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": "18",
"budget": 4140
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001884",
"normalized_example_id": "ex_001884",
"source_idx": 1884,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6900,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 5520
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001884",
"normalized_example_id": "ex_001884",
"source_idx": 1884,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6900,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 6900
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001884",
"normalized_example_id": "ex_001884",
"source_idx": 1884,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6900,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{\\circ}",
"budget": 2949
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001885",
"normalized_example_id": "ex_001885",
"source_idx": 1885,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4915,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{\\circ}",
"budget": 3932
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001885",
"normalized_example_id": "ex_001885",
"source_idx": 1885,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4915,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{\\circ}",
"budget": 4915
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001885",
"normalized_example_id": "ex_001885",
"source_idx": 1885,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4915,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90^\\circ",
"budget": 4853
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001887",
"normalized_example_id": "ex_001887",
"source_idx": 1887,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8088,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90^\\circ",
"budget": 6470
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001887",
"normalized_example_id": "ex_001887",
"source_idx": 1887,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8088,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90^\\circ",
"budget": 8088
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001887",
"normalized_example_id": "ex_001887",
"source_idx": 1887,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8088,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4000",
"budget": 2641
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001888",
"normalized_example_id": "ex_001888",
"source_idx": 1888,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4401,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4000",
"budget": 3521
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001888",
"normalized_example_id": "ex_001888",
"source_idx": 1888,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4401,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4000",
"budget": 4401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001888",
"normalized_example_id": "ex_001888",
"source_idx": 1888,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4401,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2350
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001889",
"normalized_example_id": "ex_001889",
"source_idx": 1889,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3916,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3133
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001889",
"normalized_example_id": "ex_001889",
"source_idx": 1889,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3916,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3916
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001889",
"normalized_example_id": "ex_001889",
"source_idx": 1889,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3916,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "500500",
"budget": 2264
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001891",
"normalized_example_id": "ex_001891",
"source_idx": 1891,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3774,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "500500",
"budget": 3019
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001891",
"normalized_example_id": "ex_001891",
"source_idx": 1891,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3774,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "500500",
"budget": 3774
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001891",
"normalized_example_id": "ex_001891",
"source_idx": 1891,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3774,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 1317
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001894",
"normalized_example_id": "ex_001894",
"source_idx": 1894,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2195,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 1756
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001894",
"normalized_example_id": "ex_001894",
"source_idx": 1894,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2195,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 2195
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001894",
"normalized_example_id": "ex_001894",
"source_idx": 1894,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2195,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{17+\\cos6}{4}",
"budget": 3550
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001896",
"normalized_example_id": "ex_001896",
"source_idx": 1896,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5916,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{17+\\cos6}{4}",
"budget": 4733
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001896",
"normalized_example_id": "ex_001896",
"source_idx": 1896,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5916,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{17+\\cos6}{4}",
"budget": 5916
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001896",
"normalized_example_id": "ex_001896",
"source_idx": 1896,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5916,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}-1}{2}",
"budget": 1948
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001898",
"normalized_example_id": "ex_001898",
"source_idx": 1898,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3246,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}-1}{2}",
"budget": 2597
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001898",
"normalized_example_id": "ex_001898",
"source_idx": 1898,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3246,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}-1}{2}",
"budget": 3246
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001898",
"normalized_example_id": "ex_001898",
"source_idx": 1898,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3246,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-\\sqrt{2},+\\infty)",
"budget": 3771
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001899",
"normalized_example_id": "ex_001899",
"source_idx": 1899,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6285,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-\\sqrt{2},+\\infty)",
"budget": 5028
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001899",
"normalized_example_id": "ex_001899",
"source_idx": 1899,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6285,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-\\sqrt{2},+\\infty)",
"budget": 6285
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001899",
"normalized_example_id": "ex_001899",
"source_idx": 1899,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6285,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "640",
"budget": 1388
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001900",
"normalized_example_id": "ex_001900",
"source_idx": 1900,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2314,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "640",
"budget": 1851
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001900",
"normalized_example_id": "ex_001900",
"source_idx": 1900,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2314,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "640",
"budget": 2314
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001900",
"normalized_example_id": "ex_001900",
