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": "24",
"budget": 1942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004476",
"normalized_example_id": "ex_004476",
"source_idx": 4476,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3237,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 2590
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004476",
"normalized_example_id": "ex_004476",
"source_idx": 4476,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3237,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 3237
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004476",
"normalized_example_id": "ex_004476",
"source_idx": 4476,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3237,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6+\\frac{2\\sqrt{17}}{3}+\\frac{16\\sqrt{2}}{3}\\mathrm{~}",
"budget": 5511
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004477",
"normalized_example_id": "ex_004477",
"source_idx": 4477,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9185,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6+\\frac{2\\sqrt{17}}{3}+\\frac{16\\sqrt{2}}{3}\\mathrm{~}",
"budget": 7348
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004477",
"normalized_example_id": "ex_004477",
"source_idx": 4477,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9185,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6+\\frac{2\\sqrt{17}}{3}+\\frac{16\\sqrt{2}}{3}\\mathrm{~}",
"budget": 9185
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004477",
"normalized_example_id": "ex_004477",
"source_idx": 4477,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9185,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2886
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004479",
"normalized_example_id": "ex_004479",
"source_idx": 4479,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4810,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3848
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004479",
"normalized_example_id": "ex_004479",
"source_idx": 4479,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4810,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4810
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004479",
"normalized_example_id": "ex_004479",
"source_idx": 4479,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4810,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3494
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004481",
"normalized_example_id": "ex_004481",
"source_idx": 4481,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5824,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4659
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004481",
"normalized_example_id": "ex_004481",
"source_idx": 4481,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5824,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5824
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004481",
"normalized_example_id": "ex_004481",
"source_idx": 4481,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5824,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,3,5,7,13",
"budget": 6067
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004482",
"normalized_example_id": "ex_004482",
"source_idx": 4482,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10111,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,3,5,7,13",
"budget": 8089
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004482",
"normalized_example_id": "ex_004482",
"source_idx": 4482,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10111,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,3,5,7,13",
"budget": 10111
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004482",
"normalized_example_id": "ex_004482",
"source_idx": 4482,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10111,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{x^{3}}{3}+x+4\\cdot\\ln|x+3|+2\\cdot\\ln|x-1|-3\\cdot\\ln|x|+C",
"budget": 1455
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004484",
"normalized_example_id": "ex_004484",
"source_idx": 4484,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{x^{3}}{3}+x+4\\cdot\\ln|x+3|+2\\cdot\\ln|x-1|-3\\cdot\\ln|x|+C",
"budget": 1940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004484",
"normalized_example_id": "ex_004484",
"source_idx": 4484,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{x^{3}}{3}+x+4\\cdot\\ln|x+3|+2\\cdot\\ln|x-1|-3\\cdot\\ln|x|+C",
"budget": 2425
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004484",
"normalized_example_id": "ex_004484",
"source_idx": 4484,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17",
"budget": 1750
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004487",
"normalized_example_id": "ex_004487",
"source_idx": 4487,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2917,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17",
"budget": 2334
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004487",
"normalized_example_id": "ex_004487",
"source_idx": 4487,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2917,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17",
"budget": 2917
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004487",
"normalized_example_id": "ex_004487",
"source_idx": 4487,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2917,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "125",
"budget": 1877
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004489",
"normalized_example_id": "ex_004489",
"source_idx": 4489,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3129,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "125",
"budget": 2503
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004489",
"normalized_example_id": "ex_004489",
"source_idx": 4489,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3129,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "125",
"budget": 3129
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004489",
"normalized_example_id": "ex_004489",
"source_idx": 4489,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3129,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23",
"budget": 3230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004490",
"normalized_example_id": "ex_004490",
"source_idx": 4490,
"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": "23",
"budget": 4306
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004490",
"normalized_example_id": "ex_004490",
"source_idx": 4490,
"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": "23",
"budget": 5383
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004490",
"normalized_example_id": "ex_004490",
"source_idx": 4490,
"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": "f(x) = 0",
"budget": 1337
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004491",
"normalized_example_id": "ex_004491",
"source_idx": 4491,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2228,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = 0",
"budget": 1782
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004491",
"normalized_example_id": "ex_004491",
"source_idx": 4491,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2228,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = 0",
"budget": 2228
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004491",
"normalized_example_id": "ex_004491",
"source_idx": 4491,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2228,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2n-3",
"budget": 4346
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004492",
"normalized_example_id": "ex_004492",
"source_idx": 4492,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7243,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2n-3",
"budget": 5794
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004492",
"normalized_example_id": "ex_004492",
"source_idx": 4492,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7243,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2n-3",
"budget": 7243
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004492",
"normalized_example_id": "ex_004492",
