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": "171",
"budget": 6064
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003248",
"normalized_example_id": "ex_003248",
"source_idx": 3248,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10107,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "171",
"budget": 8086
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003248",
"normalized_example_id": "ex_003248",
"source_idx": 3248,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10107,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "171",
"budget": 10107
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003248",
"normalized_example_id": "ex_003248",
"source_idx": 3248,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10107,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4014
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003251",
"normalized_example_id": "ex_003251",
"source_idx": 3251,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5352
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003251",
"normalized_example_id": "ex_003251",
"source_idx": 3251,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6690
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003251",
"normalized_example_id": "ex_003251",
"source_idx": 3251,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "890",
"budget": 797
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003254",
"normalized_example_id": "ex_003254",
"source_idx": 3254,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1329,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "890",
"budget": 1063
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003254",
"normalized_example_id": "ex_003254",
"source_idx": 3254,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1329,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "890",
"budget": 1329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003254",
"normalized_example_id": "ex_003254",
"source_idx": 3254,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1329,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 2378
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003255",
"normalized_example_id": "ex_003255",
"source_idx": 3255,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3964,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 3171
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003255",
"normalized_example_id": "ex_003255",
"source_idx": 3255,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3964,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 3964
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003255",
"normalized_example_id": "ex_003255",
"source_idx": 3255,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3964,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "336",
"budget": 3369
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003256",
"normalized_example_id": "ex_003256",
"source_idx": 3256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5615,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "336",
"budget": 4492
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003256",
"normalized_example_id": "ex_003256",
"source_idx": 3256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5615,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "336",
"budget": 5615
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003256",
"normalized_example_id": "ex_003256",
"source_idx": 3256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5615,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3\\sqrt{14}}{5}",
"budget": 2163
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003257",
"normalized_example_id": "ex_003257",
"source_idx": 3257,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3605,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3\\sqrt{14}}{5}",
"budget": 2884
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003257",
"normalized_example_id": "ex_003257",
"source_idx": 3257,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3605,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3\\sqrt{14}}{5}",
"budget": 3605
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003257",
"normalized_example_id": "ex_003257",
"source_idx": 3257,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3605,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003258",
"normalized_example_id": "ex_003258",
"source_idx": 3258,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7324,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 5859
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003258",
"normalized_example_id": "ex_003258",
"source_idx": 3258,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7324,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 7324
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003258",
"normalized_example_id": "ex_003258",
"source_idx": 3258,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7324,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{169}{10}",
"budget": 2083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003259",
"normalized_example_id": "ex_003259",
"source_idx": 3259,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{169}{10}",
"budget": 2778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003259",
"normalized_example_id": "ex_003259",
"source_idx": 3259,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{169}{10}",
"budget": 3472
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003259",
"normalized_example_id": "ex_003259",
"source_idx": 3259,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-6),(-20,-4),(10,-10),(6,-30),(4,20)",
"budget": 1600
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003261",
"normalized_example_id": "ex_003261",
"source_idx": 3261,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2667,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-6),(-20,-4),(10,-10),(6,-30),(4,20)",
"budget": 2134
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003261",
"normalized_example_id": "ex_003261",
"source_idx": 3261,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2667,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-6),(-20,-4),(10,-10),(6,-30),(4,20)",
"budget": 2667
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003261",
"normalized_example_id": "ex_003261",
"source_idx": 3261,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2667,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2020",
"budget": 2696
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003263",
"normalized_example_id": "ex_003263",
"source_idx": 3263,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4494,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2020",
"budget": 3595
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003263",
"normalized_example_id": "ex_003263",
"source_idx": 3263,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4494,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2020",
"budget": 4494
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003263",
"normalized_example_id": "ex_003263",
"source_idx": 3263,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4494,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4x^{2}+4xy+y^{2}-10y-15=0",
"budget": 2581
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003264",
"normalized_example_id": "ex_003264",
"source_idx": 3264,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4302,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4x^{2}+4xy+y^{2}-10y-15=0",
"budget": 3442
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003264",
"normalized_example_id": "ex_003264",
