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": "\\frac{255}{2}",
"budget": 3972
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004061",
"normalized_example_id": "ex_004061",
"source_idx": 4061,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6620,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{255}{2}",
"budget": 5296
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004061",
"normalized_example_id": "ex_004061",
"source_idx": 4061,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6620,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{255}{2}",
"budget": 6620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004061",
"normalized_example_id": "ex_004061",
"source_idx": 4061,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6620,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,3,4,9,19,24,49,99",
"budget": 6079
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004062",
"normalized_example_id": "ex_004062",
"source_idx": 4062,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,3,4,9,19,24,49,99",
"budget": 8105
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004062",
"normalized_example_id": "ex_004062",
"source_idx": 4062,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,3,4,9,19,24,49,99",
"budget": 10131
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004062",
"normalized_example_id": "ex_004062",
"source_idx": 4062,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "M(X)=\\lambda",
"budget": 1093
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004066",
"normalized_example_id": "ex_004066",
"source_idx": 4066,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1821,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "M(X)=\\lambda",
"budget": 1457
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004066",
"normalized_example_id": "ex_004066",
"source_idx": 4066,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1821,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "M(X)=\\lambda",
"budget": 1821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004066",
"normalized_example_id": "ex_004066",
"source_idx": 4066,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1821,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{91}",
"budget": 1790
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004068",
"normalized_example_id": "ex_004068",
"source_idx": 4068,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2983,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{91}",
"budget": 2386
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004068",
"normalized_example_id": "ex_004068",
"source_idx": 4068,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2983,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{91}",
"budget": 2983
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004068",
"normalized_example_id": "ex_004068",
"source_idx": 4068,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2983,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{29}{20}",
"budget": 3515
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004071",
"normalized_example_id": "ex_004071",
"source_idx": 4071,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5859,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{29}{20}",
"budget": 4687
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004071",
"normalized_example_id": "ex_004071",
"source_idx": 4071,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5859,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{29}{20}",
"budget": 5859
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004071",
"normalized_example_id": "ex_004071",
"source_idx": 4071,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5859,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004074",
"normalized_example_id": "ex_004074",
"source_idx": 4074,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3233,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2586
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004074",
"normalized_example_id": "ex_004074",
"source_idx": 4074,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3233,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3233
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004074",
"normalized_example_id": "ex_004074",
"source_idx": 4074,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3233,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 4720
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004077",
"normalized_example_id": "ex_004077",
"source_idx": 4077,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7867,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 6294
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004077",
"normalized_example_id": "ex_004077",
"source_idx": 4077,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7867,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 7867
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004077",
"normalized_example_id": "ex_004077",
"source_idx": 4077,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7867,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4,2",
"budget": 5697
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004079",
"normalized_example_id": "ex_004079",
"source_idx": 4079,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9495,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4,2",
"budget": 7596
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004079",
"normalized_example_id": "ex_004079",
"source_idx": 4079,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9495,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4,2",
"budget": 9495
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004079",
"normalized_example_id": "ex_004079",
"source_idx": 4079,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9495,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n+1}{2}",
"budget": 2531
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004080",
"normalized_example_id": "ex_004080",
"source_idx": 4080,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n+1}{2}",
"budget": 3375
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004080",
"normalized_example_id": "ex_004080",
"source_idx": 4080,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n+1}{2}",
"budget": 4219
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004080",
"normalized_example_id": "ex_004080",
"source_idx": 4080,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1427
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004081",
"normalized_example_id": "ex_004081",
"source_idx": 4081,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2378,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1902
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004081",
"normalized_example_id": "ex_004081",
"source_idx": 4081,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2378,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2378
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004081",
"normalized_example_id": "ex_004081",
"source_idx": 4081,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2378,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3829
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004089",
"normalized_example_id": "ex_004089",
"source_idx": 4089,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6382,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 5106
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004089",
"normalized_example_id": "ex_004089",
"source_idx": 4089,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6382,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 6382
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004089",
"normalized_example_id": "ex_004089",
"source_idx": 4089,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6382,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{3}+\\ln2",
"budget": 3435
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004091",
"normalized_example_id": "ex_004091",
"source_idx": 4091,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5725,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{3}+\\ln2",
