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": "-2, -1, 0, 1, 2",
"budget": 4068
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002773",
"normalized_example_id": "ex_002773",
"source_idx": 2773,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4068,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2+\\sqrt{5}",
"budget": 4381
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002775",
"normalized_example_id": "ex_002775",
"source_idx": 2775,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7301,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2+\\sqrt{5}",
"budget": 5841
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002775",
"normalized_example_id": "ex_002775",
"source_idx": 2775,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7301,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2+\\sqrt{5}",
"budget": 7301
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002775",
"normalized_example_id": "ex_002775",
"source_idx": 2775,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7301,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "43",
"budget": 5379
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002779",
"normalized_example_id": "ex_002779",
"source_idx": 2779,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8965,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "43",
"budget": 7172
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002779",
"normalized_example_id": "ex_002779",
"source_idx": 2779,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8965,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "43",
"budget": 8965
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002779",
"normalized_example_id": "ex_002779",
"source_idx": 2779,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8965,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x)=x",
"budget": 1799
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002781",
"normalized_example_id": "ex_002781",
"source_idx": 2781,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2998,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x)=x",
"budget": 2398
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002781",
"normalized_example_id": "ex_002781",
"source_idx": 2781,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2998,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x)=x",
"budget": 2998
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002781",
"normalized_example_id": "ex_002781",
"source_idx": 2781,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2998,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{24}{7}",
"budget": 5929
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002782",
"normalized_example_id": "ex_002782",
"source_idx": 2782,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9881,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{24}{7}",
"budget": 7905
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002782",
"normalized_example_id": "ex_002782",
"source_idx": 2782,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9881,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{24}{7}",
"budget": 9881
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002782",
"normalized_example_id": "ex_002782",
"source_idx": 2782,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9881,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "138600",
"budget": 2110
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002783",
"normalized_example_id": "ex_002783",
"source_idx": 2783,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3516,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "138600",
"budget": 2813
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002783",
"normalized_example_id": "ex_002783",
"source_idx": 2783,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3516,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "138600",
"budget": 3516
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002783",
"normalized_example_id": "ex_002783",
"source_idx": 2783,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3516,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "is",
"budget": 4945
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002785",
"normalized_example_id": "ex_002785",
"source_idx": 2785,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8242,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "is",
"budget": 6594
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002785",
"normalized_example_id": "ex_002785",
"source_idx": 2785,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8242,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "is",
"budget": 8242
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002785",
"normalized_example_id": "ex_002785",
"source_idx": 2785,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8242,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 5032
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002787",
"normalized_example_id": "ex_002787",
"source_idx": 2787,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8386,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 6709
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002787",
"normalized_example_id": "ex_002787",
"source_idx": 2787,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8386,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 8386
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002787",
"normalized_example_id": "ex_002787",
"source_idx": 2787,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8386,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{182}{729}",
"budget": 3028
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002788",
"normalized_example_id": "ex_002788",
"source_idx": 2788,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5047,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{182}{729}",
"budget": 4038
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002788",
"normalized_example_id": "ex_002788",
"source_idx": 2788,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5047,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{182}{729}",
"budget": 5047
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002788",
"normalized_example_id": "ex_002788",
"source_idx": 2788,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5047,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2x-1)\\sin2x+\\cos2x+C",
"budget": 884
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002789",
"normalized_example_id": "ex_002789",
"source_idx": 2789,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2x-1)\\sin2x+\\cos2x+C",
"budget": 1179
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002789",
"normalized_example_id": "ex_002789",
"source_idx": 2789,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2x-1)\\sin2x+\\cos2x+C",
"budget": 1474
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002789",
"normalized_example_id": "ex_002789",
"source_idx": 2789,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-1,-1)",
"budget": 858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002794",
"normalized_example_id": "ex_002794",
"source_idx": 2794,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1430,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-1,-1)",
"budget": 1144
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002794",
"normalized_example_id": "ex_002794",
"source_idx": 2794,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1430,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-1,-1)",
"budget": 1430
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002794",
"normalized_example_id": "ex_002794",
"source_idx": 2794,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1430,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(6,7,5,3)",
"budget": 1488
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002797",
"normalized_example_id": "ex_002797",
"source_idx": 2797,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2480,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(6,7,5,3)",
"budget": 1984
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002797",
