex_002030",
"source_idx": 2030,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3947,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n}=10^{2-\\left(\\frac{1}{2}\\right)^{n-1}}",
"budget": 3947
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002030",
"normalized_example_id": "ex_002030",
"source_idx": 2030,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3947,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{5}{9}",
"budget": 1219
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002031",
"normalized_example_id": "ex_002031",
"source_idx": 2031,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2032,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{5}{9}",
"budget": 1626
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002031",
"normalized_example_id": "ex_002031",
"source_idx": 2031,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2032,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{5}{9}",
"budget": 2032
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002031",
"normalized_example_id": "ex_002031",
"source_idx": 2031,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2032,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9x-y+16=0",
"budget": 1168
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002032",
"normalized_example_id": "ex_002032",
"source_idx": 2032,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9x-y+16=0",
"budget": 1557
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002032",
"normalized_example_id": "ex_002032",
"source_idx": 2032,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9x-y+16=0",
"budget": 1946
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002032",
"normalized_example_id": "ex_002032",
"source_idx": 2032,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 3329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002033",
"normalized_example_id": "ex_002033",
"source_idx": 2033,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5549,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 4439
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002033",
"normalized_example_id": "ex_002033",
"source_idx": 2033,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5549,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 5549
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002033",
"normalized_example_id": "ex_002033",
"source_idx": 2033,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5549,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2.4",
"budget": 4103
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002038",
"normalized_example_id": "ex_002038",
"source_idx": 2038,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6839,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2.4",
"budget": 5471
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002038",
"normalized_example_id": "ex_002038",
"source_idx": 2038,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6839,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2.4",
"budget": 6839
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002038",
"normalized_example_id": "ex_002038",
"source_idx": 2038,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6839,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2001 \\cdot 2^{1998}",
"budget": 1993
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002040",
"normalized_example_id": "ex_002040",
"source_idx": 2040,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3321,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2001 \\cdot 2^{1998}",
"budget": 2657
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002040",
"normalized_example_id": "ex_002040",
"source_idx": 2040,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3321,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2001 \\cdot 2^{1998}",
"budget": 3321
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002040",
"normalized_example_id": "ex_002040",
"source_idx": 2040,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3321,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{7}",
"budget": 2535
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002041",
"normalized_example_id": "ex_002041",
"source_idx": 2041,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4225,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{7}",
"budget": 3380
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002041",
"normalized_example_id": "ex_002041",
"source_idx": 2041,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4225,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{7}",
"budget": 4225
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002041",
"normalized_example_id": "ex_002041",
"source_idx": 2041,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4225,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{3}",
"budget": 5397
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002042",
"normalized_example_id": "ex_002042",
"source_idx": 2042,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8995,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{3}",
"budget": 7196
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002042",
"normalized_example_id": "ex_002042",
"source_idx": 2042,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8995,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{3}",
"budget": 8995
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002042",
"normalized_example_id": "ex_002042",
"source_idx": 2042,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8995,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{4a}",
"budget": 2524
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002045",
"normalized_example_id": "ex_002045",
"source_idx": 2045,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4206,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{4a}",
"budget": 3365
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002045",
"normalized_example_id": "ex_002045",
"source_idx": 2045,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4206,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{4a}",
"budget": 4206
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002045",
"normalized_example_id": "ex_002045",
"source_idx": 2045,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4206,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;3;5;31)",
"budget": 5851
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002046",
"normalized_example_id": "ex_002046",
"source_idx": 2046,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9751,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;3;5;31)",
"budget": 7801
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002046",
"normalized_example_id": "ex_002046",
"source_idx": 2046,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9751,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;3;5;31)",
"budget": 9751
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002046",
"normalized_example_id": "ex_002046",
"source_idx": 2046,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9751,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{2}u\\leqk<2u",
"budget": 2146
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002047",
"normalized_example_id": "ex_002047",
"source_idx": 2047,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3576,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{2}u\\leqk<2u",
"budget": 2861
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002047",
"normalized_example_id": "ex_002047",
"source_idx": 2047,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3576,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{2}u\\leqk<2u",
"budget": 3576
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002047",
"normalized_example_id": "ex_002047",
"source_idx": 2047,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3576,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_1=2, y_1=5; x_2=5, y_2=2",
"budget": 1462
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002049",
"normalized_example_id": "ex_002049",
"source_idx": 2049,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2436,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_1=2, y_1=5; x_2=5, y_2=2",
"budget": 1949
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002049",
"normalized_example_id": "ex_002049",
"source_idx": 2049,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2436,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_1=2, y_1=5; x_2=5, y_2=2",
"budget": 2436
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002049",
"normalized_example_id": "ex_002049",
"source_idx": 2049,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2436,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 2084
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002051",
"normalized_example_id": "ex_002051",
"source_idx": 2051,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 2779
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002051",
"normalized_example_id": "ex_002051",
"source_idx": 2051,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 3474
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002051",
"normalized_example_id": "ex_002051",
"source_idx": 2051,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "56",
"budget": 1287
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002055",
"normalized_example_id": "ex_002055",
"source_idx": 2055,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2145,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "56",
"budget": 1716
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002055",
"normalized_example_id": "ex_002055",
"source_idx": 2055,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2145,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "56",
"budget": 2145
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002055",
"normalized_example_id": "ex_002055",
"source_idx": 2055,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2145,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.