"source_idx": 3264,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4302,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4x^{2}+4xy+y^{2}-10y-15=0",
"budget": 4302
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003264",
"normalized_example_id": "ex_003264",
"source_idx": 3264,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4302,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{14}{3},\\frac{21}{4},6}",
"budget": 1540
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003266",
"normalized_example_id": "ex_003266",
"source_idx": 3266,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2567,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{14}{3},\\frac{21}{4},6}",
"budget": 2054
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003266",
"normalized_example_id": "ex_003266",
"source_idx": 3266,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2567,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{14}{3},\\frac{21}{4},6}",
"budget": 2567
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003266",
"normalized_example_id": "ex_003266",
"source_idx": 3266,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2567,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "W_{1}=\\frac{p_{0}V_{0}}{k-1}[(\\frac{V_{0}}{V_{1}})^{k-1}-1]",
"budget": 3994
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003267",
"normalized_example_id": "ex_003267",
"source_idx": 3267,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "W_{1}=\\frac{p_{0}V_{0}}{k-1}[(\\frac{V_{0}}{V_{1}})^{k-1}-1]",
"budget": 5326
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003267",
"normalized_example_id": "ex_003267",
"source_idx": 3267,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "W_{1}=\\frac{p_{0}V_{0}}{k-1}[(\\frac{V_{0}}{V_{1}})^{k-1}-1]",
"budget": 6657
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003267",
"normalized_example_id": "ex_003267",
"source_idx": 3267,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{96}{7}",
"budget": 1212
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003268",
"normalized_example_id": "ex_003268",
"source_idx": 3268,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2020,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{96}{7}",
"budget": 1616
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003268",
"normalized_example_id": "ex_003268",
"source_idx": 3268,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2020,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{96}{7}",
"budget": 2020
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003268",
"normalized_example_id": "ex_003268",
"source_idx": 3268,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2020,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2872
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003270",
"normalized_example_id": "ex_003270",
"source_idx": 3270,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4787,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3830
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003270",
"normalized_example_id": "ex_003270",
"source_idx": 3270,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4787,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4787
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003270",
"normalized_example_id": "ex_003270",
"source_idx": 3270,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4787,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "P(x)=x(x-1)(x-2)(x-3)",
"budget": 2477
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003271",
"normalized_example_id": "ex_003271",
"source_idx": 3271,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4128,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "P(x)=x(x-1)(x-2)(x-3)",
"budget": 3302
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003271",
"normalized_example_id": "ex_003271",
"source_idx": 3271,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4128,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "P(x)=x(x-1)(x-2)(x-3)",
"budget": 4128
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003271",
"normalized_example_id": "ex_003271",
"source_idx": 3271,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4128,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln|x-3+\\sqrt{x^{2}-6x+3}|+C",
"budget": 1991
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003273",
"normalized_example_id": "ex_003273",
"source_idx": 3273,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3318,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln|x-3+\\sqrt{x^{2}-6x+3}|+C",
"budget": 2654
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003273",
"normalized_example_id": "ex_003273",
"source_idx": 3273,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3318,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln|x-3+\\sqrt{x^{2}-6x+3}|+C",
"budget": 3318
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003273",
"normalized_example_id": "ex_003273",
"source_idx": 3273,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3318,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,2",
"budget": 2041
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003275",
"normalized_example_id": "ex_003275",
"source_idx": 3275,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3401,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,2",
"budget": 2721
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003275",
"normalized_example_id": "ex_003275",
"source_idx": 3275,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3401,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,2",
"budget": 3401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003275",
"normalized_example_id": "ex_003275",
"source_idx": 3275,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3401,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "683",
"budget": 3982
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003276",
"normalized_example_id": "ex_003276",
"source_idx": 3276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6637,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "683",
"budget": 5310
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003276",
"normalized_example_id": "ex_003276",
"source_idx": 3276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6637,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "683",
"budget": 6637
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003276",
"normalized_example_id": "ex_003276",
"source_idx": 3276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6637,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{37}{60}",
"budget": 2495
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003279",
"normalized_example_id": "ex_003279",
"source_idx": 3279,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{37}{60}",
"budget": 3327
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003279",
"normalized_example_id": "ex_003279",
"source_idx": 3279,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{37}{60}",
"budget": 4159
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003279",
"normalized_example_id": "ex_003279",
"source_idx": 3279,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-2022",
"budget": 1455
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003280",
"normalized_example_id": "ex_003280",
"source_idx": 3280,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-2022",
"budget": 1940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003280",
"normalized_example_id": "ex_003280",
"source_idx": 3280,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-2022",
"budget": 2425
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003280",
"normalized_example_id": "ex_003280",
"source_idx": 3280,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2^7 > 100",
