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": "30",
"budget": 3022
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005492",
"normalized_example_id": "ex_005492",
"source_idx": 5492,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5037,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4030
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005492",
"normalized_example_id": "ex_005492",
"source_idx": 5492,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5037,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5037
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005492",
"normalized_example_id": "ex_005492",
"source_idx": 5492,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5037,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "450",
"budget": 2057
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005494",
"normalized_example_id": "ex_005494",
"source_idx": 5494,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3428,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "450",
"budget": 2742
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005494",
"normalized_example_id": "ex_005494",
"source_idx": 5494,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3428,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "450",
"budget": 3428
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005494",
"normalized_example_id": "ex_005494",
"source_idx": 5494,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3428,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1244
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005496",
"normalized_example_id": "ex_005496",
"source_idx": 5496,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2074,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1659
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005496",
"normalized_example_id": "ex_005496",
"source_idx": 5496,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2074,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2074
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005496",
"normalized_example_id": "ex_005496",
"source_idx": 5496,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2074,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\pi}{3}",
"budget": 3937
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005497",
"normalized_example_id": "ex_005497",
"source_idx": 5497,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6561,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\pi}{3}",
"budget": 5249
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005497",
"normalized_example_id": "ex_005497",
"source_idx": 5497,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6561,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\pi}{3}",
"budget": 6561
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005497",
"normalized_example_id": "ex_005497",
"source_idx": 5497,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6561,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "792",
"budget": 4550
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005498",
"normalized_example_id": "ex_005498",
"source_idx": 5498,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7584,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "792",
"budget": 6067
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005498",
"normalized_example_id": "ex_005498",
"source_idx": 5498,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7584,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "792",
"budget": 7584
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005498",
"normalized_example_id": "ex_005498",
"source_idx": 5498,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7584,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3754
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005499",
"normalized_example_id": "ex_005499",
"source_idx": 5499,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6257,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5006
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005499",
"normalized_example_id": "ex_005499",
"source_idx": 5499,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6257,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6257
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005499",
"normalized_example_id": "ex_005499",
"source_idx": 5499,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6257,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "843",
"budget": 5258
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005502",
"normalized_example_id": "ex_005502",
"source_idx": 5502,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8763,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "843",
"budget": 7010
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005502",
"normalized_example_id": "ex_005502",
"source_idx": 5502,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8763,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "843",
"budget": 8763
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005502",
"normalized_example_id": "ex_005502",
"source_idx": 5502,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8763,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "62",
"budget": 1125
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005503",
"normalized_example_id": "ex_005503",
"source_idx": 5503,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1875,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "62",
"budget": 1500
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005503",
"normalized_example_id": "ex_005503",
"source_idx": 5503,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1875,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "62",
"budget": 1875
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005503",
"normalized_example_id": "ex_005503",
"source_idx": 5503,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1875,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3958
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005504",
"normalized_example_id": "ex_005504",
"source_idx": 5504,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5278
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005504",
"normalized_example_id": "ex_005504",
"source_idx": 5504,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6597
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005504",
"normalized_example_id": "ex_005504",
"source_idx": 5504,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\cos^{2}2x+2\\cos2x-1=0",
"budget": 2339
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005507",
"normalized_example_id": "ex_005507",
"source_idx": 5507,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3899,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\cos^{2}2x+2\\cos2x-1=0",
"budget": 3119
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005507",
"normalized_example_id": "ex_005507",
"source_idx": 5507,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3899,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\cos^{2}2x+2\\cos2x-1=0",
"budget": 3899
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005507",
"normalized_example_id": "ex_005507",
"source_idx": 5507,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3899,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{k}{6}",
"budget": 4881
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005509",
"normalized_example_id": "ex_005509",
"source_idx": 5509,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8135,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{k}{6}",
"budget": 6508
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005509",
"normalized_example_id": "ex_005509",
"source_idx": 5509,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8135,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{k}{6}",
"budget": 8135
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005509",
"normalized_example_id": "ex_005509",
"source_idx": 5509,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8135,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{9-4n}{2+8n}",
"budget": 2452
