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": "4002",
"budget": 3681
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001632",
"normalized_example_id": "ex_001632",
"source_idx": 1632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3681,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "729",
"budget": 3422
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001633",
"normalized_example_id": "ex_001633",
"source_idx": 1633,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5704,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "729",
"budget": 4563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001633",
"normalized_example_id": "ex_001633",
"source_idx": 1633,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5704,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "729",
"budget": 5704
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001633",
"normalized_example_id": "ex_001633",
"source_idx": 1633,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5704,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 3365
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001635",
"normalized_example_id": "ex_001635",
"source_idx": 1635,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5609,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 4487
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001635",
"normalized_example_id": "ex_001635",
"source_idx": 1635,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5609,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 5609
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001635",
"normalized_example_id": "ex_001635",
"source_idx": 1635,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5609,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}}{2}",
"budget": 3496
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001637",
"normalized_example_id": "ex_001637",
"source_idx": 1637,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5826,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}}{2}",
"budget": 4661
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001637",
"normalized_example_id": "ex_001637",
"source_idx": 1637,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5826,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}}{2}",
"budget": 5826
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001637",
"normalized_example_id": "ex_001637",
"source_idx": 1637,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5826,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6990500",
"budget": 1936
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001639",
"normalized_example_id": "ex_001639",
"source_idx": 1639,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6990500",
"budget": 2582
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001639",
"normalized_example_id": "ex_001639",
"source_idx": 1639,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6990500",
"budget": 3227
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001639",
"normalized_example_id": "ex_001639",
"source_idx": 1639,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.375",
"budget": 2155
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001640",
"normalized_example_id": "ex_001640",
"source_idx": 1640,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3591,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.375",
"budget": 2873
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001640",
"normalized_example_id": "ex_001640",
"source_idx": 1640,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3591,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.375",
"budget": 3591
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001640",
"normalized_example_id": "ex_001640",
"source_idx": 1640,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3591,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(e^{2\\pi}-1)",
"budget": 898
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001642",
"normalized_example_id": "ex_001642",
"source_idx": 1642,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1496,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(e^{2\\pi}-1)",
"budget": 1197
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001642",
"normalized_example_id": "ex_001642",
"source_idx": 1642,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1496,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(e^{2\\pi}-1)",
"budget": 1496
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001642",
"normalized_example_id": "ex_001642",
"source_idx": 1642,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1496,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2014",
"budget": 1597
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001643",
"normalized_example_id": "ex_001643",
"source_idx": 1643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2661,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2014",
"budget": 2129
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001643",
"normalized_example_id": "ex_001643",
"source_idx": 1643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2661,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2014",
"budget": 2661
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001643",
"normalized_example_id": "ex_001643",
"source_idx": 1643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2661,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "42",
"budget": 6025
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001644",
"normalized_example_id": "ex_001644",
"source_idx": 1644,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10041,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "42",
"budget": 8033
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001644",
"normalized_example_id": "ex_001644",
"source_idx": 1644,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10041,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "42",
"budget": 10041
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001644",
"normalized_example_id": "ex_001644",
"source_idx": 1644,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10041,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3537",
"budget": 3455
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001647",
"normalized_example_id": "ex_001647",
"source_idx": 1647,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5759,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3537",
"budget": 4607
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001647",
"normalized_example_id": "ex_001647",
"source_idx": 1647,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5759,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3537",
"budget": 5759
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001647",
"normalized_example_id": "ex_001647",
"source_idx": 1647,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5759,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70",
"budget": 2044
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001651",
"normalized_example_id": "ex_001651",
"source_idx": 1651,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3407,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70",
"budget": 2726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001651",
"normalized_example_id": "ex_001651",
"source_idx": 1651,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3407,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70",
"budget": 3407
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001651",
"normalized_example_id": "ex_001651",
"source_idx": 1651,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3407,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,1),(4,1),(0,-2),(4,-2),(0,-3),(3,-3)",
"budget": 1774
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001652",
"normalized_example_id": "ex_001652",
"source_idx": 1652,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2957,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,1),(4,1),(0,-2),(4,-2),(0,-3),(3,-3)",
"budget": 2366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001652",
