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": "1,3,11,33",
"budget": 5759
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005726",
"normalized_example_id": "ex_005726",
"source_idx": 5726,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7199,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,3,11,33",
"budget": 7199
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005726",
"normalized_example_id": "ex_005726",
"source_idx": 5726,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7199,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 4114
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005729",
"normalized_example_id": "ex_005729",
"source_idx": 5729,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6856,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 5485
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005729",
"normalized_example_id": "ex_005729",
"source_idx": 5729,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6856,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 6856
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005729",
"normalized_example_id": "ex_005729",
"source_idx": 5729,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6856,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 1435
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005730",
"normalized_example_id": "ex_005730",
"source_idx": 5730,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2391,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 1913
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005730",
"normalized_example_id": "ex_005730",
"source_idx": 5730,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2391,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 2391
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005730",
"normalized_example_id": "ex_005730",
"source_idx": 5730,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2391,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y)=(0,1),(0,-1)",
"budget": 4004
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005732",
"normalized_example_id": "ex_005732",
"source_idx": 5732,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6673,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y)=(0,1),(0,-1)",
"budget": 5338
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005732",
"normalized_example_id": "ex_005732",
"source_idx": 5732,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6673,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y)=(0,1),(0,-1)",
"budget": 6673
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005732",
"normalized_example_id": "ex_005732",
"source_idx": 5732,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6673,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45^{\\circ}",
"budget": 2831
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005733",
"normalized_example_id": "ex_005733",
"source_idx": 5733,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4719,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45^{\\circ}",
"budget": 3775
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005733",
"normalized_example_id": "ex_005733",
"source_idx": 5733,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4719,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45^{\\circ}",
"budget": 4719
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005733",
"normalized_example_id": "ex_005733",
"source_idx": 5733,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4719,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;1)",
"budget": 1851
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005734",
"normalized_example_id": "ex_005734",
"source_idx": 5734,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3085,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;1)",
"budget": 2468
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005734",
"normalized_example_id": "ex_005734",
"source_idx": 5734,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3085,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;1)",
"budget": 3085
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005734",
"normalized_example_id": "ex_005734",
"source_idx": 5734,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3085,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,\\frac{1}{2}",
"budget": 2410
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005735",
"normalized_example_id": "ex_005735",
"source_idx": 5735,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4016,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,\\frac{1}{2}",
"budget": 3213
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005735",
"normalized_example_id": "ex_005735",
"source_idx": 5735,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4016,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,\\frac{1}{2}",
"budget": 4016
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005735",
"normalized_example_id": "ex_005735",
"source_idx": 5735,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4016,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{130}{759}",
"budget": 3238
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005739",
"normalized_example_id": "ex_005739",
"source_idx": 5739,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5397,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{130}{759}",
"budget": 4318
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005739",
"normalized_example_id": "ex_005739",
"source_idx": 5739,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5397,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{130}{759}",
"budget": 5397
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005739",
"normalized_example_id": "ex_005739",
"source_idx": 5739,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5397,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 3774
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005741",
"normalized_example_id": "ex_005741",
"source_idx": 5741,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6290,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 5032
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005741",
"normalized_example_id": "ex_005741",
"source_idx": 5741,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6290,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 6290
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005741",
"normalized_example_id": "ex_005741",
"source_idx": 5741,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6290,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1102
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005744",
"normalized_example_id": "ex_005744",
"source_idx": 5744,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1836,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1469
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005744",
"normalized_example_id": "ex_005744",
"source_idx": 5744,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1836,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1836
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005744",
"normalized_example_id": "ex_005744",
"source_idx": 5744,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1836,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}",
"budget": 3821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005745",
"normalized_example_id": "ex_005745",
"source_idx": 5745,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6369,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}",
"budget": 5095
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005745",
"normalized_example_id": "ex_005745",
"source_idx": 5745,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6369,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}",
"budget": 6369
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005745",
"normalized_example_id": "ex_005745",
"source_idx": 5745,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6369,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30,60,90",
"budget": 3795
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005746",
"normalized_example_id": "ex_005746",
"source_idx": 5746,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6325,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30,60,90",
"budget": 5060
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005746",
"normalized_example_id": "ex_005746",