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005510",
"normalized_example_id": "ex_005510",
"source_idx": 5510,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4086,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{9-4n}{2+8n}",
"budget": 3269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005510",
"normalized_example_id": "ex_005510",
"source_idx": 5510,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4086,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{9-4n}{2+8n}",
"budget": 4086
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005510",
"normalized_example_id": "ex_005510",
"source_idx": 5510,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4086,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{R(\\sqrt{6}-2)}{2}",
"budget": 2446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005511",
"normalized_example_id": "ex_005511",
"source_idx": 5511,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4076,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{R(\\sqrt{6}-2)}{2}",
"budget": 3261
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005511",
"normalized_example_id": "ex_005511",
"source_idx": 5511,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4076,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{R(\\sqrt{6}-2)}{2}",
"budget": 4076
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005511",
"normalized_example_id": "ex_005511",
"source_idx": 5511,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4076,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "341",
"budget": 1120
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005512",
"normalized_example_id": "ex_005512",
"source_idx": 5512,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1866,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "341",
"budget": 1493
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005512",
"normalized_example_id": "ex_005512",
"source_idx": 5512,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1866,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "341",
"budget": 1866
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005512",
"normalized_example_id": "ex_005512",
"source_idx": 5512,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1866,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2066
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005514",
"normalized_example_id": "ex_005514",
"source_idx": 5514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3444,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2755
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005514",
"normalized_example_id": "ex_005514",
"source_idx": 5514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3444,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3444
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005514",
"normalized_example_id": "ex_005514",
"source_idx": 5514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3444,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{47}{256}",
"budget": 2168
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005516",
"normalized_example_id": "ex_005516",
"source_idx": 5516,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3613,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{47}{256}",
"budget": 2890
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005516",
"normalized_example_id": "ex_005516",
"source_idx": 5516,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3613,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{47}{256}",
"budget": 3613
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005516",
"normalized_example_id": "ex_005516",
"source_idx": 5516,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3613,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "357",
"budget": 3778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005518",
"normalized_example_id": "ex_005518",
"source_idx": 5518,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6296,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "357",
"budget": 5037
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005518",
"normalized_example_id": "ex_005518",
"source_idx": 5518,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6296,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "357",
"budget": 6296
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005518",
"normalized_example_id": "ex_005518",
"source_idx": 5518,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6296,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "91",
"budget": 3272
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005519",
"normalized_example_id": "ex_005519",
"source_idx": 5519,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5454,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "91",
"budget": 4363
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005519",
"normalized_example_id": "ex_005519",
"source_idx": 5519,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5454,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "91",
"budget": 5454
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005519",
"normalized_example_id": "ex_005519",
"source_idx": 5519,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5454,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1002^2",
"budget": 2959
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005520",
"normalized_example_id": "ex_005520",
"source_idx": 5520,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4932,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1002^2",
"budget": 3946
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005520",
"normalized_example_id": "ex_005520",
"source_idx": 5520,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4932,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1002^2",
"budget": 4932
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005520",
"normalized_example_id": "ex_005520",
"source_idx": 5520,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4932,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1543
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005522",
"normalized_example_id": "ex_005522",
"source_idx": 5522,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2572,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2058
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005522",
"normalized_example_id": "ex_005522",
"source_idx": 5522,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2572,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2572
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005522",
"normalized_example_id": "ex_005522",
"source_idx": 5522,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2572,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5108
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005523",
"normalized_example_id": "ex_005523",
"source_idx": 5523,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8514,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6811
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005523",
"normalized_example_id": "ex_005523",
"source_idx": 5523,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8514,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8514
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005523",
"normalized_example_id": "ex_005523",
"source_idx": 5523,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8514,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arccos\\frac{1}{x^{2}}",
"budget": 1160
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005524",
"normalized_example_id": "ex_005524",
"source_idx": 5524,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1933,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arccos\\frac{1}{x^{2}}",
"budget": 1546
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005524",
"normalized_example_id": "ex_005524",
"source_idx": 5524,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1933,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arccos\\frac{1}{x^{2}}",
"budget": 1933
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005524",