"source_idx": 1900,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2314,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y)=\\operatorname{lcm}(x,y)",
"budget": 3238
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001902",
"normalized_example_id": "ex_001902",
"source_idx": 1902,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5397,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y)=\\operatorname{lcm}(x,y)",
"budget": 4318
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001902",
"normalized_example_id": "ex_001902",
"source_idx": 1902,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5397,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y)=\\operatorname{lcm}(x,y)",
"budget": 5397
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001902",
"normalized_example_id": "ex_001902",
"source_idx": 1902,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5397,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.2347",
"budget": 2107
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001903",
"normalized_example_id": "ex_001903",
"source_idx": 1903,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3511,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.2347",
"budget": 2809
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001903",
"normalized_example_id": "ex_001903",
"source_idx": 1903,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3511,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.2347",
"budget": 3511
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001903",
"normalized_example_id": "ex_001903",
"source_idx": 1903,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3511,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "198",
"budget": 1455
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001904",
"normalized_example_id": "ex_001904",
"source_idx": 1904,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "198",
"budget": 1940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001904",
"normalized_example_id": "ex_001904",
"source_idx": 1904,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "198",
"budget": 2425
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001904",
"normalized_example_id": "ex_001904",
"source_idx": 1904,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 2047
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001908",
"normalized_example_id": "ex_001908",
"source_idx": 1908,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 2729
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001908",
"normalized_example_id": "ex_001908",
"source_idx": 1908,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 3411
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001908",
"normalized_example_id": "ex_001908",
"source_idx": 1908,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "k = \\frac{2\\sqrt{2}}{\\pi} \\cos \\left( \\frac{\\pi}{2\\sqrt{2}} \\right)",
"budget": 3758
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001909",
"normalized_example_id": "ex_001909",
"source_idx": 1909,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6264,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "k = \\frac{2\\sqrt{2}}{\\pi} \\cos \\left( \\frac{\\pi}{2\\sqrt{2}} \\right)",
"budget": 5011
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001909",
"normalized_example_id": "ex_001909",
"source_idx": 1909,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6264,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "k = \\frac{2\\sqrt{2}}{\\pi} \\cos \\left( \\frac{\\pi}{2\\sqrt{2}} \\right)",
"budget": 6264
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001909",
"normalized_example_id": "ex_001909",
"source_idx": 1909,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6264,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "k = 2",
"budget": 5866
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001911",
"normalized_example_id": "ex_001911",
"source_idx": 1911,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9776,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "k = 2",
"budget": 7821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001911",
"normalized_example_id": "ex_001911",
"source_idx": 1911,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9776,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "k = 2",
"budget": 9776
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001911",
"normalized_example_id": "ex_001911",
"source_idx": 1911,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9776,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 2014
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001912",
"normalized_example_id": "ex_001912",
"source_idx": 1912,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3357,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 2686
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001912",
"normalized_example_id": "ex_001912",
"source_idx": 1912,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3357,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 3357
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001912",
"normalized_example_id": "ex_001912",
"source_idx": 1912,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3357,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p(x)=-(x-4)(x-1)(x+\\frac{3}{2})",
"budget": 3265
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001914",
"normalized_example_id": "ex_001914",
"source_idx": 1914,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5441,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p(x)=-(x-4)(x-1)(x+\\frac{3}{2})",
"budget": 4353
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001914",
"normalized_example_id": "ex_001914",
"source_idx": 1914,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5441,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p(x)=-(x-4)(x-1)(x+\\frac{3}{2})",
"budget": 5441
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001914",
"normalized_example_id": "ex_001914",
"source_idx": 1914,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5441,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.48",
"budget": 2840
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001915",
"normalized_example_id": "ex_001915",
"source_idx": 1915,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4733,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.48",
"budget": 3786
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001915",
"normalized_example_id": "ex_001915",
"source_idx": 1915,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4733,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.48",
"budget": 4733
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001915",
"normalized_example_id": "ex_001915",
"source_idx": 1915,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4733,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21\\sqrt{55}\\mathrm{~}^{3},84\\mathrm{~}^{2}",
"budget": 1544
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001916",
"normalized_example_id": "ex_001916",
"source_idx": 1916,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2574,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21\\sqrt{55}\\mathrm{~}^{3},84\\mathrm{~}^{2}",
"budget": 2059
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001916",
"normalized_example_id": "ex_001916",
"source_idx": 1916,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2574,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21\\sqrt{55}\\mathrm{~}^{3},84\\mathrm{~}^{2}",
"budget": 2574
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001916",
"normalized_example_id": "ex_001916",
"source_idx": 1916,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2574,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "351,702,1053,1404",
"budget": 3358
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001917",
"normalized_example_id": "ex_001917",
"source_idx": 1917,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5596,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "351,702,1053,1404",
"budget": 4477
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001917",
"normalized_example_id": "ex_001917",
"source_idx": 1917,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5596,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "351,702,1053,1404",
"budget": 5596
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001917",
