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": "n = 5",
"budget": 5287
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006021",
"normalized_example_id": "ex_006021",
"source_idx": 6021,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8812,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n = 5",
"budget": 7050
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006021",
"normalized_example_id": "ex_006021",
"source_idx": 6021,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8812,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n = 5",
"budget": 8812
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006021",
"normalized_example_id": "ex_006021",
"source_idx": 6021,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8812,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 5575
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006024",
"normalized_example_id": "ex_006024",
"source_idx": 6024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9291,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 7433
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006024",
"normalized_example_id": "ex_006024",
"source_idx": 6024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9291,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 9291
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006024",
"normalized_example_id": "ex_006024",
"source_idx": 6024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9291,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{9\\sqrt{3}+3\\sqrt{15}}{8}",
"budget": 3083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006026",
"normalized_example_id": "ex_006026",
"source_idx": 6026,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5138,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{9\\sqrt{3}+3\\sqrt{15}}{8}",
"budget": 4110
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006026",
"normalized_example_id": "ex_006026",
"source_idx": 6026,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5138,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{9\\sqrt{3}+3\\sqrt{15}}{8}",
"budget": 5138
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006026",
"normalized_example_id": "ex_006026",
"source_idx": 6026,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5138,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(\\frac{\\pi}{2};0;\\frac{\\pi}{2}),(0;\\frac{\\pi}{2};0)",
"budget": 2935
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006027",
"normalized_example_id": "ex_006027",
"source_idx": 6027,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(\\frac{\\pi}{2};0;\\frac{\\pi}{2}),(0;\\frac{\\pi}{2};0)",
"budget": 3914
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006027",
"normalized_example_id": "ex_006027",
"source_idx": 6027,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(\\frac{\\pi}{2};0;\\frac{\\pi}{2}),(0;\\frac{\\pi}{2};0)",
"budget": 4892
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006027",
"normalized_example_id": "ex_006027",
"source_idx": 6027,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{27}{8}",
"budget": 3149
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006029",
"normalized_example_id": "ex_006029",
"source_idx": 6029,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5249,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{27}{8}",
"budget": 4199
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006029",
"normalized_example_id": "ex_006029",
"source_idx": 6029,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5249,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{27}{8}",
"budget": 5249
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006029",
"normalized_example_id": "ex_006029",
"source_idx": 6029,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5249,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 1780
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006030",
"normalized_example_id": "ex_006030",
"source_idx": 6030,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2967,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 2374
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006030",
"normalized_example_id": "ex_006030",
"source_idx": 6030,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2967,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 2967
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006030",
"normalized_example_id": "ex_006030",
"source_idx": 6030,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2967,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{499}+\\frac{999}{1}",
"budget": 4799
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006031",
"normalized_example_id": "ex_006031",
"source_idx": 6031,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7999,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{499}+\\frac{999}{1}",
"budget": 6399
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006031",
"normalized_example_id": "ex_006031",
"source_idx": 6031,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7999,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{499}+\\frac{999}{1}",
"budget": 7999
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006031",
"normalized_example_id": "ex_006031",
"source_idx": 6031,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7999,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4\\pi/\\sqrt{27}",
"budget": 3244
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006032",
"normalized_example_id": "ex_006032",
"source_idx": 6032,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5406,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4\\pi/\\sqrt{27}",
"budget": 4325
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006032",
"normalized_example_id": "ex_006032",
"source_idx": 6032,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5406,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4\\pi/\\sqrt{27}",
"budget": 5406
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006032",
"normalized_example_id": "ex_006032",
"source_idx": 6032,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5406,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}}{20}",
"budget": 2181
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006033",
"normalized_example_id": "ex_006033",
"source_idx": 6033,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3635,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}}{20}",
"budget": 2908
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006033",
"normalized_example_id": "ex_006033",
"source_idx": 6033,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3635,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}}{20}",
"budget": 3635
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006033",
"normalized_example_id": "ex_006033",
"source_idx": 6033,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3635,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "33",
"budget": 3505
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006034",
"normalized_example_id": "ex_006034",
"source_idx": 6034,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5841,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "33",
"budget": 4673
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006034",
"normalized_example_id": "ex_006034",
"source_idx": 6034,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5841,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "33",
"budget": 5841
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006034",
"normalized_example_id": "ex_006034",
"source_idx": 6034,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5841,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.97",
"budget": 1272
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006036",
"normalized_example_id": "ex_006036",
"source_idx": 6036,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2120,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.97",
"budget": 1696
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006036",
"normalized_example_id": "ex_006036",
"source_idx": 6036,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2120,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.97",
"budget": 2120
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006036",