"normalized_example_id": "ex_002797",
"source_idx": 2797,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2480,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(6,7,5,3)",
"budget": 2480
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002797",
"normalized_example_id": "ex_002797",
"source_idx": 2797,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2480,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 2, 3, 6, 7, 8, 9",
"budget": 6040
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002799",
"normalized_example_id": "ex_002799",
"source_idx": 2799,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10067,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 2, 3, 6, 7, 8, 9",
"budget": 8054
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002799",
"normalized_example_id": "ex_002799",
"source_idx": 2799,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10067,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 2, 3, 6, 7, 8, 9",
"budget": 10067
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002799",
"normalized_example_id": "ex_002799",
"source_idx": 2799,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10067,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "110",
"budget": 5080
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002804",
"normalized_example_id": "ex_002804",
"source_idx": 2804,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8466,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "110",
"budget": 6773
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002804",
"normalized_example_id": "ex_002804",
"source_idx": 2804,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8466,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "110",
"budget": 8466
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002804",
"normalized_example_id": "ex_002804",
"source_idx": 2804,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8466,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34or66",
"budget": 3424
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002805",
"normalized_example_id": "ex_002805",
"source_idx": 2805,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5707,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34or66",
"budget": 4566
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002805",
"normalized_example_id": "ex_002805",
"source_idx": 2805,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5707,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34or66",
"budget": 5707
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002805",
"normalized_example_id": "ex_002805",
"source_idx": 2805,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5707,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\frac{1}{2}, y=\\frac{1}{3}",
"budget": 3581
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002809",
"normalized_example_id": "ex_002809",
"source_idx": 2809,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5968,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\frac{1}{2}, y=\\frac{1}{3}",
"budget": 4774
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002809",
"normalized_example_id": "ex_002809",
"source_idx": 2809,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5968,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\frac{1}{2}, y=\\frac{1}{3}",
"budget": 5968
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002809",
"normalized_example_id": "ex_002809",
"source_idx": 2809,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5968,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,2)",
"budget": 1337
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002812",
"normalized_example_id": "ex_002812",
"source_idx": 2812,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,2)",
"budget": 1783
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002812",
"normalized_example_id": "ex_002812",
"source_idx": 2812,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,2)",
"budget": 2229
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002812",
"normalized_example_id": "ex_002812",
"source_idx": 2812,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "72",
"budget": 3383
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002820",
"normalized_example_id": "ex_002820",
"source_idx": 2820,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "72",
"budget": 4511
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002820",
"normalized_example_id": "ex_002820",
"source_idx": 2820,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "72",
"budget": 5639
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002820",
"normalized_example_id": "ex_002820",
"source_idx": 2820,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3430",
"budget": 2741
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002822",
"normalized_example_id": "ex_002822",
"source_idx": 2822,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4569,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3430",
"budget": 3655
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002822",
"normalized_example_id": "ex_002822",
"source_idx": 2822,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4569,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3430",
"budget": 4569
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002822",
"normalized_example_id": "ex_002822",
"source_idx": 2822,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4569,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 1576
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002827",
"normalized_example_id": "ex_002827",
"source_idx": 2827,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2626,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 2101
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002827",
"normalized_example_id": "ex_002827",
"source_idx": 2827,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2626,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 2626
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002827",
"normalized_example_id": "ex_002827",
"source_idx": 2827,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2626,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x-1)^{2}+y^{2}=1",
"budget": 2634
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002829",
"normalized_example_id": "ex_002829",
"source_idx": 2829,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4390,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x-1)^{2}+y^{2}=1",
"budget": 3512
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002829",
"normalized_example_id": "ex_002829",
"source_idx": 2829,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4390,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x-1)^{2}+y^{2}=1",
"budget": 4390
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002829",
"normalized_example_id": "ex_002829",
"source_idx": 2829,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4390,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3535
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002830",
"normalized_example_id": "ex_002830",
"source_idx": 2830,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4714
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002830",
"normalized_example_id": "ex_002830",
"source_idx": 2830,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5892
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002830",
"normalized_example_id": "ex_002830",
"source_idx": 2830,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 2386
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002831",
"normalized_example_id": "ex_002831",
"source_idx": 2831,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3976,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 3181
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002831",
"normalized_example_id": "ex_002831",
"source_idx": 2831,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3976,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 3976
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002831",
"normalized_example_id": "ex_002831",