"source_idx": 5746,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6325,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30,60,90",
"budget": 6325
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005746",
"normalized_example_id": "ex_005746",
"source_idx": 5746,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6325,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "87",
"budget": 1360
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005747",
"normalized_example_id": "ex_005747",
"source_idx": 5747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2267,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "87",
"budget": 1814
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005747",
"normalized_example_id": "ex_005747",
"source_idx": 5747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2267,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "87",
"budget": 2267
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005747",
"normalized_example_id": "ex_005747",
"source_idx": 5747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2267,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\pi/12,5\\pi/12",
"budget": 2265
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005748",
"normalized_example_id": "ex_005748",
"source_idx": 5748,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3775,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\pi/12,5\\pi/12",
"budget": 3020
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005748",
"normalized_example_id": "ex_005748",
"source_idx": 5748,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3775,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\pi/12,5\\pi/12",
"budget": 3775
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005748",
"normalized_example_id": "ex_005748",
"source_idx": 5748,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3775,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "u_{n}=2-\\frac{2}{3}(-1)^{n}-\\frac{1}{3}2^{n}",
"budget": 1427
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005751",
"normalized_example_id": "ex_005751",
"source_idx": 5751,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2379,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "u_{n}=2-\\frac{2}{3}(-1)^{n}-\\frac{1}{3}2^{n}",
"budget": 1903
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005751",
"normalized_example_id": "ex_005751",
"source_idx": 5751,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2379,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "u_{n}=2-\\frac{2}{3}(-1)^{n}-\\frac{1}{3}2^{n}",
"budget": 2379
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005751",
"normalized_example_id": "ex_005751",
"source_idx": 5751,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2379,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3275
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005754",
"normalized_example_id": "ex_005754",
"source_idx": 5754,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5459,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4367
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005754",
"normalized_example_id": "ex_005754",
"source_idx": 5754,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5459,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5459
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005754",
"normalized_example_id": "ex_005754",
"source_idx": 5754,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5459,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "221",
"budget": 1158
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005755",
"normalized_example_id": "ex_005755",
"source_idx": 5755,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "221",
"budget": 1544
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005755",
"normalized_example_id": "ex_005755",
"source_idx": 5755,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "221",
"budget": 1930
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005755",
"normalized_example_id": "ex_005755",
"source_idx": 5755,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "889",
"budget": 1343
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005757",
"normalized_example_id": "ex_005757",
"source_idx": 5757,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2239,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "889",
"budget": 1791
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005757",
"normalized_example_id": "ex_005757",
"source_idx": 5757,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2239,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "889",
"budget": 2239
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005757",
"normalized_example_id": "ex_005757",
"source_idx": 5757,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2239,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.5",
"budget": 2818
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005758",
"normalized_example_id": "ex_005758",
"source_idx": 5758,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4697,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.5",
"budget": 3758
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005758",
"normalized_example_id": "ex_005758",
"source_idx": 5758,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4697,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.5",
"budget": 4697
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005758",
"normalized_example_id": "ex_005758",
"source_idx": 5758,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4697,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "864",
"budget": 2288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005759",
"normalized_example_id": "ex_005759",
"source_idx": 5759,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3813,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "864",
"budget": 3050
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005759",
"normalized_example_id": "ex_005759",
"source_idx": 5759,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3813,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "864",
"budget": 3813
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005759",
"normalized_example_id": "ex_005759",
"source_idx": 5759,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3813,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6710,6712,6713",
"budget": 3998
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005763",
"normalized_example_id": "ex_005763",
"source_idx": 5763,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6664,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6710,6712,6713",
"budget": 5331
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005763",
"normalized_example_id": "ex_005763",
"source_idx": 5763,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6664,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6710,6712,6713",
"budget": 6664
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005763",
"normalized_example_id": "ex_005763",
"source_idx": 5763,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6664,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_n = n^2",
"budget": 2644
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005764",
"normalized_example_id": "ex_005764",
"source_idx": 5764,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4406,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_n = n^2",
"budget": 3525
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005764",
"normalized_example_id": "ex_005764",
"source_idx": 5764,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4406,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_n = n^2",
"budget": 4406
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005764",
"normalized_example_id": "ex_005764",
"source_idx": 5764,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4406,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6490716149",
"budget": 3098
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005765",
"normalized_example_id": "ex_005765",
"source_idx": 5765,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5163,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6490716149",
"budget": 4130
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005765",
"normalized_example_id": "ex_005765",
"source_idx": 5765,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5163,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6490716149",
