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": "6",
"budget": 1566
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001810",
"normalized_example_id": "ex_001810",
"source_idx": 1810,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1566,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x, y, z) = (3, 0, 3), (0, 1, 2), (4, 2, 5)",
"budget": 3158
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001811",
"normalized_example_id": "ex_001811",
"source_idx": 1811,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5264,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x, y, z) = (3, 0, 3), (0, 1, 2), (4, 2, 5)",
"budget": 4211
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001811",
"normalized_example_id": "ex_001811",
"source_idx": 1811,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5264,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x, y, z) = (3, 0, 3), (0, 1, 2), (4, 2, 5)",
"budget": 5264
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001811",
"normalized_example_id": "ex_001811",
"source_idx": 1811,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5264,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_1=-2,\\,x_2=3-\\sqrt{2},\\,x_3=1-2\\sqrt{2}",
"budget": 2702
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001814",
"normalized_example_id": "ex_001814",
"source_idx": 1814,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4503,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_1=-2,\\,x_2=3-\\sqrt{2},\\,x_3=1-2\\sqrt{2}",
"budget": 3602
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001814",
"normalized_example_id": "ex_001814",
"source_idx": 1814,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4503,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_1=-2,\\,x_2=3-\\sqrt{2},\\,x_3=1-2\\sqrt{2}",
"budget": 4503
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001814",
"normalized_example_id": "ex_001814",
"source_idx": 1814,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4503,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1162
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001817",
"normalized_example_id": "ex_001817",
"source_idx": 1817,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1937,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1550
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001817",
"normalized_example_id": "ex_001817",
"source_idx": 1817,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1937,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1937
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001817",
"normalized_example_id": "ex_001817",
"source_idx": 1817,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1937,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 2601
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001818",
"normalized_example_id": "ex_001818",
"source_idx": 1818,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4335,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 3468
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001818",
"normalized_example_id": "ex_001818",
"source_idx": 1818,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4335,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 4335
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001818",
"normalized_example_id": "ex_001818",
"source_idx": 1818,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4335,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "65",
"budget": 1583
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001819",
"normalized_example_id": "ex_001819",
"source_idx": 1819,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2638,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "65",
"budget": 2110
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001819",
"normalized_example_id": "ex_001819",
"source_idx": 1819,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2638,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "65",
"budget": 2638
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001819",
"normalized_example_id": "ex_001819",
"source_idx": 1819,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2638,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90",
"budget": 1759
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001821",
"normalized_example_id": "ex_001821",
"source_idx": 1821,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2932,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90",
"budget": 2346
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001821",
"normalized_example_id": "ex_001821",
"source_idx": 1821,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2932,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90",
"budget": 2932
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001821",
"normalized_example_id": "ex_001821",
"source_idx": 1821,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2932,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{1}{3}",
"budget": 4459
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001823",
"normalized_example_id": "ex_001823",
"source_idx": 1823,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7432,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{1}{3}",
"budget": 5946
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001823",
"normalized_example_id": "ex_001823",
"source_idx": 1823,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7432,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{1}{3}",
"budget": 7432
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001823",
"normalized_example_id": "ex_001823",
"source_idx": 1823,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7432,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3n^{2}-3n+1",
"budget": 3092
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001825",
"normalized_example_id": "ex_001825",
"source_idx": 1825,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5153,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3n^{2}-3n+1",
"budget": 4122
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001825",
"normalized_example_id": "ex_001825",
"source_idx": 1825,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5153,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3n^{2}-3n+1",
"budget": 5153
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001825",
"normalized_example_id": "ex_001825",
"source_idx": 1825,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5153,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "no",
"budget": 2977
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001828",
"normalized_example_id": "ex_001828",
"source_idx": 1828,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4961,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "no",
"budget": 3969
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001828",
"normalized_example_id": "ex_001828",
"source_idx": 1828,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4961,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "no",
"budget": 4961
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001828",
"normalized_example_id": "ex_001828",
"source_idx": 1828,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4961,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3296
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001829",
"normalized_example_id": "ex_001829",
"source_idx": 1829,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5493,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001829",
"normalized_example_id": "ex_001829",
"source_idx": 1829,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5493,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5493
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001829",
"normalized_example_id": "ex_001829",
"source_idx": 1829,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5493,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 4915
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001830",
"normalized_example_id": "ex_001830",
"source_idx": 1830,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8192,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 6554
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001830",
"normalized_example_id": "ex_001830",