"normalized_example_id": "ex_001652",
"source_idx": 1652,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2957,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,1),(4,1),(0,-2),(4,-2),(0,-3),(3,-3)",
"budget": 2957
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001652",
"normalized_example_id": "ex_001652",
"source_idx": 1652,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2957,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "39",
"budget": 4670
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001653",
"normalized_example_id": "ex_001653",
"source_idx": 1653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7783,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "39",
"budget": 6226
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001653",
"normalized_example_id": "ex_001653",
"source_idx": 1653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7783,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "39",
"budget": 7783
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001653",
"normalized_example_id": "ex_001653",
"source_idx": 1653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7783,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "208",
"budget": 4219
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001654",
"normalized_example_id": "ex_001654",
"source_idx": 1654,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7032,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "208",
"budget": 5626
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001654",
"normalized_example_id": "ex_001654",
"source_idx": 1654,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7032,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "208",
"budget": 7032
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001654",
"normalized_example_id": "ex_001654",
"source_idx": 1654,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7032,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "E",
"budget": 1445
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001655",
"normalized_example_id": "ex_001655",
"source_idx": 1655,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2408,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "E",
"budget": 1926
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001655",
"normalized_example_id": "ex_001655",
"source_idx": 1655,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2408,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "E",
"budget": 2408
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001655",
"normalized_example_id": "ex_001655",
"source_idx": 1655,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2408,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_{1}=-1,\\quadx_{2}=-8",
"budget": 3332
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001657",
"normalized_example_id": "ex_001657",
"source_idx": 1657,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5554,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_{1}=-1,\\quadx_{2}=-8",
"budget": 4443
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001657",
"normalized_example_id": "ex_001657",
"source_idx": 1657,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5554,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_{1}=-1,\\quadx_{2}=-8",
"budget": 5554
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001657",
"normalized_example_id": "ex_001657",
"source_idx": 1657,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5554,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1660
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001661",
"normalized_example_id": "ex_001661",
"source_idx": 1661,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2767,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2214
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001661",
"normalized_example_id": "ex_001661",
"source_idx": 1661,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2767,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2767
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001661",
"normalized_example_id": "ex_001661",
"source_idx": 1661,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2767,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001662",
"normalized_example_id": "ex_001662",
"source_idx": 1662,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4630,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3704
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001662",
"normalized_example_id": "ex_001662",
"source_idx": 1662,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4630,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4630
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001662",
"normalized_example_id": "ex_001662",
"source_idx": 1662,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4630,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "160",
"budget": 3284
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001663",
"normalized_example_id": "ex_001663",
"source_idx": 1663,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "160",
"budget": 4379
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001663",
"normalized_example_id": "ex_001663",
"source_idx": 1663,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "160",
"budget": 5474
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001663",
"normalized_example_id": "ex_001663",
"source_idx": 1663,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n-2}",
"budget": 2445
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001664",
"normalized_example_id": "ex_001664",
"source_idx": 1664,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n-2}",
"budget": 3260
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001664",
"normalized_example_id": "ex_001664",
"source_idx": 1664,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n-2}",
"budget": 4075
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001664",
"normalized_example_id": "ex_001664",
"source_idx": 1664,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1420",
"budget": 5170
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001666",
"normalized_example_id": "ex_001666",
"source_idx": 1666,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8616,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1420",
"budget": 6893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001666",
"normalized_example_id": "ex_001666",
"source_idx": 1666,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8616,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1420",
"budget": 8616
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001666",
"normalized_example_id": "ex_001666",
"source_idx": 1666,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8616,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1018080",
"budget": 5972
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001667",
"normalized_example_id": "ex_001667",
"source_idx": 1667,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9953,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1018080",
"budget": 7962
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001667",
"normalized_example_id": "ex_001667",
"source_idx": 1667,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9953,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1018080",
"budget": 9953
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001667",
"normalized_example_id": "ex_001667",
"source_idx": 1667,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9953,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 2495
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001671",
"normalized_example_id": "ex_001671",
"source_idx": 1671,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 3327
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001671",
"normalized_example_id": "ex_001671",
"source_idx": 1671,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 4159
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001671",
"normalized_example_id": "ex_001671",