"budget": 4580
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004091",
"normalized_example_id": "ex_004091",
"source_idx": 4091,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5725,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{3}+\\ln2",
"budget": 5725
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004091",
"normalized_example_id": "ex_004091",
"source_idx": 4091,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5725,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2173
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004093",
"normalized_example_id": "ex_004093",
"source_idx": 4093,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3621,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2897
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004093",
"normalized_example_id": "ex_004093",
"source_idx": 4093,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3621,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3621
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004093",
"normalized_example_id": "ex_004093",
"source_idx": 4093,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3621,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 4457
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004094",
"normalized_example_id": "ex_004094",
"source_idx": 4094,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7428,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 5942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004094",
"normalized_example_id": "ex_004094",
"source_idx": 4094,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7428,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 7428
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004094",
"normalized_example_id": "ex_004094",
"source_idx": 4094,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7428,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "71",
"budget": 2984
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004096",
"normalized_example_id": "ex_004096",
"source_idx": 4096,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4973,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "71",
"budget": 3978
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004096",
"normalized_example_id": "ex_004096",
"source_idx": 4096,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4973,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "71",
"budget": 4973
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004096",
"normalized_example_id": "ex_004096",
"source_idx": 4096,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4973,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\varphi_{3}(x)=3x",
"budget": 1789
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004098",
"normalized_example_id": "ex_004098",
"source_idx": 4098,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2982,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\varphi_{3}(x)=3x",
"budget": 2386
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004098",
"normalized_example_id": "ex_004098",
"source_idx": 4098,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2982,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\varphi_{3}(x)=3x",
"budget": 2982
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004098",
"normalized_example_id": "ex_004098",
"source_idx": 4098,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2982,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-11,-9,-8,-6,-5,-3",
"budget": 1409
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004101",
"normalized_example_id": "ex_004101",
"source_idx": 4101,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2349,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-11,-9,-8,-6,-5,-3",
"budget": 1879
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004101",
"normalized_example_id": "ex_004101",
"source_idx": 4101,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2349,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-11,-9,-8,-6,-5,-3",
"budget": 2349
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004101",
"normalized_example_id": "ex_004101",
"source_idx": 4101,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2349,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi}{24}",
"budget": 2328
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004102",
"normalized_example_id": "ex_004102",
"source_idx": 4102,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3880,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi}{24}",
"budget": 3104
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004102",
"normalized_example_id": "ex_004102",
"source_idx": 4102,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3880,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi}{24}",
"budget": 3880
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004102",
"normalized_example_id": "ex_004102",
"source_idx": 4102,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3880,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5005
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004104",
"normalized_example_id": "ex_004104",
"source_idx": 4104,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8342,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6674
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004104",
"normalized_example_id": "ex_004104",
"source_idx": 4104,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8342,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8342
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004104",
"normalized_example_id": "ex_004104",
"source_idx": 4104,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8342,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p=3,q=2",
"budget": 2852
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004105",
"normalized_example_id": "ex_004105",
"source_idx": 4105,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4754,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p=3,q=2",
"budget": 3803
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004105",
"normalized_example_id": "ex_004105",
"source_idx": 4105,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4754,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p=3,q=2",
"budget": 4754
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004105",
"normalized_example_id": "ex_004105",
"source_idx": 4105,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4754,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2028",
"budget": 1862
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004106",
"normalized_example_id": "ex_004106",
"source_idx": 4106,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3104,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2028",
"budget": 2483
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004106",
"normalized_example_id": "ex_004106",
"source_idx": 4106,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3104,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2028",
"budget": 3104
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004106",
"normalized_example_id": "ex_004106",
"source_idx": 4106,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3104,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "108^\\circ",
"budget": 5180
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004108",
"normalized_example_id": "ex_004108",
"source_idx": 4108,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8634,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "108^\\circ",
"budget": 6907
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004108",
"normalized_example_id": "ex_004108",
"source_idx": 4108,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8634,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "108^\\circ",
"budget": 8634
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004108",
"normalized_example_id": "ex_004108",
"source_idx": 4108,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8634,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4547
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004110",
"normalized_example_id": "ex_004110",
