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": "120",
"budget": 6832
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004536",
"normalized_example_id": "ex_004536",
"source_idx": 4536,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8540,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8540
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004536",
"normalized_example_id": "ex_004536",
"source_idx": 4536,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8540,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}{13},\\frac{9}{26},-\\frac{18}{13}",
"budget": 1351
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004537",
"normalized_example_id": "ex_004537",
"source_idx": 4537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2251,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}{13},\\frac{9}{26},-\\frac{18}{13}",
"budget": 1801
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004537",
"normalized_example_id": "ex_004537",
"source_idx": 4537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2251,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}{13},\\frac{9}{26},-\\frac{18}{13}",
"budget": 2251
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004537",
"normalized_example_id": "ex_004537",
"source_idx": 4537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2251,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "629",
"budget": 5027
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004539",
"normalized_example_id": "ex_004539",
"source_idx": 4539,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8378,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "629",
"budget": 6702
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004539",
"normalized_example_id": "ex_004539",
"source_idx": 4539,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8378,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "629",
"budget": 8378
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004539",
"normalized_example_id": "ex_004539",
"source_idx": 4539,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8378,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2n-1",
"budget": 3410
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004542",
"normalized_example_id": "ex_004542",
"source_idx": 4542,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5684,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2n-1",
"budget": 4547
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004542",
"normalized_example_id": "ex_004542",
"source_idx": 4542,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5684,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2n-1",
"budget": 5684
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004542",
"normalized_example_id": "ex_004542",
"source_idx": 4542,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5684,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,3,4,5,7,9,12,17",
"budget": 1408
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004543",
"normalized_example_id": "ex_004543",
"source_idx": 4543,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2346,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,3,4,5,7,9,12,17",
"budget": 1877
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004543",
"normalized_example_id": "ex_004543",
"source_idx": 4543,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2346,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,3,4,5,7,9,12,17",
"budget": 2346
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004543",
"normalized_example_id": "ex_004543",
"source_idx": 4543,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2346,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.97",
"budget": 1862
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004545",
"normalized_example_id": "ex_004545",
"source_idx": 4545,
"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": "0.97",
"budget": 2483
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004545",
"normalized_example_id": "ex_004545",
"source_idx": 4545,
"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": "0.97",
"budget": 3104
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004545",
"normalized_example_id": "ex_004545",
"source_idx": 4545,
"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": "p=5,q=3,r=19",
"budget": 2475
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004546",
"normalized_example_id": "ex_004546",
"source_idx": 4546,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4125,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=5,q=3,r=19",
"budget": 3300
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004546",
"normalized_example_id": "ex_004546",
"source_idx": 4546,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4125,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=5,q=3,r=19",
"budget": 4125
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004546",
"normalized_example_id": "ex_004546",
"source_idx": 4546,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4125,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "22",
"budget": 3118
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004548",
"normalized_example_id": "ex_004548",
"source_idx": 4548,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5197,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "22",
"budget": 4158
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004548",
"normalized_example_id": "ex_004548",
"source_idx": 4548,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5197,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "22",
"budget": 5197
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004548",
"normalized_example_id": "ex_004548",
"source_idx": 4548,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5197,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1217
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004549",
"normalized_example_id": "ex_004549",
"source_idx": 4549,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2029,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1623
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004549",
"normalized_example_id": "ex_004549",
"source_idx": 4549,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2029,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2029
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004549",
"normalized_example_id": "ex_004549",
"source_idx": 4549,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2029,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11-6\\sqrt{2}}{4}",
"budget": 3512
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004552",
"normalized_example_id": "ex_004552",
"source_idx": 4552,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5854,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11-6\\sqrt{2}}{4}",
"budget": 4683
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004552",
"normalized_example_id": "ex_004552",
"source_idx": 4552,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5854,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11-6\\sqrt{2}}{4}",
"budget": 5854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004552",
"normalized_example_id": "ex_004552",
"source_idx": 4552,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5854,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4925
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004554",
"normalized_example_id": "ex_004554",
"source_idx": 4554,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8208,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6566
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004554",
"normalized_example_id": "ex_004554",
"source_idx": 4554,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8208,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8208
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004554",
"normalized_example_id": "ex_004554",
"source_idx": 4554,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8208,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "428",
"budget": 3542
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004556",
"normalized_example_id": "ex_004556",
