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": "p=3 \\text{ or } 7",
"budget": 2179
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001507",
"normalized_example_id": "ex_001507",
"source_idx": 1507,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3631,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=3 \\text{ or } 7",
"budget": 2905
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001507",
"normalized_example_id": "ex_001507",
"source_idx": 1507,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3631,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=3 \\text{ or } 7",
"budget": 3631
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001507",
"normalized_example_id": "ex_001507",
"source_idx": 1507,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3631,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;0)\\cup(\\frac{1}{2};3)",
"budget": 3414
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001510",
"normalized_example_id": "ex_001510",
"source_idx": 1510,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;0)\\cup(\\frac{1}{2};3)",
"budget": 4552
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001510",
"normalized_example_id": "ex_001510",
"source_idx": 1510,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;0)\\cup(\\frac{1}{2};3)",
"budget": 5690
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001510",
"normalized_example_id": "ex_001510",
"source_idx": 1510,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 1071
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001512",
"normalized_example_id": "ex_001512",
"source_idx": 1512,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 1428
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001512",
"normalized_example_id": "ex_001512",
"source_idx": 1512,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 1785
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001512",
"normalized_example_id": "ex_001512",
"source_idx": 1512,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "306",
"budget": 3590
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001514",
"normalized_example_id": "ex_001514",
"source_idx": 1514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5983,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "306",
"budget": 4786
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001514",
"normalized_example_id": "ex_001514",
"source_idx": 1514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5983,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "306",
"budget": 5983
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001514",
"normalized_example_id": "ex_001514",
"source_idx": 1514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5983,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2 + \\sqrt{5}}{6}",
"budget": 5436
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001516",
"normalized_example_id": "ex_001516",
"source_idx": 1516,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9060,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2 + \\sqrt{5}}{6}",
"budget": 7248
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001516",
"normalized_example_id": "ex_001516",
"source_idx": 1516,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9060,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2 + \\sqrt{5}}{6}",
"budget": 9060
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001516",
"normalized_example_id": "ex_001516",
"source_idx": 1516,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9060,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\left(\\frac{a^{2}+1}{2 a}\\right)^{2}",
"budget": 5918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001517",
"normalized_example_id": "ex_001517",
"source_idx": 1517,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9863,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\left(\\frac{a^{2}+1}{2 a}\\right)^{2}",
"budget": 7890
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001517",
"normalized_example_id": "ex_001517",
"source_idx": 1517,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9863,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\left(\\frac{a^{2}+1}{2 a}\\right)^{2}",
"budget": 9863
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001517",
"normalized_example_id": "ex_001517",
"source_idx": 1517,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9863,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 968
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001518",
"normalized_example_id": "ex_001518",
"source_idx": 1518,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1291
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001518",
"normalized_example_id": "ex_001518",
"source_idx": 1518,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1614
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001518",
"normalized_example_id": "ex_001518",
"source_idx": 1518,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\geqslant\\frac{5+\\sqrt{61}}{2}",
"budget": 2563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001521",
"normalized_example_id": "ex_001521",
"source_idx": 1521,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4272,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\geqslant\\frac{5+\\sqrt{61}}{2}",
"budget": 3418
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001521",
"normalized_example_id": "ex_001521",
"source_idx": 1521,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4272,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\geqslant\\frac{5+\\sqrt{61}}{2}",
"budget": 4272
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001521",
"normalized_example_id": "ex_001521",
"source_idx": 1521,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4272,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;-2",
"budget": 2172
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001524",
"normalized_example_id": "ex_001524",
"source_idx": 1524,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3620,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;-2",
"budget": 2896
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001524",
"normalized_example_id": "ex_001524",
"source_idx": 1524,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3620,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;-2",
"budget": 3620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001524",
"normalized_example_id": "ex_001524",
"source_idx": 1524,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3620,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 1444
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001531",
"normalized_example_id": "ex_001531",
"source_idx": 1531,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2406,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 1925
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001531",
"normalized_example_id": "ex_001531",
"source_idx": 1531,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2406,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 2406
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001531",
"normalized_example_id": "ex_001531",
"source_idx": 1531,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2406,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 1184
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001532",
"normalized_example_id": "ex_001532",
"source_idx": 1532,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1974,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 1579
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001532",
"normalized_example_id": "ex_001532",
"source_idx": 1532,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1974,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 1974
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001532",
"normalized_example_id": "ex_001532",
"source_idx": 1532,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1974,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e^4",
"budget": 2301
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001534",
"normalized_example_id": "ex_001534",