"budget": 5163
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005765",
"normalized_example_id": "ex_005765",
"source_idx": 5765,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5163,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7744",
"budget": 5079
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005768",
"normalized_example_id": "ex_005768",
"source_idx": 5768,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8465,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7744",
"budget": 6772
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005768",
"normalized_example_id": "ex_005768",
"source_idx": 5768,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8465,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7744",
"budget": 8465
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005768",
"normalized_example_id": "ex_005768",
"source_idx": 5768,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8465,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2089
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005769",
"normalized_example_id": "ex_005769",
"source_idx": 5769,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3481,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2785
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005769",
"normalized_example_id": "ex_005769",
"source_idx": 5769,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3481,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3481
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005769",
"normalized_example_id": "ex_005769",
"source_idx": 5769,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3481,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "375",
"budget": 1268
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005770",
"normalized_example_id": "ex_005770",
"source_idx": 5770,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2114,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "375",
"budget": 1691
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005770",
"normalized_example_id": "ex_005770",
"source_idx": 5770,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2114,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "375",
"budget": 2114
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005770",
"normalized_example_id": "ex_005770",
"source_idx": 5770,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2114,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5.2",
"budget": 1903
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005773",
"normalized_example_id": "ex_005773",
"source_idx": 5773,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3172,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5.2",
"budget": 2538
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005773",
"normalized_example_id": "ex_005773",
"source_idx": 5773,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3172,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5.2",
"budget": 3172
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005773",
"normalized_example_id": "ex_005773",
"source_idx": 5773,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3172,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{55}{216}",
"budget": 3211
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005775",
"normalized_example_id": "ex_005775",
"source_idx": 5775,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5352,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{55}{216}",
"budget": 4282
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005775",
"normalized_example_id": "ex_005775",
"source_idx": 5775,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5352,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{55}{216}",
"budget": 5352
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005775",
"normalized_example_id": "ex_005775",
"source_idx": 5775,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5352,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20071",
"budget": 860
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005777",
"normalized_example_id": "ex_005777",
"source_idx": 5777,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1433,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20071",
"budget": 1146
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005777",
"normalized_example_id": "ex_005777",
"source_idx": 5777,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1433,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20071",
"budget": 1433
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005777",
"normalized_example_id": "ex_005777",
"source_idx": 5777,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1433,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0<x+y \\leqslant \\sqrt[3]{4} a",
"budget": 4459
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005778",
"normalized_example_id": "ex_005778",
"source_idx": 5778,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7431,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0<x+y \\leqslant \\sqrt[3]{4} a",
"budget": 5945
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005778",
"normalized_example_id": "ex_005778",
"source_idx": 5778,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7431,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0<x+y \\leqslant \\sqrt[3]{4} a",
"budget": 7431
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005778",
"normalized_example_id": "ex_005778",
"source_idx": 5778,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7431,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 1020
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005779",
"normalized_example_id": "ex_005779",
"source_idx": 5779,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1700,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 1360
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005779",
"normalized_example_id": "ex_005779",
"source_idx": 5779,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1700,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 1700
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005779",
"normalized_example_id": "ex_005779",
"source_idx": 5779,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1700,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1or3",
"budget": 3875
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005780",
"normalized_example_id": "ex_005780",
"source_idx": 5780,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6459,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1or3",
"budget": 5167
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005780",
"normalized_example_id": "ex_005780",
"source_idx": 5780,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6459,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1or3",
"budget": 6459
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005780",
"normalized_example_id": "ex_005780",
"source_idx": 5780,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6459,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-\\frac{33}{4}",
"budget": 2257
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005783",
"normalized_example_id": "ex_005783",
"source_idx": 5783,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3762,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-\\frac{33}{4}",
"budget": 3010
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005783",
"normalized_example_id": "ex_005783",
"source_idx": 5783,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3762,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-\\frac{33}{4}",
"budget": 3762
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005783",
"normalized_example_id": "ex_005783",
"source_idx": 5783,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3762,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{p-1}{4}",
"budget": 2511
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005784",
"normalized_example_id": "ex_005784",
"source_idx": 5784,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4185,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{p-1}{4}",
"budget": 3348
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005784",
"normalized_example_id": "ex_005784",
"source_idx": 5784,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4185,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.