"source_idx": 4556,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5903,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "428",
"budget": 4722
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004556",
"normalized_example_id": "ex_004556",
"source_idx": 4556,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5903,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "428",
"budget": 5903
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004556",
"normalized_example_id": "ex_004556",
"source_idx": 4556,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5903,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "181",
"budget": 1592
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004557",
"normalized_example_id": "ex_004557",
"source_idx": 4557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2653,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "181",
"budget": 2122
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004557",
"normalized_example_id": "ex_004557",
"source_idx": 4557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2653,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "181",
"budget": 2653
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004557",
"normalized_example_id": "ex_004557",
"source_idx": 4557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2653,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "334",
"budget": 1172
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004559",
"normalized_example_id": "ex_004559",
"source_idx": 4559,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1954,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "334",
"budget": 1563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004559",
"normalized_example_id": "ex_004559",
"source_idx": 4559,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1954,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "334",
"budget": 1954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004559",
"normalized_example_id": "ex_004559",
"source_idx": 4559,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1954,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 2554
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004560",
"normalized_example_id": "ex_004560",
"source_idx": 4560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4257,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 3406
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004560",
"normalized_example_id": "ex_004560",
"source_idx": 4560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4257,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 4257
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004560",
"normalized_example_id": "ex_004560",
"source_idx": 4560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4257,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8}{15}",
"budget": 3056
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004561",
"normalized_example_id": "ex_004561",
"source_idx": 4561,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5093,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8}{15}",
"budget": 4074
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004561",
"normalized_example_id": "ex_004561",
"source_idx": 4561,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5093,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8}{15}",
"budget": 5093
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004561",
"normalized_example_id": "ex_004561",
"source_idx": 4561,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5093,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2730",
"budget": 5713
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004563",
"normalized_example_id": "ex_004563",
"source_idx": 4563,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9522,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2730",
"budget": 7618
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004563",
"normalized_example_id": "ex_004563",
"source_idx": 4563,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9522,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2730",
"budget": 9522
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004563",
"normalized_example_id": "ex_004563",
"source_idx": 4563,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9522,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3287
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004565",
"normalized_example_id": "ex_004565",
"source_idx": 4565,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5478,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4382
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004565",
"normalized_example_id": "ex_004565",
"source_idx": 4565,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5478,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5478
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004565",
"normalized_example_id": "ex_004565",
"source_idx": 4565,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5478,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{16}{5}",
"budget": 2755
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004566",
"normalized_example_id": "ex_004566",
"source_idx": 4566,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4592,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{16}{5}",
"budget": 3674
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004566",
"normalized_example_id": "ex_004566",
"source_idx": 4566,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4592,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{16}{5}",
"budget": 4592
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004566",
"normalized_example_id": "ex_004566",
"source_idx": 4566,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4592,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5625",
"budget": 1886
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004567",
"normalized_example_id": "ex_004567",
"source_idx": 4567,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3144,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5625",
"budget": 2515
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004567",
"normalized_example_id": "ex_004567",
"source_idx": 4567,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3144,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5625",
"budget": 3144
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004567",
"normalized_example_id": "ex_004567",
"source_idx": 4567,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3144,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3}{2}",
"budget": 4131
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004569",
"normalized_example_id": "ex_004569",
"source_idx": 4569,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6885,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3}{2}",
"budget": 5508
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004569",
"normalized_example_id": "ex_004569",
"source_idx": 4569,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6885,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3}{2}",
"budget": 6885
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004569",
"normalized_example_id": "ex_004569",
"source_idx": 4569,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6885,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 1890
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004572",
"normalized_example_id": "ex_004572",
"source_idx": 4572,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3150,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 2520
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004572",
"normalized_example_id": "ex_004572",
"source_idx": 4572,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3150,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 3150
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004572",
"normalized_example_id": "ex_004572",
"source_idx": 4572,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3150,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70950",
"budget": 1445
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004573",