"source_idx": 1534,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3835,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e^4",
"budget": 3068
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001534",
"normalized_example_id": "ex_001534",
"source_idx": 1534,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3835,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e^4",
"budget": 3835
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001534",
"normalized_example_id": "ex_001534",
"source_idx": 1534,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3835,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "576",
"budget": 3195
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001537",
"normalized_example_id": "ex_001537",
"source_idx": 1537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5325,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "576",
"budget": 4260
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001537",
"normalized_example_id": "ex_001537",
"source_idx": 1537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5325,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "576",
"budget": 5325
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001537",
"normalized_example_id": "ex_001537",
"source_idx": 1537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5325,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{37}{60}",
"budget": 1766
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001539",
"normalized_example_id": "ex_001539",
"source_idx": 1539,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2944,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{37}{60}",
"budget": 2355
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001539",
"normalized_example_id": "ex_001539",
"source_idx": 1539,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2944,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{37}{60}",
"budget": 2944
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001539",
"normalized_example_id": "ex_001539",
"source_idx": 1539,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2944,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,3",
"budget": 1119
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001541",
"normalized_example_id": "ex_001541",
"source_idx": 1541,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1865,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,3",
"budget": 1492
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001541",
"normalized_example_id": "ex_001541",
"source_idx": 1541,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1865,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,3",
"budget": 1865
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001541",
"normalized_example_id": "ex_001541",
"source_idx": 1541,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1865,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 2361
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001544",
"normalized_example_id": "ex_001544",
"source_idx": 1544,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3935,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 3148
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001544",
"normalized_example_id": "ex_001544",
"source_idx": 1544,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3935,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 3935
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001544",
"normalized_example_id": "ex_001544",
"source_idx": 1544,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3935,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "210",
"budget": 4380
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001545",
"normalized_example_id": "ex_001545",
"source_idx": 1545,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7300,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "210",
"budget": 5840
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001545",
"normalized_example_id": "ex_001545",
"source_idx": 1545,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7300,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "210",
"budget": 7300
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001545",
"normalized_example_id": "ex_001545",
"source_idx": 1545,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7300,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,q)=(3,2)",
"budget": 2642
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001548",
"normalized_example_id": "ex_001548",
"source_idx": 1548,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4404,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,q)=(3,2)",
"budget": 3523
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001548",
"normalized_example_id": "ex_001548",
"source_idx": 1548,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4404,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,q)=(3,2)",
"budget": 4404
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001548",
"normalized_example_id": "ex_001548",
"source_idx": 1548,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4404,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4910
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001551",
"normalized_example_id": "ex_001551",
"source_idx": 1551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8184,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 6547
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001551",
"normalized_example_id": "ex_001551",
"source_idx": 1551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8184,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 8184
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001551",
"normalized_example_id": "ex_001551",
"source_idx": 1551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8184,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{4 \\sqrt{3}}{9}",
"budget": 2612
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001552",
"normalized_example_id": "ex_001552",
"source_idx": 1552,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4353,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{4 \\sqrt{3}}{9}",
"budget": 3482
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001552",
"normalized_example_id": "ex_001552",
"source_idx": 1552,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4353,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{4 \\sqrt{3}}{9}",
"budget": 4353
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001552",
"normalized_example_id": "ex_001552",
"source_idx": 1552,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4353,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 2484
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001553",
"normalized_example_id": "ex_001553",
"source_idx": 1553,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4140,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 3312
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001553",
"normalized_example_id": "ex_001553",
"source_idx": 1553,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4140,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 4140
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001553",
"normalized_example_id": "ex_001553",
"source_idx": 1553,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4140,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{n}{2n-1}",
"budget": 1596
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001554",
"normalized_example_id": "ex_001554",
"source_idx": 1554,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{n}{2n-1}",
"budget": 2128
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001554",
"normalized_example_id": "ex_001554",
"source_idx": 1554,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{n}{2n-1}",
"budget": 2660
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001554",
"normalized_example_id": "ex_001554",
"source_idx": 1554,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x)=\\frac{1}{1-x-x^{2}}",
"budget": 860
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001556",
"normalized_example_id": "ex_001556",
"source_idx": 1556,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1434,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x)=\\frac{1}{1-x-x^{2}}",