"source_idx": 1830,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8192,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 8192
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001830",
"normalized_example_id": "ex_001830",
"source_idx": 1830,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8192,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\sqrt{3}",
"budget": 2639
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001833",
"normalized_example_id": "ex_001833",
"source_idx": 1833,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\sqrt{3}",
"budget": 3518
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001833",
"normalized_example_id": "ex_001833",
"source_idx": 1833,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\sqrt{3}",
"budget": 4398
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001833",
"normalized_example_id": "ex_001833",
"source_idx": 1833,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{45}{4045},b)\\frac{2020^{2019}}{2019!}",
"budget": 3698
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001838",
"normalized_example_id": "ex_001838",
"source_idx": 1838,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6163,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{45}{4045},b)\\frac{2020^{2019}}{2019!}",
"budget": 4930
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001838",
"normalized_example_id": "ex_001838",
"source_idx": 1838,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6163,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{45}{4045},b)\\frac{2020^{2019}}{2019!}",
"budget": 6163
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001838",
"normalized_example_id": "ex_001838",
"source_idx": 1838,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6163,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{\\sinx}\\cdot(x\\cdot\\cosx-\\frac{\\sinx}{\\cos^2x})",
"budget": 4586
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001840",
"normalized_example_id": "ex_001840",
"source_idx": 1840,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7643,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{\\sinx}\\cdot(x\\cdot\\cosx-\\frac{\\sinx}{\\cos^2x})",
"budget": 6114
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001840",
"normalized_example_id": "ex_001840",
"source_idx": 1840,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7643,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{\\sinx}\\cdot(x\\cdot\\cosx-\\frac{\\sinx}{\\cos^2x})",
"budget": 7643
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001840",
"normalized_example_id": "ex_001840",
"source_idx": 1840,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7643,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9}{92}",
"budget": 1085
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001841",
"normalized_example_id": "ex_001841",
"source_idx": 1841,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1809,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9}{92}",
"budget": 1447
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001841",
"normalized_example_id": "ex_001841",
"source_idx": 1841,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1809,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9}{92}",
"budget": 1809
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001841",
"normalized_example_id": "ex_001841",
"source_idx": 1841,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1809,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1528
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001842",
"normalized_example_id": "ex_001842",
"source_idx": 1842,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1",
"budget": 2038
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001842",
"normalized_example_id": "ex_001842",
"source_idx": 1842,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1",
"budget": 2547
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001842",
"normalized_example_id": "ex_001842",
"source_idx": 1842,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{R(5-\\sqrt{5})}{10}",
"budget": 2411
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001844",
"normalized_example_id": "ex_001844",
"source_idx": 1844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4019,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{R(5-\\sqrt{5})}{10}",
"budget": 3215
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001844",
"normalized_example_id": "ex_001844",
"source_idx": 1844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4019,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{R(5-\\sqrt{5})}{10}",
"budget": 4019
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001844",
"normalized_example_id": "ex_001844",
"source_idx": 1844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4019,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "401",
"budget": 3770
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001847",
"normalized_example_id": "ex_001847",
"source_idx": 1847,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6283,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "401",
"budget": 5026
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001847",
"normalized_example_id": "ex_001847",
"source_idx": 1847,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6283,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "401",
"budget": 6283
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001847",
"normalized_example_id": "ex_001847",
"source_idx": 1847,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6283,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:3",
"budget": 2582
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001849",
"normalized_example_id": "ex_001849",
"source_idx": 1849,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4303,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:3",
"budget": 3442
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001849",
"normalized_example_id": "ex_001849",
"source_idx": 1849,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4303,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:3",
"budget": 4303
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001849",
"normalized_example_id": "ex_001849",
"source_idx": 1849,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4303,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{1}{2}+\\frac{\\sqrt{2}}{2}",
"budget": 5531
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001852",
"normalized_example_id": "ex_001852",
"source_idx": 1852,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9218,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{1}{2}+\\frac{\\sqrt{2}}{2}",
"budget": 7374
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001852",
"normalized_example_id": "ex_001852",
"source_idx": 1852,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9218,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{1}{2}+\\frac{\\sqrt{2}}{2}",
"budget": 9218
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001852",
"normalized_example_id": "ex_001852",
"source_idx": 1852,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9218,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "87",
"budget": 1457
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001854",
"normalized_example_id": "ex_001854",
"source_idx": 1854,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "87",
"budget": 1943
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001854",
"normalized_example_id": "ex_001854",
"source_idx": 1854,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "87",
"budget": 2429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001854",
"normalized_example_id": "ex_001854",
"source_idx": 1854,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "OA=2,OB=16",
"budget": 2407
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001859",
"normalized_example_id": "ex_001859",
"source_idx": 1859,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4012,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "OA=2,OB=16",
"budget": 3210
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001859",
"normalized_example_id": "ex_001859",
"source_idx": 1859,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4012,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "OA=2,OB=16",