"normalized_example_id": "ex_006036",
"source_idx": 6036,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2120,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "m = 3, 9, 11, 33, 99",
"budget": 3064
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006038",
"normalized_example_id": "ex_006038",
"source_idx": 6038,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5106,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "m = 3, 9, 11, 33, 99",
"budget": 4085
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006038",
"normalized_example_id": "ex_006038",
"source_idx": 6038,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5106,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "m = 3, 9, 11, 33, 99",
"budget": 5106
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006038",
"normalized_example_id": "ex_006038",
"source_idx": 6038,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5106,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 5567
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006039",
"normalized_example_id": "ex_006039",
"source_idx": 6039,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9278,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 7422
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006039",
"normalized_example_id": "ex_006039",
"source_idx": 6039,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9278,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 9278
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006039",
"normalized_example_id": "ex_006039",
"source_idx": 6039,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9278,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "334.63",
"budget": 3623
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006044",
"normalized_example_id": "ex_006044",
"source_idx": 6044,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6038,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "334.63",
"budget": 4830
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006044",
"normalized_example_id": "ex_006044",
"source_idx": 6044,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6038,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "334.63",
"budget": 6038
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006044",
"normalized_example_id": "ex_006044",
"source_idx": 6044,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6038,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{7623}{250000}",
"budget": 2291
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006045",
"normalized_example_id": "ex_006045",
"source_idx": 6045,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3819,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{7623}{250000}",
"budget": 3055
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006045",
"normalized_example_id": "ex_006045",
"source_idx": 6045,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3819,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{7623}{250000}",
"budget": 3819
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006045",
"normalized_example_id": "ex_006045",
"source_idx": 6045,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3819,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 3083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006046",
"normalized_example_id": "ex_006046",
"source_idx": 6046,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5138,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 4110
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006046",
"normalized_example_id": "ex_006046",
"source_idx": 6046,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5138,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 5138
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006046",
"normalized_example_id": "ex_006046",
"source_idx": 6046,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5138,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "26",
"budget": 4202
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006048",
"normalized_example_id": "ex_006048",
"source_idx": 6048,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "26",
"budget": 5602
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006048",
"normalized_example_id": "ex_006048",
"source_idx": 6048,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "26",
"budget": 7003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006048",
"normalized_example_id": "ex_006048",
"source_idx": 6048,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 1883
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006051",
"normalized_example_id": "ex_006051",
"source_idx": 6051,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3138,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 2510
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006051",
"normalized_example_id": "ex_006051",
"source_idx": 6051,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3138,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 3138
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006051",
"normalized_example_id": "ex_006051",
"source_idx": 6051,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3138,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{H^{3}\\sqrt{3}}{4\\sin^{2}\\alpha}",
"budget": 3323
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006052",
"normalized_example_id": "ex_006052",
"source_idx": 6052,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5539,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{H^{3}\\sqrt{3}}{4\\sin^{2}\\alpha}",
"budget": 4431
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006052",
"normalized_example_id": "ex_006052",
"source_idx": 6052,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5539,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{H^{3}\\sqrt{3}}{4\\sin^{2}\\alpha}",
"budget": 5539
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006052",
"normalized_example_id": "ex_006052",
"source_idx": 6052,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5539,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left[-\\frac{4}{3},-\\frac{3}{4}\\right] \\cup\\left[\\frac{3}{4}, \\frac{4}{3}\\right]",
"budget": 4471
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006058",
"normalized_example_id": "ex_006058",
"source_idx": 6058,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7451,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left[-\\frac{4}{3},-\\frac{3}{4}\\right] \\cup\\left[\\frac{3}{4}, \\frac{4}{3}\\right]",
"budget": 5961
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006058",
"normalized_example_id": "ex_006058",
"source_idx": 6058,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7451,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left[-\\frac{4}{3},-\\frac{3}{4}\\right] \\cup\\left[\\frac{3}{4}, \\frac{4}{3}\\right]",
"budget": 7451
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006058",
"normalized_example_id": "ex_006058",
"source_idx": 6058,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7451,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "792",
"budget": 1029
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006059",
"normalized_example_id": "ex_006059",
"source_idx": 6059,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "792",
"budget": 1372
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006059",
"normalized_example_id": "ex_006059",
"source_idx": 6059,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "792",
"budget": 1715
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006059",
"normalized_example_id": "ex_006059",
"source_idx": 6059,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "157",
"budget": 1843
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006062",
"normalized_example_id": "ex_006062",
"source_idx": 6062,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3071,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "157",
"budget": 2457
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006062",
"normalized_example_id": "ex_006062",
"source_idx": 6062,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3071,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "157",
"budget": 3071
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006062",
