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": "(3,3,4)",
"budget": 9982
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000514",
"normalized_example_id": "ex_000514",
"source_idx": 514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9982,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-1)",
"budget": 3495
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000517",
"normalized_example_id": "ex_000517",
"source_idx": 517,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5825,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-1)",
"budget": 4660
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000517",
"normalized_example_id": "ex_000517",
"source_idx": 517,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5825,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-1)",
"budget": 5825
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000517",
"normalized_example_id": "ex_000517",
"source_idx": 517,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5825,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 938
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000522",
"normalized_example_id": "ex_000522",
"source_idx": 522,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1563,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1250
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000522",
"normalized_example_id": "ex_000522",
"source_idx": 522,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1563,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000522",
"normalized_example_id": "ex_000522",
"source_idx": 522,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1563,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a_{n}=\\frac{1}{\\sqrt{5}}[(\\frac{1+\\sqrt{5}}{2})^{n}-(\\frac{1-\\sqrt{5}}{2})^{n}]",
"budget": 1580
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000527",
"normalized_example_id": "ex_000527",
"source_idx": 527,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2633,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a_{n}=\\frac{1}{\\sqrt{5}}[(\\frac{1+\\sqrt{5}}{2})^{n}-(\\frac{1-\\sqrt{5}}{2})^{n}]",
"budget": 2106
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000527",
"normalized_example_id": "ex_000527",
"source_idx": 527,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2633,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a_{n}=\\frac{1}{\\sqrt{5}}[(\\frac{1+\\sqrt{5}}{2})^{n}-(\\frac{1-\\sqrt{5}}{2})^{n}]",
"budget": 2633
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000527",
"normalized_example_id": "ex_000527",
"source_idx": 527,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2633,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2a}{\\sqrt{5}}",
"budget": 2056
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000529",
"normalized_example_id": "ex_000529",
"source_idx": 529,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3427,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2a}{\\sqrt{5}}",
"budget": 2742
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000529",
"normalized_example_id": "ex_000529",
"source_idx": 529,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3427,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2a}{\\sqrt{5}}",
"budget": 3427
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000529",
"normalized_example_id": "ex_000529",
"source_idx": 529,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3427,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30\\mathrm{~}",
"budget": 5432
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000531",
"normalized_example_id": "ex_000531",
"source_idx": 531,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9053,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30\\mathrm{~}",
"budget": 7242
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000531",
"normalized_example_id": "ex_000531",
"source_idx": 531,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9053,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30\\mathrm{~}",
"budget": 9053
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000531",
"normalized_example_id": "ex_000531",
"source_idx": 531,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9053,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "126000,105000,94500",
"budget": 978
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000533",
"normalized_example_id": "ex_000533",
"source_idx": 533,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1630,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "126000,105000,94500",
"budget": 1304
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000533",
"normalized_example_id": "ex_000533",
"source_idx": 533,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1630,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "126000,105000,94500",
"budget": 1630
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000533",
"normalized_example_id": "ex_000533",
"source_idx": 533,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1630,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "189548",
"budget": 3417
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000534",
"normalized_example_id": "ex_000534",
"source_idx": 534,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5695,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "189548",
"budget": 4556
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000534",
"normalized_example_id": "ex_000534",
"source_idx": 534,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5695,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "189548",
"budget": 5695
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000534",
"normalized_example_id": "ex_000534",
"source_idx": 534,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5695,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10,6,8",
"budget": 775
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000535",
"normalized_example_id": "ex_000535",
"source_idx": 535,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1292,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10,6,8",
"budget": 1034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000535",
"normalized_example_id": "ex_000535",
"source_idx": 535,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1292,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10,6,8",
"budget": 1292
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000535",
"normalized_example_id": "ex_000535",
"source_idx": 535,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1292,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "39",
"budget": 3061
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000537",
"normalized_example_id": "ex_000537",
"source_idx": 537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5101,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "39",
"budget": 4081
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000537",
"normalized_example_id": "ex_000537",
"source_idx": 537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5101,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "39",
"budget": 5101
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000537",
"normalized_example_id": "ex_000537",
"source_idx": 537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5101,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20000",
"budget": 2189
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000546",
"normalized_example_id": "ex_000546",
"source_idx": 546,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3649,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20000",
"budget": 2919
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000546",
"normalized_example_id": "ex_000546",
"source_idx": 546,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3649,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20000",
"budget": 3649
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000546",
"normalized_example_id": "ex_000546",
"source_idx": 546,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3649,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1562
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000548",
"normalized_example_id": "ex_000548",
"source_idx": 548,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2603,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2082
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000548",
"normalized_example_id": "ex_000548",
