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": "5,6,8",
"budget": 4173
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006650",
"normalized_example_id": "ex_006650",
"source_idx": 6650,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5216,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5,6,8",
"budget": 5216
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006650",
"normalized_example_id": "ex_006650",
"source_idx": 6650,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5216,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 1842
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006652",
"normalized_example_id": "ex_006652",
"source_idx": 6652,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3070,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 2456
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006652",
"normalized_example_id": "ex_006652",
"source_idx": 6652,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3070,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 3070
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006652",
"normalized_example_id": "ex_006652",
"source_idx": 6652,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3070,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "333",
"budget": 3086
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006653",
"normalized_example_id": "ex_006653",
"source_idx": 6653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5143,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "333",
"budget": 4114
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006653",
"normalized_example_id": "ex_006653",
"source_idx": 6653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5143,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "333",
"budget": 5143
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006653",
"normalized_example_id": "ex_006653",
"source_idx": 6653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5143,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 4501
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006654",
"normalized_example_id": "ex_006654",
"source_idx": 6654,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7502,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 6002
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006654",
"normalized_example_id": "ex_006654",
"source_idx": 6654,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7502,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 7502
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006654",
"normalized_example_id": "ex_006654",
"source_idx": 6654,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7502,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=251, b=7",
"budget": 2858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006655",
"normalized_example_id": "ex_006655",
"source_idx": 6655,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4763,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=251, b=7",
"budget": 3810
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006655",
"normalized_example_id": "ex_006655",
"source_idx": 6655,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4763,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=251, b=7",
"budget": 4763
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006655",
"normalized_example_id": "ex_006655",
"source_idx": 6655,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4763,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\angle CED = 45^\\circ",
"budget": 4348
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006656",
"normalized_example_id": "ex_006656",
"source_idx": 6656,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7246,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\angle CED = 45^\\circ",
"budget": 5797
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006656",
"normalized_example_id": "ex_006656",
"source_idx": 6656,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7246,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\angle CED = 45^\\circ",
"budget": 7246
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006656",
"normalized_example_id": "ex_006656",
"source_idx": 6656,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7246,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "989",
"budget": 5791
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006657",
"normalized_example_id": "ex_006657",
"source_idx": 6657,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9651,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "989",
"budget": 7721
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006657",
"normalized_example_id": "ex_006657",
"source_idx": 6657,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9651,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "989",
"budget": 9651
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006657",
"normalized_example_id": "ex_006657",
"source_idx": 6657,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9651,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(\\frac{5}{2},+\\infty)",
"budget": 2868
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006658",
"normalized_example_id": "ex_006658",
"source_idx": 6658,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4780,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(\\frac{5}{2},+\\infty)",
"budget": 3824
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006658",
"normalized_example_id": "ex_006658",
"source_idx": 6658,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4780,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(\\frac{5}{2},+\\infty)",
"budget": 4780
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006658",
"normalized_example_id": "ex_006658",
"source_idx": 6658,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4780,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5574
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006659",
"normalized_example_id": "ex_006659",
"source_idx": 6659,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9290,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7432
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006659",
"normalized_example_id": "ex_006659",
"source_idx": 6659,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9290,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 9290
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006659",
"normalized_example_id": "ex_006659",
"source_idx": 6659,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9290,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\leq1/3;x\\geq1",
"budget": 2083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006660",
"normalized_example_id": "ex_006660",
"source_idx": 6660,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\leq1/3;x\\geq1",
"budget": 2778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006660",
"normalized_example_id": "ex_006660",
"source_idx": 6660,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\leq1/3;x\\geq1",
"budget": 3472
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006660",
"normalized_example_id": "ex_006660",
"source_idx": 6660,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4923
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006662",
"normalized_example_id": "ex_006662",
"source_idx": 6662,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8205,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6564
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006662",
"normalized_example_id": "ex_006662",
"source_idx": 6662,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8205,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8205
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006662",
"normalized_example_id": "ex_006662",
"source_idx": 6662,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8205,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(y)=0",
"budget": 4261
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006665",
"normalized_example_id": "ex_006665",
"source_idx": 6665,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7101,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(y)=0",
"budget": 5681
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006665",
"normalized_example_id": "ex_006665",