"normalized_example_id": "ex_005524",
"source_idx": 5524,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1933,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "719",
"budget": 4775
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005525",
"normalized_example_id": "ex_005525",
"source_idx": 5525,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7958,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "719",
"budget": 6366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005525",
"normalized_example_id": "ex_005525",
"source_idx": 5525,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7958,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "719",
"budget": 7958
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005525",
"normalized_example_id": "ex_005525",
"source_idx": 5525,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7958,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-1)\\cup(-1,0)\\cup(1,\\frac{3}{2})",
"budget": 2335
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005526",
"normalized_example_id": "ex_005526",
"source_idx": 5526,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-1)\\cup(-1,0)\\cup(1,\\frac{3}{2})",
"budget": 3114
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005526",
"normalized_example_id": "ex_005526",
"source_idx": 5526,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-1)\\cup(-1,0)\\cup(1,\\frac{3}{2})",
"budget": 3892
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005526",
"normalized_example_id": "ex_005526",
"source_idx": 5526,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3922
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005527",
"normalized_example_id": "ex_005527",
"source_idx": 5527,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6537,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005527",
"normalized_example_id": "ex_005527",
"source_idx": 5527,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6537,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6537
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005527",
"normalized_example_id": "ex_005527",
"source_idx": 5527,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6537,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 1007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005528",
"normalized_example_id": "ex_005528",
"source_idx": 5528,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 1342
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005528",
"normalized_example_id": "ex_005528",
"source_idx": 5528,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 1678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005528",
"normalized_example_id": "ex_005528",
"source_idx": 5528,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 1511
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005529",
"normalized_example_id": "ex_005529",
"source_idx": 5529,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2519,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 2015
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005529",
"normalized_example_id": "ex_005529",
"source_idx": 5529,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2519,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 2519
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005529",
"normalized_example_id": "ex_005529",
"source_idx": 5529,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2519,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3325
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005536",
"normalized_example_id": "ex_005536",
"source_idx": 5536,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5541,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4433
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005536",
"normalized_example_id": "ex_005536",
"source_idx": 5536,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5541,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5541
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005536",
"normalized_example_id": "ex_005536",
"source_idx": 5536,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5541,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10000",
"budget": 4595
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005537",
"normalized_example_id": "ex_005537",
"source_idx": 5537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7659,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10000",
"budget": 6127
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005537",
"normalized_example_id": "ex_005537",
"source_idx": 5537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7659,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10000",
"budget": 7659
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005537",
"normalized_example_id": "ex_005537",
"source_idx": 5537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7659,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 2145
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005540",
"normalized_example_id": "ex_005540",
"source_idx": 5540,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3575,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 2860
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005540",
"normalized_example_id": "ex_005540",
"source_idx": 5540,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3575,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 3575
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005540",
"normalized_example_id": "ex_005540",
"source_idx": 5540,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3575,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-6,0",
"budget": 3758
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005541",
"normalized_example_id": "ex_005541",
"source_idx": 5541,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6263,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-6,0",
"budget": 5010
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005541",
"normalized_example_id": "ex_005541",
"source_idx": 5541,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6263,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-6,0",
"budget": 6263
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005541",
"normalized_example_id": "ex_005541",
"source_idx": 5541,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6263,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 3319
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005542",
"normalized_example_id": "ex_005542",
"source_idx": 5542,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5531,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 4425
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005542",
"normalized_example_id": "ex_005542",
"source_idx": 5542,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5531,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 5531
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005542",
"normalized_example_id": "ex_005542",
"source_idx": 5542,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5531,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{5}",
"budget": 5342
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005543",
"normalized_example_id": "ex_005543",
"source_idx": 5543,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8904,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{5}",
"budget": 7123
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005543",
"normalized_example_id": "ex_005543",
"source_idx": 5543,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8904,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{5}",
"budget": 8904
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005543",
"normalized_example_id": "ex_005543",
"source_idx": 5543,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8904,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)=x",
"budget": 4570
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005544",
"normalized_example_id": "ex_005544",
"source_idx": 5544,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7616,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.