"source_idx": 4110,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7579,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6063
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004110",
"normalized_example_id": "ex_004110",
"source_idx": 4110,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7579,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7579
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004110",
"normalized_example_id": "ex_004110",
"source_idx": 4110,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7579,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 1954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004111",
"normalized_example_id": "ex_004111",
"source_idx": 4111,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3257,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 2606
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004111",
"normalized_example_id": "ex_004111",
"source_idx": 4111,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3257,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 3257
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004111",
"normalized_example_id": "ex_004111",
"source_idx": 4111,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3257,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(k,p)=(1,1),(4,2)or(7,3)",
"budget": 2980
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004112",
"normalized_example_id": "ex_004112",
"source_idx": 4112,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4967,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(k,p)=(1,1),(4,2)or(7,3)",
"budget": 3974
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004112",
"normalized_example_id": "ex_004112",
"source_idx": 4112,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4967,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(k,p)=(1,1),(4,2)or(7,3)",
"budget": 4967
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004112",
"normalized_example_id": "ex_004112",
"source_idx": 4112,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4967,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n+1+(-1)^{n+1}}{n+2}",
"budget": 6020
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004114",
"normalized_example_id": "ex_004114",
"source_idx": 4114,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n+1+(-1)^{n+1}}{n+2}",
"budget": 8027
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004114",
"normalized_example_id": "ex_004114",
"source_idx": 4114,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n+1+(-1)^{n+1}}{n+2}",
"budget": 10034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004114",
"normalized_example_id": "ex_004114",
"source_idx": 4114,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arcsin\\cos\\arcsinx+\\arccos\\sin\\arccosx=\\frac{\\pi}{2}",
"budget": 2546
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004115",
"normalized_example_id": "ex_004115",
"source_idx": 4115,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4244,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arcsin\\cos\\arcsinx+\\arccos\\sin\\arccosx=\\frac{\\pi}{2}",
"budget": 3395
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004115",
"normalized_example_id": "ex_004115",
"source_idx": 4115,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4244,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arcsin\\cos\\arcsinx+\\arccos\\sin\\arccosx=\\frac{\\pi}{2}",
"budget": 4244
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004115",
"normalized_example_id": "ex_004115",
"source_idx": 4115,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4244,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50",
"budget": 2183
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004116",
"normalized_example_id": "ex_004116",
"source_idx": 4116,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50",
"budget": 2911
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004116",
"normalized_example_id": "ex_004116",
"source_idx": 4116,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50",
"budget": 3639
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004116",
"normalized_example_id": "ex_004116",
"source_idx": 4116,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100\\pi",
"budget": 1712
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004119",
"normalized_example_id": "ex_004119",
"source_idx": 4119,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2854,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100\\pi",
"budget": 2283
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004119",
"normalized_example_id": "ex_004119",
"source_idx": 4119,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2854,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100\\pi",
"budget": 2854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004119",
"normalized_example_id": "ex_004119",
"source_idx": 4119,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2854,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 2288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004120",
"normalized_example_id": "ex_004120",
"source_idx": 4120,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3814,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 3051
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004120",
"normalized_example_id": "ex_004120",
"source_idx": 4120,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3814,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 3814
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004120",
"normalized_example_id": "ex_004120",
"source_idx": 4120,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3814,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5204
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004121",
"normalized_example_id": "ex_004121",
"source_idx": 4121,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8674,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004121",
"normalized_example_id": "ex_004121",
"source_idx": 4121,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8674,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8674
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004121",
"normalized_example_id": "ex_004121",
"source_idx": 4121,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8674,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\text{ or } f(x)=-x",
"budget": 4397
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004123",
"normalized_example_id": "ex_004123",
"source_idx": 4123,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7329,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\text{ or } f(x)=-x",
"budget": 5863
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004123",
"normalized_example_id": "ex_004123",
"source_idx": 4123,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7329,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\text{ or } f(x)=-x",
"budget": 7329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004123",
"normalized_example_id": "ex_004123",
"source_idx": 4123,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7329,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1751
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004124",
"normalized_example_id": "ex_004124",
"source_idx": 4124,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2919,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2335
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004124",
"normalized_example_id": "ex_004124",
"source_idx": 4124,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2919,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2919
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004124",
"normalized_example_id": "ex_004124",
"source_idx": 4124,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2919,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 4339
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004125",
"normalized_example_id": "ex_004125",
"source_idx": 4125,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7232,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.