"source_idx": 6665,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7101,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(y)=0",
"budget": 7101
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006665",
"normalized_example_id": "ex_006665",
"source_idx": 6665,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7101,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "110,250",
"budget": 1828
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006666",
"normalized_example_id": "ex_006666",
"source_idx": 6666,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3046,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "110,250",
"budget": 2437
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006666",
"normalized_example_id": "ex_006666",
"source_idx": 6666,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3046,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "110,250",
"budget": 3046
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006666",
"normalized_example_id": "ex_006666",
"source_idx": 6666,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3046,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "81",
"budget": 1136
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006668",
"normalized_example_id": "ex_006668",
"source_idx": 6668,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "81",
"budget": 1514
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006668",
"normalized_example_id": "ex_006668",
"source_idx": 6668,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "81",
"budget": 1893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006668",
"normalized_example_id": "ex_006668",
"source_idx": 6668,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\cos (A-B)=-\\frac{1}{2}",
"budget": 1939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006670",
"normalized_example_id": "ex_006670",
"source_idx": 6670,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3231,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\cos (A-B)=-\\frac{1}{2}",
"budget": 2585
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006670",
"normalized_example_id": "ex_006670",
"source_idx": 6670,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3231,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\cos (A-B)=-\\frac{1}{2}",
"budget": 3231
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006670",
"normalized_example_id": "ex_006670",
"source_idx": 6670,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3231,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{5}{2}",
"budget": 1529
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006671",
"normalized_example_id": "ex_006671",
"source_idx": 6671,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2548,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{5}{2}",
"budget": 2038
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006671",
"normalized_example_id": "ex_006671",
"source_idx": 6671,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2548,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{5}{2}",
"budget": 2548
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006671",
"normalized_example_id": "ex_006671",
"source_idx": 6671,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2548,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{12}",
"budget": 2986
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006673",
"normalized_example_id": "ex_006673",
"source_idx": 6673,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4976,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{12}",
"budget": 3981
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006673",
"normalized_example_id": "ex_006673",
"source_idx": 6673,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4976,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{12}",
"budget": 4976
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006673",
"normalized_example_id": "ex_006673",
"source_idx": 6673,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4976,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2769
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006676",
"normalized_example_id": "ex_006676",
"source_idx": 6676,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4615,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3692
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006676",
"normalized_example_id": "ex_006676",
"source_idx": 6676,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4615,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4615
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006676",
"normalized_example_id": "ex_006676",
"source_idx": 6676,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4615,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 5682
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006678",
"normalized_example_id": "ex_006678",
"source_idx": 6678,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9470,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 7576
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006678",
"normalized_example_id": "ex_006678",
"source_idx": 6678,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9470,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 9470
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006678",
"normalized_example_id": "ex_006678",
"source_idx": 6678,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9470,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 3953
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006681",
"normalized_example_id": "ex_006681",
"source_idx": 6681,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6588,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 5270
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006681",
"normalized_example_id": "ex_006681",
"source_idx": 6681,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6588,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 6588
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006681",
"normalized_example_id": "ex_006681",
"source_idx": 6681,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6588,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8R^{3}\\sqrt{3}",
"budget": 1937
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006683",
"normalized_example_id": "ex_006683",
"source_idx": 6683,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8R^{3}\\sqrt{3}",
"budget": 2583
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006683",
"normalized_example_id": "ex_006683",
"source_idx": 6683,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8R^{3}\\sqrt{3}",
"budget": 3229
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006683",
"normalized_example_id": "ex_006683",
"source_idx": 6683,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,5,7)",
"budget": 5198
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006684",
"normalized_example_id": "ex_006684",
"source_idx": 6684,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8664,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,5,7)",
"budget": 6931
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006684",
"normalized_example_id": "ex_006684",
"source_idx": 6684,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8664,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,5,7)",
"budget": 8664
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006684",
"normalized_example_id": "ex_006684",
"source_idx": 6684,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8664,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}+\\sqrt{2},\\frac{1}{2}-\\sqrt{2},1+\\sqrt{3},1-\\sqrt{3}",
"budget": 3572
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006685",
"normalized_example_id": "ex_006685",
"source_idx": 6685,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5954,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}+\\sqrt{2},\\frac{1}{2}-\\sqrt{2},1+\\sqrt{3},1-\\sqrt{3}",
"budget": 4763
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006685",
"normalized_example_id": "ex_006685",
"source_idx": 6685,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5954,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}+\\sqrt{2},\\frac{1}{2}-\\sqrt{2},1+\\sqrt{3},1-\\sqrt{3}",
"budget": 5954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006685",
"normalized_example_id": "ex_006685",