"budget": 4012
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001859",
"normalized_example_id": "ex_001859",
"source_idx": 1859,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4012,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 - 2",
"budget": 2491
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001861",
"normalized_example_id": "ex_001861",
"source_idx": 1861,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4151,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 - 2",
"budget": 3321
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001861",
"normalized_example_id": "ex_001861",
"source_idx": 1861,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4151,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 - 2",
"budget": 4151
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001861",
"normalized_example_id": "ex_001861",
"source_idx": 1861,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4151,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(n) = n + 2",
"budget": 4700
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001863",
"normalized_example_id": "ex_001863",
"source_idx": 1863,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7834,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(n) = n + 2",
"budget": 6267
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001863",
"normalized_example_id": "ex_001863",
"source_idx": 1863,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7834,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(n) = n + 2",
"budget": 7834
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001863",
"normalized_example_id": "ex_001863",
"source_idx": 1863,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7834,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\mapsto\\frac{1}{2}-x",
"budget": 1240
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001865",
"normalized_example_id": "ex_001865",
"source_idx": 1865,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2066,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\mapsto\\frac{1}{2}-x",
"budget": 1653
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001865",
"normalized_example_id": "ex_001865",
"source_idx": 1865,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2066,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\mapsto\\frac{1}{2}-x",
"budget": 2066
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001865",
"normalized_example_id": "ex_001865",
"source_idx": 1865,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2066,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "180",
"budget": 956
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001866",
"normalized_example_id": "ex_001866",
"source_idx": 1866,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1593,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "180",
"budget": 1274
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001866",
"normalized_example_id": "ex_001866",
"source_idx": 1866,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1593,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "180",
"budget": 1593
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001866",
"normalized_example_id": "ex_001866",
"source_idx": 1866,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1593,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1527
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001868",
"normalized_example_id": "ex_001868",
"source_idx": 1868,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2545,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2036
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001868",
"normalized_example_id": "ex_001868",
"source_idx": 1868,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2545,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2545
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001868",
"normalized_example_id": "ex_001868",
"source_idx": 1868,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2545,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "220",
"budget": 845
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001872",
"normalized_example_id": "ex_001872",
"source_idx": 1872,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1408,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "220",
"budget": 1126
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001872",
"normalized_example_id": "ex_001872",
"source_idx": 1872,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1408,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "220",
"budget": 1408
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001872",
"normalized_example_id": "ex_001872",
"source_idx": 1872,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1408,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9072",
"budget": 1992
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001876",
"normalized_example_id": "ex_001876",
"source_idx": 1876,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3320,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9072",
"budget": 2656
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001876",
"normalized_example_id": "ex_001876",
"source_idx": 1876,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3320,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9072",
"budget": 3320
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001876",
"normalized_example_id": "ex_001876",
"source_idx": 1876,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3320,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{1}{2a}",
"budget": 2899
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001880",
"normalized_example_id": "ex_001880",
"source_idx": 1880,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4832,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{1}{2a}",
"budget": 3866
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001880",
"normalized_example_id": "ex_001880",
"source_idx": 1880,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4832,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{1}{2a}",
"budget": 4832
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001880",
"normalized_example_id": "ex_001880",
"source_idx": 1880,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4832,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001881",
"normalized_example_id": "ex_001881",
"source_idx": 1881,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1565,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1252
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001881",
"normalized_example_id": "ex_001881",
"source_idx": 1881,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1565,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1565
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001881",
"normalized_example_id": "ex_001881",
"source_idx": 1881,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1565,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001882",
"normalized_example_id": "ex_001882",
"source_idx": 1882,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1424,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 1139
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001882",
"normalized_example_id": "ex_001882",
"source_idx": 1882,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1424,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 1424
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001882",
"normalized_example_id": "ex_001882",
"source_idx": 1882,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1424,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{3}",
"budget": 5807
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001883",
"normalized_example_id": "ex_001883",
"source_idx": 1883,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{3}",
"budget": 7742
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001883",
"normalized_example_id": "ex_001883",
"source_idx": 1883,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{3}",
"budget": 9678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001883",
"normalized_example_id": "ex_001883",
"source_idx": 1883,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9678,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.