"source_idx": 548,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2603,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2603
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000548",
"normalized_example_id": "ex_000548",
"source_idx": 548,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2603,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 661
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000551",
"normalized_example_id": "ex_000551",
"source_idx": 551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1101,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 881
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000551",
"normalized_example_id": "ex_000551",
"source_idx": 551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1101,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1101
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000551",
"normalized_example_id": "ex_000551",
"source_idx": 551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1101,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "280",
"budget": 1679
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000555",
"normalized_example_id": "ex_000555",
"source_idx": 555,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2799,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "280",
"budget": 2239
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000555",
"normalized_example_id": "ex_000555",
"source_idx": 555,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2799,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "280",
"budget": 2799
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000555",
"normalized_example_id": "ex_000555",
"source_idx": 555,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2799,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{36}{19}\\sqrt{2}",
"budget": 3858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000557",
"normalized_example_id": "ex_000557",
"source_idx": 557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6430,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{36}{19}\\sqrt{2}",
"budget": 5144
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000557",
"normalized_example_id": "ex_000557",
"source_idx": 557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6430,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{36}{19}\\sqrt{2}",
"budget": 6430
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000557",
"normalized_example_id": "ex_000557",
"source_idx": 557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6430,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "d(n^2)",
"budget": 2449
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000558",
"normalized_example_id": "ex_000558",
"source_idx": 558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4082,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "d(n^2)",
"budget": 3266
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000558",
"normalized_example_id": "ex_000558",
"source_idx": 558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4082,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "d(n^2)",
"budget": 4082
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000558",
"normalized_example_id": "ex_000558",
"source_idx": 558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4082,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-143",
"budget": 925
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000559",
"normalized_example_id": "ex_000559",
"source_idx": 559,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1542,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-143",
"budget": 1234
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000559",
"normalized_example_id": "ex_000559",
"source_idx": 559,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1542,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-143",
"budget": 1542
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000559",
"normalized_example_id": "ex_000559",
"source_idx": 559,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1542,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(a, b, c) = (1, -1, -1), (-2, 5, 23), (-3, 5, 47)",
"budget": 3007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000560",
"normalized_example_id": "ex_000560",
"source_idx": 560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5012,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(a, b, c) = (1, -1, -1), (-2, 5, 23), (-3, 5, 47)",
"budget": 4010
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000560",
"normalized_example_id": "ex_000560",
"source_idx": 560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5012,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(a, b, c) = (1, -1, -1), (-2, 5, 23), (-3, 5, 47)",
"budget": 5012
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000560",
"normalized_example_id": "ex_000560",
"source_idx": 560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5012,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{6}{11}",
"budget": 3738
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000564",
"normalized_example_id": "ex_000564",
"source_idx": 564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6230,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{6}{11}",
"budget": 4984
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000564",
"normalized_example_id": "ex_000564",
"source_idx": 564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6230,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{6}{11}",
"budget": 6230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000564",
"normalized_example_id": "ex_000564",
"source_idx": 564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6230,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0,1,4,9,16,25",
"budget": 4814
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000566",
"normalized_example_id": "ex_000566",
"source_idx": 566,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8023,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0,1,4,9,16,25",
"budget": 6418
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000566",
"normalized_example_id": "ex_000566",
"source_idx": 566,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8023,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0,1,4,9,16,25",
"budget": 8023
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000566",
"normalized_example_id": "ex_000566",
"source_idx": 566,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8023,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 926
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000567",
"normalized_example_id": "ex_000567",
"source_idx": 567,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1543,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1234
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000567",
"normalized_example_id": "ex_000567",
"source_idx": 567,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1543,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1543
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000567",
"normalized_example_id": "ex_000567",
"source_idx": 567,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1543,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "325",
"budget": 3485
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000568",
"normalized_example_id": "ex_000568",
"source_idx": 568,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5809,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "325",
"budget": 4647
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000568",
"normalized_example_id": "ex_000568",
"source_idx": 568,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5809,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "325",
"budget": 5809
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000568",
"normalized_example_id": "ex_000568",
"source_idx": 568,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5809,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0,1)",
"budget": 5317
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000570",
"normalized_example_id": "ex_000570",
"source_idx": 570,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8862,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0,1)",
"budget": 7090
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000570",
"normalized_example_id": "ex_000570",