"source_idx": 6685,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5954,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16148",
"budget": 742
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006687",
"normalized_example_id": "ex_006687",
"source_idx": 6687,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1237,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16148",
"budget": 990
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006687",
"normalized_example_id": "ex_006687",
"source_idx": 6687,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1237,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16148",
"budget": 1237
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006687",
"normalized_example_id": "ex_006687",
"source_idx": 6687,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1237,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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[3]{4 k}",
"budget": 2876
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006689",
"normalized_example_id": "ex_006689",
"source_idx": 6689,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4794,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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[3]{4 k}",
"budget": 3835
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006689",
"normalized_example_id": "ex_006689",
"source_idx": 6689,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4794,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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[3]{4 k}",
"budget": 4794
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006689",
"normalized_example_id": "ex_006689",
"source_idx": 6689,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4794,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{1009522}{2019045}",
"budget": 5832
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006690",
"normalized_example_id": "ex_006690",
"source_idx": 6690,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9720,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{1009522}{2019045}",
"budget": 7776
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006690",
"normalized_example_id": "ex_006690",
"source_idx": 6690,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9720,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{1009522}{2019045}",
"budget": 9720
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006690",
"normalized_example_id": "ex_006690",
"source_idx": 6690,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9720,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1000",
"budget": 3333
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006691",
"normalized_example_id": "ex_006691",
"source_idx": 6691,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5555,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1000",
"budget": 4444
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006691",
"normalized_example_id": "ex_006691",
"source_idx": 6691,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5555,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1000",
"budget": 5555
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006691",
"normalized_example_id": "ex_006691",
"source_idx": 6691,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5555,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3290
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006693",
"normalized_example_id": "ex_006693",
"source_idx": 6693,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5483,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4386
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006693",
"normalized_example_id": "ex_006693",
"source_idx": 6693,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5483,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5483
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006693",
"normalized_example_id": "ex_006693",
"source_idx": 6693,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5483,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{\\frac{n\\left(2 n^{2}+1\\right)}{3}}",
"budget": 2932
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006698",
"normalized_example_id": "ex_006698",
"source_idx": 6698,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4887,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{\\frac{n\\left(2 n^{2}+1\\right)}{3}}",
"budget": 3910
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006698",
"normalized_example_id": "ex_006698",
"source_idx": 6698,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4887,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{\\frac{n\\left(2 n^{2}+1\\right)}{3}}",
"budget": 4887
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006698",
"normalized_example_id": "ex_006698",
"source_idx": 6698,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4887,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 2216
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006699",
"normalized_example_id": "ex_006699",
"source_idx": 6699,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3694,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 2955
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006699",
"normalized_example_id": "ex_006699",
"source_idx": 6699,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3694,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 3694
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006699",
"normalized_example_id": "ex_006699",
"source_idx": 6699,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3694,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "61",
"budget": 5893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006701",
"normalized_example_id": "ex_006701",
"source_idx": 6701,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9821,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "61",
"budget": 7857
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006701",
"normalized_example_id": "ex_006701",
"source_idx": 6701,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9821,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "61",
"budget": 9821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006701",
"normalized_example_id": "ex_006701",
"source_idx": 6701,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9821,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{\\frac{n(2n^2+1)}{3}}",
"budget": 5104
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006705",
"normalized_example_id": "ex_006705",
"source_idx": 6705,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8507,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{\\frac{n(2n^2+1)}{3}}",
"budget": 6806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006705",
"normalized_example_id": "ex_006705",
"source_idx": 6705,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8507,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{\\frac{n(2n^2+1)}{3}}",
"budget": 8507
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006705",
"normalized_example_id": "ex_006705",
"source_idx": 6705,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8507,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "738",
"budget": 4720
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006706",
"normalized_example_id": "ex_006706",
"source_idx": 6706,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7867,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "738",
"budget": 6294
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006706",
"normalized_example_id": "ex_006706",
"source_idx": 6706,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7867,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "738",
"budget": 7867
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006706",
"normalized_example_id": "ex_006706",
"source_idx": 6706,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7867,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x-3)",
"budget": 3796
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006707",
"normalized_example_id": "ex_006707",
"source_idx": 6707,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x-3)",
"budget": 5062
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006707",
"normalized_example_id": "ex_006707",
"source_idx": 6707,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6327,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.