"budget": 1147
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001556",
"normalized_example_id": "ex_001556",
"source_idx": 1556,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1434,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x)=\\frac{1}{1-x-x^{2}}",
"budget": 1434
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001556",
"normalized_example_id": "ex_001556",
"source_idx": 1556,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1434,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 773
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001557",
"normalized_example_id": "ex_001557",
"source_idx": 1557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1289,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 1031
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001557",
"normalized_example_id": "ex_001557",
"source_idx": 1557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1289,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 1289
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001557",
"normalized_example_id": "ex_001557",
"source_idx": 1557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1289,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "49",
"budget": 1772
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001558",
"normalized_example_id": "ex_001558",
"source_idx": 1558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2953,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "49",
"budget": 2362
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001558",
"normalized_example_id": "ex_001558",
"source_idx": 1558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2953,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "49",
"budget": 2953
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001558",
"normalized_example_id": "ex_001558",
"source_idx": 1558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2953,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\text{Area of the convex hull of } P_1, P_2, \\ldots, P_n",
"budget": 5102
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001560",
"normalized_example_id": "ex_001560",
"source_idx": 1560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8504,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\text{Area of the convex hull of } P_1, P_2, \\ldots, P_n",
"budget": 6803
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001560",
"normalized_example_id": "ex_001560",
"source_idx": 1560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8504,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\text{Area of the convex hull of } P_1, P_2, \\ldots, P_n",
"budget": 8504
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001560",
"normalized_example_id": "ex_001560",
"source_idx": 1560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8504,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2687
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001561",
"normalized_example_id": "ex_001561",
"source_idx": 1561,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4478,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3582
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001561",
"normalized_example_id": "ex_001561",
"source_idx": 1561,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4478,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4478
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001561",
"normalized_example_id": "ex_001561",
"source_idx": 1561,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4478,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11,12,14,16,17",
"budget": 3013
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001564",
"normalized_example_id": "ex_001564",
"source_idx": 1564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11,12,14,16,17",
"budget": 4018
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001564",
"normalized_example_id": "ex_001564",
"source_idx": 1564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11,12,14,16,17",
"budget": 5022
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001564",
"normalized_example_id": "ex_001564",
"source_idx": 1564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 1928
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001566",
"normalized_example_id": "ex_001566",
"source_idx": 1566,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3213,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 2570
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001566",
"normalized_example_id": "ex_001566",
"source_idx": 1566,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3213,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 3213
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001566",
"normalized_example_id": "ex_001566",
"source_idx": 1566,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3213,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "175",
"budget": 1039
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001567",
"normalized_example_id": "ex_001567",
"source_idx": 1567,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1731,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "175",
"budget": 1385
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001567",
"normalized_example_id": "ex_001567",
"source_idx": 1567,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1731,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "175",
"budget": 1731
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001567",
"normalized_example_id": "ex_001567",
"source_idx": 1567,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1731,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001570",
"normalized_example_id": "ex_001570",
"source_idx": 1570,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2876,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2301
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001570",
"normalized_example_id": "ex_001570",
"source_idx": 1570,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2876,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2876
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001570",
"normalized_example_id": "ex_001570",
"source_idx": 1570,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2876,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 3606
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001571",
"normalized_example_id": "ex_001571",
"source_idx": 1571,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6010,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 4808
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001571",
"normalized_example_id": "ex_001571",
"source_idx": 1571,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6010,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 6010
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001571",
"normalized_example_id": "ex_001571",
"source_idx": 1571,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6010,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "802",
"budget": 3979
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001574",
"normalized_example_id": "ex_001574",
"source_idx": 1574,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6631,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "802",
"budget": 5305
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001574",
"normalized_example_id": "ex_001574",
"source_idx": 1574,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6631,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "802",
"budget": 6631
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001574",
"normalized_example_id": "ex_001574",
"source_idx": 1574,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6631,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\left(1-\\frac{\\sqrt{2}}{2}\\right) a",
"budget": 800
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001578",
"normalized_example_id": "ex_001578",
"source_idx": 1578,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1334,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.