"normalized_example_id": "ex_001917",
"source_idx": 1917,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5596,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1991",
"budget": 1833
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001918",
"normalized_example_id": "ex_001918",
"source_idx": 1918,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3055,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1991",
"budget": 2444
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001918",
"normalized_example_id": "ex_001918",
"source_idx": 1918,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3055,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1991",
"budget": 3055
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001918",
"normalized_example_id": "ex_001918",
"source_idx": 1918,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3055,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "31",
"budget": 4043
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001920",
"normalized_example_id": "ex_001920",
"source_idx": 1920,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6738,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "31",
"budget": 5390
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001920",
"normalized_example_id": "ex_001920",
"source_idx": 1920,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6738,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "31",
"budget": 6738
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001920",
"normalized_example_id": "ex_001920",
"source_idx": 1920,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6738,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 783
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001923",
"normalized_example_id": "ex_001923",
"source_idx": 1923,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1305,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 1044
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001923",
"normalized_example_id": "ex_001923",
"source_idx": 1923,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1305,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 1305
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001923",
"normalized_example_id": "ex_001923",
"source_idx": 1923,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1305,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3\\pi}{4}",
"budget": 1850
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001924",
"normalized_example_id": "ex_001924",
"source_idx": 1924,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3\\pi}{4}",
"budget": 2466
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001924",
"normalized_example_id": "ex_001924",
"source_idx": 1924,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3\\pi}{4}",
"budget": 3083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001924",
"normalized_example_id": "ex_001924",
"source_idx": 1924,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=-0.9524838",
"budget": 5606
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001925",
"normalized_example_id": "ex_001925",
"source_idx": 1925,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9343,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=-0.9524838",
"budget": 7474
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001925",
"normalized_example_id": "ex_001925",
"source_idx": 1925,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9343,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=-0.9524838",
"budget": 9343
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001925",
"normalized_example_id": "ex_001925",
"source_idx": 1925,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9343,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(D)}",
"budget": 3586
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001926",
"normalized_example_id": "ex_001926",
"source_idx": 1926,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5976,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(D)}",
"budget": 4781
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001926",
"normalized_example_id": "ex_001926",
"source_idx": 1926,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5976,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(D)}",
"budget": 5976
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001926",
"normalized_example_id": "ex_001926",
"source_idx": 1926,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5976,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "63\\mathrm{~}^{2}",
"budget": 2857
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001927",
"normalized_example_id": "ex_001927",
"source_idx": 1927,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4762,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "63\\mathrm{~}^{2}",
"budget": 3810
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001927",
"normalized_example_id": "ex_001927",
"source_idx": 1927,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4762,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "63\\mathrm{~}^{2}",
"budget": 4762
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001927",
"normalized_example_id": "ex_001927",
"source_idx": 1927,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4762,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3968
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001929",
"normalized_example_id": "ex_001929",
"source_idx": 1929,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5291
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001929",
"normalized_example_id": "ex_001929",
"source_idx": 1929,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6614
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001929",
"normalized_example_id": "ex_001929",
"source_idx": 1929,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2481
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001934",
"normalized_example_id": "ex_001934",
"source_idx": 1934,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4135,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3308
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001934",
"normalized_example_id": "ex_001934",
"source_idx": 1934,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4135,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4135
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001934",
"normalized_example_id": "ex_001934",
"source_idx": 1934,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4135,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 988
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001935",
"normalized_example_id": "ex_001935",
"source_idx": 1935,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1647,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 1318
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001935",
"normalized_example_id": "ex_001935",
"source_idx": 1935,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1647,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 1647
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001935",
"normalized_example_id": "ex_001935",
"source_idx": 1935,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1647,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "501",
"budget": 1711
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001937",
"normalized_example_id": "ex_001937",
"source_idx": 1937,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2851,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "501",
"budget": 2281
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001937",
"normalized_example_id": "ex_001937",
"source_idx": 1937,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2851,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "501",
"budget": 2851
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001937",
"normalized_example_id": "ex_001937",
"source_idx": 1937,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2851,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2500",
"budget": 2652
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001938",
"normalized_example_id": "ex_001938",
"source_idx": 1938,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4420,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.