"source_idx": 2831,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3976,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1528
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002832",
"normalized_example_id": "ex_002832",
"source_idx": 2832,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2038
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002832",
"normalized_example_id": "ex_002832",
"source_idx": 2832,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2547
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002832",
"normalized_example_id": "ex_002832",
"source_idx": 2832,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y=x^{2}-4 x+3",
"budget": 2992
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002835",
"normalized_example_id": "ex_002835",
"source_idx": 2835,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4986,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y=x^{2}-4 x+3",
"budget": 3989
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002835",
"normalized_example_id": "ex_002835",
"source_idx": 2835,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4986,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y=x^{2}-4 x+3",
"budget": 4986
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002835",
"normalized_example_id": "ex_002835",
"source_idx": 2835,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4986,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 714
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002837",
"normalized_example_id": "ex_002837",
"source_idx": 2837,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1190,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 952
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002837",
"normalized_example_id": "ex_002837",
"source_idx": 2837,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1190,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1190
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002837",
"normalized_example_id": "ex_002837",
"source_idx": 2837,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1190,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2866
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002838",
"normalized_example_id": "ex_002838",
"source_idx": 2838,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4776,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002838",
"normalized_example_id": "ex_002838",
"source_idx": 2838,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4776,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4776
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002838",
"normalized_example_id": "ex_002838",
"source_idx": 2838,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4776,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "227",
"budget": 3837
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002843",
"normalized_example_id": "ex_002843",
"source_idx": 2843,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6395,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "227",
"budget": 5116
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002843",
"normalized_example_id": "ex_002843",
"source_idx": 2843,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6395,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "227",
"budget": 6395
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002843",
"normalized_example_id": "ex_002843",
"source_idx": 2843,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6395,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A",
"budget": 2476
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002844",
"normalized_example_id": "ex_002844",
"source_idx": 2844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4126,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A",
"budget": 3301
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002844",
"normalized_example_id": "ex_002844",
"source_idx": 2844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4126,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A",
"budget": 4126
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002844",
"normalized_example_id": "ex_002844",
"source_idx": 2844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4126,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 6109
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002848",
"normalized_example_id": "ex_002848",
"source_idx": 2848,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10182,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 8146
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002848",
"normalized_example_id": "ex_002848",
"source_idx": 2848,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10182,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 10182
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002848",
"normalized_example_id": "ex_002848",
"source_idx": 2848,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10182,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{15\\sqrt{2}}{2}",
"budget": 2537
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002849",
"normalized_example_id": "ex_002849",
"source_idx": 2849,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4228,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{15\\sqrt{2}}{2}",
"budget": 3382
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002849",
"normalized_example_id": "ex_002849",
"source_idx": 2849,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4228,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{15\\sqrt{2}}{2}",
"budget": 4228
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002849",
"normalized_example_id": "ex_002849",
"source_idx": 2849,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4228,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3232",
"budget": 2551
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002852",
"normalized_example_id": "ex_002852",
"source_idx": 2852,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4251,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3232",
"budget": 3401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002852",
"normalized_example_id": "ex_002852",
"source_idx": 2852,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4251,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3232",
"budget": 4251
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002852",
"normalized_example_id": "ex_002852",
"source_idx": 2852,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4251,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{7}{2}",
"budget": 3420
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002853",
"normalized_example_id": "ex_002853",
"source_idx": 2853,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5700,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{7}{2}",
"budget": 4560
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002853",
"normalized_example_id": "ex_002853",
"source_idx": 2853,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5700,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{7}{2}",
"budget": 5700
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002853",
"normalized_example_id": "ex_002853",
"source_idx": 2853,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5700,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "130",
"budget": 2691
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002855",
"normalized_example_id": "ex_002855",
"source_idx": 2855,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4485,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "130",
"budget": 3588
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002855",
"normalized_example_id": "ex_002855",
"source_idx": 2855,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4485,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "130",
"budget": 4485
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002855",
"normalized_example_id": "ex_002855",
"source_idx": 2855,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4485,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.