"source_idx": 570,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8862,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0,1)",
"budget": 8862
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000570",
"normalized_example_id": "ex_000570",
"source_idx": 570,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8862,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 3755
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000572",
"normalized_example_id": "ex_000572",
"source_idx": 572,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6259,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 5007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000572",
"normalized_example_id": "ex_000572",
"source_idx": 572,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6259,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 6259
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000572",
"normalized_example_id": "ex_000572",
"source_idx": 572,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6259,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 5397
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000573",
"normalized_example_id": "ex_000573",
"source_idx": 573,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8995,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 7196
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000573",
"normalized_example_id": "ex_000573",
"source_idx": 573,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8995,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 8995
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000573",
"normalized_example_id": "ex_000573",
"source_idx": 573,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8995,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000575",
"normalized_example_id": "ex_000575",
"source_idx": 575,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3196,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2557
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000575",
"normalized_example_id": "ex_000575",
"source_idx": 575,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3196,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3196
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000575",
"normalized_example_id": "ex_000575",
"source_idx": 575,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3196,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x)=2 n-2",
"budget": 4750
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000576",
"normalized_example_id": "ex_000576",
"source_idx": 576,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7916,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x)=2 n-2",
"budget": 6333
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000576",
"normalized_example_id": "ex_000576",
"source_idx": 576,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7916,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x)=2 n-2",
"budget": 7916
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000576",
"normalized_example_id": "ex_000576",
"source_idx": 576,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7916,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 1133
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000577",
"normalized_example_id": "ex_000577",
"source_idx": 577,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1888,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 1510
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000577",
"normalized_example_id": "ex_000577",
"source_idx": 577,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1888,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 1888
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000577",
"normalized_example_id": "ex_000577",
"source_idx": 577,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1888,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "52",
"budget": 4244
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000578",
"normalized_example_id": "ex_000578",
"source_idx": 578,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7073,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "52",
"budget": 5658
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000578",
"normalized_example_id": "ex_000578",
"source_idx": 578,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7073,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "52",
"budget": 7073
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000578",
"normalized_example_id": "ex_000578",
"source_idx": 578,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7073,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2009",
"budget": 2675
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000581",
"normalized_example_id": "ex_000581",
"source_idx": 581,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4459,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2009",
"budget": 3567
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000581",
"normalized_example_id": "ex_000581",
"source_idx": 581,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4459,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2009",
"budget": 4459
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000581",
"normalized_example_id": "ex_000581",
"source_idx": 581,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4459,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "210",
"budget": 2186
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000586",
"normalized_example_id": "ex_000586",
"source_idx": 586,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3644,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "210",
"budget": 2915
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000586",
"normalized_example_id": "ex_000586",
"source_idx": 586,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3644,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "210",
"budget": 3644
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000586",
"normalized_example_id": "ex_000586",
"source_idx": 586,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3644,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2\\pi}{3},\\frac{4\\pi}{3}}",
"budget": 2222
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000588",
"normalized_example_id": "ex_000588",
"source_idx": 588,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3703,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2\\pi}{3},\\frac{4\\pi}{3}}",
"budget": 2962
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000588",
"normalized_example_id": "ex_000588",
"source_idx": 588,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3703,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2\\pi}{3},\\frac{4\\pi}{3}}",
"budget": 3703
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000588",
"normalized_example_id": "ex_000588",
"source_idx": 588,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3703,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "75",
"budget": 4918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000591",
"normalized_example_id": "ex_000591",
"source_idx": 591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8197,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "75",
"budget": 6558
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000591",
"normalized_example_id": "ex_000591",
"source_idx": 591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8197,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "75",
"budget": 8197
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000591",
"normalized_example_id": "ex_000591",
"source_idx": 591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8197,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1989
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000595",
"normalized_example_id": "ex_000595",
"source_idx": 595,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3315,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2652
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000595",
"normalized_example_id": "ex_000595",
"source_idx": 595,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3315,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3315
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000595",
"normalized_example_id": "ex_000595",
"source_idx": 595,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3315,
"... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.