"normalized_example_id": "ex_004573",
"source_idx": 4573,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2409,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70950",
"budget": 1927
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004573",
"normalized_example_id": "ex_004573",
"source_idx": 4573,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2409,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70950",
"budget": 2409
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004573",
"normalized_example_id": "ex_004573",
"source_idx": 4573,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2409,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{273}}{9}",
"budget": 3257
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004574",
"normalized_example_id": "ex_004574",
"source_idx": 4574,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{273}}{9}",
"budget": 4343
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004574",
"normalized_example_id": "ex_004574",
"source_idx": 4574,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{273}}{9}",
"budget": 5429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004574",
"normalized_example_id": "ex_004574",
"source_idx": 4574,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2683
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004575",
"normalized_example_id": "ex_004575",
"source_idx": 4575,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3578
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004575",
"normalized_example_id": "ex_004575",
"source_idx": 4575,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4472
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004575",
"normalized_example_id": "ex_004575",
"source_idx": 4575,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3\\sqrt{3}}{4}R^{2}",
"budget": 2243
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004577",
"normalized_example_id": "ex_004577",
"source_idx": 4577,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3739,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3\\sqrt{3}}{4}R^{2}",
"budget": 2991
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004577",
"normalized_example_id": "ex_004577",
"source_idx": 4577,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3739,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3\\sqrt{3}}{4}R^{2}",
"budget": 3739
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004577",
"normalized_example_id": "ex_004577",
"source_idx": 4577,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3739,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2}-1",
"budget": 714
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004579",
"normalized_example_id": "ex_004579",
"source_idx": 4579,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1190,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{2}-1",
"budget": 952
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004579",
"normalized_example_id": "ex_004579",
"source_idx": 4579,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1190,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{2}-1",
"budget": 1190
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004579",
"normalized_example_id": "ex_004579",
"source_idx": 4579,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1190,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{4}{35}",
"budget": 2552
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004580",
"normalized_example_id": "ex_004580",
"source_idx": 4580,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4254,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{35}",
"budget": 3403
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004580",
"normalized_example_id": "ex_004580",
"source_idx": 4580,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4254,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{35}",
"budget": 4254
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004580",
"normalized_example_id": "ex_004580",
"source_idx": 4580,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4254,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2-\\sqrt{2}",
"budget": 2509
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004582",
"normalized_example_id": "ex_004582",
"source_idx": 4582,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4181,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2-\\sqrt{2}",
"budget": 3345
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004582",
"normalized_example_id": "ex_004582",
"source_idx": 4582,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4181,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2-\\sqrt{2}",
"budget": 4181
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004582",
"normalized_example_id": "ex_004582",
"source_idx": 4582,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4181,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1042
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004583",
"normalized_example_id": "ex_004583",
"source_idx": 4583,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1736,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1389
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004583",
"normalized_example_id": "ex_004583",
"source_idx": 4583,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1736,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1736
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004583",
"normalized_example_id": "ex_004583",
"source_idx": 4583,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1736,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004584",
"normalized_example_id": "ex_004584",
"source_idx": 4584,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1369,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1095
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004584",
"normalized_example_id": "ex_004584",
"source_idx": 4584,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1369,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1369
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004584",
"normalized_example_id": "ex_004584",
"source_idx": 4584,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1369,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1400
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004587",
"normalized_example_id": "ex_004587",
"source_idx": 4587,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2334,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1867
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004587",
"normalized_example_id": "ex_004587",
"source_idx": 4587,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2334,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2334
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004587",
"normalized_example_id": "ex_004587",
"source_idx": 4587,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2334,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 1361
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004589",
"normalized_example_id": "ex_004589",
"source_idx": 4589,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2268,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 1814
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004589",
"normalized_example_id": "ex_004589",
"source_idx": 4589,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2268,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 2268
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004589",
"normalized_example_id": "ex_004589",
"source_idx": 4589,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2268,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 2873
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004591",
"normalized_example_id": "ex_004591",
"source_idx": 4591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4788,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 3830
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004591",
"normalized_example_id": "ex_004591",
"source_idx": 4591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4788,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.