"source_idx": 4492,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7243,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "35",
"budget": 4228
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004493",
"normalized_example_id": "ex_004493",
"source_idx": 4493,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7047,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "35",
"budget": 5638
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004493",
"normalized_example_id": "ex_004493",
"source_idx": 4493,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7047,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "35",
"budget": 7047
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004493",
"normalized_example_id": "ex_004493",
"source_idx": 4493,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7047,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 2577
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004494",
"normalized_example_id": "ex_004494",
"source_idx": 4494,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4295,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 3436
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004494",
"normalized_example_id": "ex_004494",
"source_idx": 4494,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4295,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 4295
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004494",
"normalized_example_id": "ex_004494",
"source_idx": 4494,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4295,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 2684
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004495",
"normalized_example_id": "ex_004495",
"source_idx": 4495,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 3579
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004495",
"normalized_example_id": "ex_004495",
"source_idx": 4495,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 4474
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004495",
"normalized_example_id": "ex_004495",
"source_idx": 4495,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1614
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004496",
"normalized_example_id": "ex_004496",
"source_idx": 4496,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2152
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004496",
"normalized_example_id": "ex_004496",
"source_idx": 4496,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2690
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004496",
"normalized_example_id": "ex_004496",
"source_idx": 4496,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "265",
"budget": 1327
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004497",
"normalized_example_id": "ex_004497",
"source_idx": 4497,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2212,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "265",
"budget": 1770
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004497",
"normalized_example_id": "ex_004497",
"source_idx": 4497,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2212,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "265",
"budget": 2212
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004497",
"normalized_example_id": "ex_004497",
"source_idx": 4497,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2212,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12504",
"budget": 2742
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004498",
"normalized_example_id": "ex_004498",
"source_idx": 4498,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4570,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12504",
"budget": 3656
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004498",
"normalized_example_id": "ex_004498",
"source_idx": 4498,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4570,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12504",
"budget": 4570
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004498",
"normalized_example_id": "ex_004498",
"source_idx": 4498,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4570,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4852
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004502",
"normalized_example_id": "ex_004502",
"source_idx": 4502,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8087,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6470
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004502",
"normalized_example_id": "ex_004502",
"source_idx": 4502,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8087,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8087
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004502",
"normalized_example_id": "ex_004502",
"source_idx": 4502,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8087,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 4238
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004505",
"normalized_example_id": "ex_004505",
"source_idx": 4505,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7064,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 5651
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004505",
"normalized_example_id": "ex_004505",
"source_idx": 4505,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7064,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 7064
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004505",
"normalized_example_id": "ex_004505",
"source_idx": 4505,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7064,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3094
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004512",
"normalized_example_id": "ex_004512",
"source_idx": 4512,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5157,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4126
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004512",
"normalized_example_id": "ex_004512",
"source_idx": 4512,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5157,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5157
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004512",
"normalized_example_id": "ex_004512",
"source_idx": 4512,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5157,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n^2 + n + 1",
"budget": 1646
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004514",
"normalized_example_id": "ex_004514",
"source_idx": 4514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2744,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n^2 + n + 1",
"budget": 2195
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004514",
"normalized_example_id": "ex_004514",
"source_idx": 4514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2744,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n^2 + n + 1",
"budget": 2744
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004514",
"normalized_example_id": "ex_004514",
"source_idx": 4514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2744,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3330
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004515",
"normalized_example_id": "ex_004515",
"source_idx": 4515,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5550,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4440
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004515",
"normalized_example_id": "ex_004515",
"source_idx": 4515,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5550,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5550
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004515",
"normalized_example_id": "ex_004515",
"source_idx": 4515,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5550,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19,29,39,49,59,69,79,89,99",
"budget": 4007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004518",
"normalized_example_id": "ex_004518",
"source_idx": 4518,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19,29,39,49,59,69,79,89,99",
"budget": 5342
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004518",
"normalized_example_id": "ex_004518",
"source_idx": 4518,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19,29,39,49,59,69,79,89,99",