"source_idx": 1671,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha = 8",
"budget": 5796
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001672",
"normalized_example_id": "ex_001672",
"source_idx": 1672,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha = 8",
"budget": 7728
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001672",
"normalized_example_id": "ex_001672",
"source_idx": 1672,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha = 8",
"budget": 9660
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001672",
"normalized_example_id": "ex_001672",
"source_idx": 1672,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "73",
"budget": 2096
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001674",
"normalized_example_id": "ex_001674",
"source_idx": 1674,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3493,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "73",
"budget": 2794
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001674",
"normalized_example_id": "ex_001674",
"source_idx": 1674,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3493,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "73",
"budget": 3493
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001674",
"normalized_example_id": "ex_001674",
"source_idx": 1674,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3493,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n-1)(n-2)}{6}",
"budget": 2003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001676",
"normalized_example_id": "ex_001676",
"source_idx": 1676,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3338,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n-1)(n-2)}{6}",
"budget": 2670
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001676",
"normalized_example_id": "ex_001676",
"source_idx": 1676,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3338,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n-1)(n-2)}{6}",
"budget": 3338
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001676",
"normalized_example_id": "ex_001676",
"source_idx": 1676,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3338,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi^{3}}{3}",
"budget": 1244
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001677",
"normalized_example_id": "ex_001677",
"source_idx": 1677,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2073,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi^{3}}{3}",
"budget": 1658
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001677",
"normalized_example_id": "ex_001677",
"source_idx": 1677,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2073,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi^{3}}{3}",
"budget": 2073
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001677",
"normalized_example_id": "ex_001677",
"source_idx": 1677,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2073,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "84",
"budget": 3323
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001679",
"normalized_example_id": "ex_001679",
"source_idx": 1679,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5538,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "84",
"budget": 4430
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001679",
"normalized_example_id": "ex_001679",
"source_idx": 1679,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5538,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "84",
"budget": 5538
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001679",
"normalized_example_id": "ex_001679",
"source_idx": 1679,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5538,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14",
"budget": 1801
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001680",
"normalized_example_id": "ex_001680",
"source_idx": 1680,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14",
"budget": 2401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001680",
"normalized_example_id": "ex_001680",
"source_idx": 1680,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14",
"budget": 3001
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001680",
"normalized_example_id": "ex_001680",
"source_idx": 1680,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "positive",
"budget": 4119
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001684",
"normalized_example_id": "ex_001684",
"source_idx": 1684,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6865,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "positive",
"budget": 5492
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001684",
"normalized_example_id": "ex_001684",
"source_idx": 1684,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6865,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "positive",
"budget": 6865
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001684",
"normalized_example_id": "ex_001684",
"source_idx": 1684,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6865,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2549
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001685",
"normalized_example_id": "ex_001685",
"source_idx": 1685,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4249,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3399
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001685",
"normalized_example_id": "ex_001685",
"source_idx": 1685,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4249,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4249
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001685",
"normalized_example_id": "ex_001685",
"source_idx": 1685,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4249,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,1,1),(2,2,2),(2,3,3),(3,2,3)",
"budget": 3230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001686",
"normalized_example_id": "ex_001686",
"source_idx": 1686,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5383,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,1,1),(2,2,2),(2,3,3),(3,2,3)",
"budget": 4306
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001686",
"normalized_example_id": "ex_001686",
"source_idx": 1686,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5383,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,1,1),(2,2,2),(2,3,3),(3,2,3)",
"budget": 5383
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001686",
"normalized_example_id": "ex_001686",
"source_idx": 1686,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5383,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 5924
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001687",
"normalized_example_id": "ex_001687",
"source_idx": 1687,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9873,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 7898
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001687",
"normalized_example_id": "ex_001687",
"source_idx": 1687,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9873,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 9873
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001687",
"normalized_example_id": "ex_001687",
"source_idx": 1687,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9873,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi}{3}",
"budget": 1861
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001689",
"normalized_example_id": "ex_001689",
"source_idx": 1689,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3101,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi}{3}",
"budget": 2481
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001689",
"normalized_example_id": "ex_001689",
"source_idx": 1689,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3101,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi}{3}",
"budget": 3101
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001689",
"normalized_example_id": "ex_001689",
"source_idx": 1689,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3101,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.