"normalized_example_id": "ex_006062",
"source_idx": 6062,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3071,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2012^{26}",
"budget": 989
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006066",
"normalized_example_id": "ex_006066",
"source_idx": 6066,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1648,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2012^{26}",
"budget": 1318
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006066",
"normalized_example_id": "ex_006066",
"source_idx": 6066,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1648,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2012^{26}",
"budget": 1648
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006066",
"normalized_example_id": "ex_006066",
"source_idx": 6066,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1648,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6600",
"budget": 1624
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006067",
"normalized_example_id": "ex_006067",
"source_idx": 6067,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2706,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6600",
"budget": 2165
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006067",
"normalized_example_id": "ex_006067",
"source_idx": 6067,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2706,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6600",
"budget": 2706
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006067",
"normalized_example_id": "ex_006067",
"source_idx": 6067,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2706,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "R = \\beta^{-\\frac{1}{\\alpha}}",
"budget": 3133
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006068",
"normalized_example_id": "ex_006068",
"source_idx": 6068,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "R = \\beta^{-\\frac{1}{\\alpha}}",
"budget": 4177
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006068",
"normalized_example_id": "ex_006068",
"source_idx": 6068,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "R = \\beta^{-\\frac{1}{\\alpha}}",
"budget": 5221
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006068",
"normalized_example_id": "ex_006068",
"source_idx": 6068,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "682",
"budget": 4465
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006072",
"normalized_example_id": "ex_006072",
"source_idx": 6072,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7442,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "682",
"budget": 5954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006072",
"normalized_example_id": "ex_006072",
"source_idx": 6072,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7442,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "682",
"budget": 7442
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006072",
"normalized_example_id": "ex_006072",
"source_idx": 6072,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7442,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "55",
"budget": 1311
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006073",
"normalized_example_id": "ex_006073",
"source_idx": 6073,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2185,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "55",
"budget": 1748
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006073",
"normalized_example_id": "ex_006073",
"source_idx": 6073,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2185,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "55",
"budget": 2185
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006073",
"normalized_example_id": "ex_006073",
"source_idx": 6073,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2185,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{4} + \\frac{1}{2} \\ln 2",
"budget": 3508
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006074",
"normalized_example_id": "ex_006074",
"source_idx": 6074,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5846,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{4} + \\frac{1}{2} \\ln 2",
"budget": 4677
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006074",
"normalized_example_id": "ex_006074",
"source_idx": 6074,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5846,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{4} + \\frac{1}{2} \\ln 2",
"budget": 5846
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006074",
"normalized_example_id": "ex_006074",
"source_idx": 6074,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5846,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3892
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006075",
"normalized_example_id": "ex_006075",
"source_idx": 6075,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6487,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5190
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006075",
"normalized_example_id": "ex_006075",
"source_idx": 6075,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6487,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6487
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006075",
"normalized_example_id": "ex_006075",
"source_idx": 6075,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6487,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1944",
"budget": 1990
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006076",
"normalized_example_id": "ex_006076",
"source_idx": 6076,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1944",
"budget": 2654
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006076",
"normalized_example_id": "ex_006076",
"source_idx": 6076,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1944",
"budget": 3317
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006076",
"normalized_example_id": "ex_006076",
"source_idx": 6076,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{4}",
"budget": 4820
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006077",
"normalized_example_id": "ex_006077",
"source_idx": 6077,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{4}",
"budget": 6427
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006077",
"normalized_example_id": "ex_006077",
"source_idx": 6077,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{4}",
"budget": 8034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006077",
"normalized_example_id": "ex_006077",
"source_idx": 6077,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 758
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006079",
"normalized_example_id": "ex_006079",
"source_idx": 6079,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1264,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 1011
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006079",
"normalized_example_id": "ex_006079",
"source_idx": 6079,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1264,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 1264
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006079",
"normalized_example_id": "ex_006079",
"source_idx": 6079,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1264,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23",
"budget": 1715
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006085",
"normalized_example_id": "ex_006085",
"source_idx": 6085,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2859,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23",
"budget": 2287
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006085",
"normalized_example_id": "ex_006085",
"source_idx": 6085,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2859,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23",
"budget": 2859
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006085",
"normalized_example_id": "ex_006085",
"source_idx": 6085,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2859,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3:5",
"budget": 1801
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006089",
"normalized_example_id": "ex_006089",
"source_idx": 6089,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3001,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.