"budget": 6678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004518",
"normalized_example_id": "ex_004518",
"source_idx": 4518,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19",
"budget": 3954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004519",
"normalized_example_id": "ex_004519",
"source_idx": 4519,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6590,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19",
"budget": 5272
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004519",
"normalized_example_id": "ex_004519",
"source_idx": 4519,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6590,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19",
"budget": 6590
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004519",
"normalized_example_id": "ex_004519",
"source_idx": 4519,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6590,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "29",
"budget": 923
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004520",
"normalized_example_id": "ex_004520",
"source_idx": 4520,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1539,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "29",
"budget": 1231
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004520",
"normalized_example_id": "ex_004520",
"source_idx": 4520,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1539,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "29",
"budget": 1539
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004520",
"normalized_example_id": "ex_004520",
"source_idx": 4520,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1539,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{x^{2}}",
"budget": 2195
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004521",
"normalized_example_id": "ex_004521",
"source_idx": 4521,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3659,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{x^{2}}",
"budget": 2927
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004521",
"normalized_example_id": "ex_004521",
"source_idx": 4521,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3659,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{x^{2}}",
"budget": 3659
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004521",
"normalized_example_id": "ex_004521",
"source_idx": 4521,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3659,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "192",
"budget": 4196
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004522",
"normalized_example_id": "ex_004522",
"source_idx": 4522,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6994,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "192",
"budget": 5595
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004522",
"normalized_example_id": "ex_004522",
"source_idx": 4522,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6994,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "192",
"budget": 6994
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004522",
"normalized_example_id": "ex_004522",
"source_idx": 4522,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6994,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=-4x=1",
"budget": 1563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004523",
"normalized_example_id": "ex_004523",
"source_idx": 4523,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2605,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=-4x=1",
"budget": 2084
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004523",
"normalized_example_id": "ex_004523",
"source_idx": 4523,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2605,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=-4x=1",
"budget": 2605
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004523",
"normalized_example_id": "ex_004523",
"source_idx": 4523,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2605,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 3901
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004526",
"normalized_example_id": "ex_004526",
"source_idx": 4526,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6501,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 5201
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004526",
"normalized_example_id": "ex_004526",
"source_idx": 4526,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6501,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 6501
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004526",
"normalized_example_id": "ex_004526",
"source_idx": 4526,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6501,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\overline{AC}=32\\mathrm{~},\\overline{BC}=24\\mathrm{~}",
"budget": 1923
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004528",
"normalized_example_id": "ex_004528",
"source_idx": 4528,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3205,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\overline{AC}=32\\mathrm{~},\\overline{BC}=24\\mathrm{~}",
"budget": 2564
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004528",
"normalized_example_id": "ex_004528",
"source_idx": 4528,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3205,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\overline{AC}=32\\mathrm{~},\\overline{BC}=24\\mathrm{~}",
"budget": 3205
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004528",
"normalized_example_id": "ex_004528",
"source_idx": 4528,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3205,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1997",
"budget": 4235
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004529",
"normalized_example_id": "ex_004529",
"source_idx": 4529,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7059,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1997",
"budget": 5647
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004529",
"normalized_example_id": "ex_004529",
"source_idx": 4529,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7059,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1997",
"budget": 7059
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004529",
"normalized_example_id": "ex_004529",
"source_idx": 4529,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7059,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{24}(n-1) n(n+1)(3 n+2)",
"budget": 3040
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004531",
"normalized_example_id": "ex_004531",
"source_idx": 4531,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5067,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{24}(n-1) n(n+1)(3 n+2)",
"budget": 4054
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004531",
"normalized_example_id": "ex_004531",
"source_idx": 4531,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5067,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{24}(n-1) n(n+1)(3 n+2)",
"budget": 5067
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004531",
"normalized_example_id": "ex_004531",
"source_idx": 4531,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5067,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 1364
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004533",
"normalized_example_id": "ex_004533",
"source_idx": 4533,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2273,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 1818
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004533",
"normalized_example_id": "ex_004533",
"source_idx": 4533,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2273,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 2273
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004533",
"normalized_example_id": "ex_004533",
"source_idx": 4533,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2273,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 5124
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004536",
"normalized_example_id": "ex_004536",
"source_idx": 4536,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8540,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.