"budget": 5853
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003285",
"normalized_example_id": "ex_003285",
"source_idx": 3285,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9755,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2^7 > 100",
"budget": 7804
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003285",
"normalized_example_id": "ex_003285",
"source_idx": 3285,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9755,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2^7 > 100",
"budget": 9755
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003285",
"normalized_example_id": "ex_003285",
"source_idx": 3285,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9755,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^\\circ, 60^\\circ, 90^\\circ",
"budget": 3257
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003288",
"normalized_example_id": "ex_003288",
"source_idx": 3288,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^\\circ, 60^\\circ, 90^\\circ",
"budget": 4343
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003288",
"normalized_example_id": "ex_003288",
"source_idx": 3288,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^\\circ, 60^\\circ, 90^\\circ",
"budget": 5429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003288",
"normalized_example_id": "ex_003288",
"source_idx": 3288,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 1702
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003289",
"normalized_example_id": "ex_003289",
"source_idx": 3289,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2836,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 2269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003289",
"normalized_example_id": "ex_003289",
"source_idx": 3289,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2836,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 2836
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003289",
"normalized_example_id": "ex_003289",
"source_idx": 3289,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2836,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^\\circ",
"budget": 4645
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003290",
"normalized_example_id": "ex_003290",
"source_idx": 3290,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7742,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^\\circ",
"budget": 6194
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003290",
"normalized_example_id": "ex_003290",
"source_idx": 3290,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7742,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^\\circ",
"budget": 7742
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003290",
"normalized_example_id": "ex_003290",
"source_idx": 3290,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7742,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4439
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003291",
"normalized_example_id": "ex_003291",
"source_idx": 3291,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003291",
"normalized_example_id": "ex_003291",
"source_idx": 3291,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7398
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003291",
"normalized_example_id": "ex_003291",
"source_idx": 3291,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "243",
"budget": 3856
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003294",
"normalized_example_id": "ex_003294",
"source_idx": 3294,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6426,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "243",
"budget": 5141
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003294",
"normalized_example_id": "ex_003294",
"source_idx": 3294,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6426,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "243",
"budget": 6426
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003294",
"normalized_example_id": "ex_003294",
"source_idx": 3294,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6426,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 2890
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003296",
"normalized_example_id": "ex_003296",
"source_idx": 3296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4816,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 3853
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003296",
"normalized_example_id": "ex_003296",
"source_idx": 3296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4816,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 4816
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003296",
"normalized_example_id": "ex_003296",
"source_idx": 3296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4816,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 2561
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003301",
"normalized_example_id": "ex_003301",
"source_idx": 3301,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4268,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 3414
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003301",
"normalized_example_id": "ex_003301",
"source_idx": 3301,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4268,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 4268
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003301",
"normalized_example_id": "ex_003301",
"source_idx": 3301,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4268,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(\\frac{-1+\\sqrt{4 a+1}}{2}\\right)^{2 n}",
"budget": 5958
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003302",
"normalized_example_id": "ex_003302",
"source_idx": 3302,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(\\frac{-1+\\sqrt{4 a+1}}{2}\\right)^{2 n}",
"budget": 7944
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003302",
"normalized_example_id": "ex_003302",
"source_idx": 3302,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(\\frac{-1+\\sqrt{4 a+1}}{2}\\right)^{2 n}",
"budget": 9930
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003302",
"normalized_example_id": "ex_003302",
"source_idx": 3302,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13:20",
"budget": 985
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003304",
"normalized_example_id": "ex_003304",
"source_idx": 3304,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1641,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13:20",
"budget": 1313
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003304",
"normalized_example_id": "ex_003304",
"source_idx": 3304,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1641,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13:20",
"budget": 1641
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003304",
"normalized_example_id": "ex_003304",
"source_idx": 3304,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1641,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2480
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003306",
"normalized_example_id": "ex_003306",
"source_idx": 3306,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4133,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3306
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003306",
"normalized_example_id": "ex_003306",
"source_idx": 3306,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4133,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4133
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003306",
"normalized_example_id": "ex_003306",
"source_idx": 3306,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4133,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;3),(-1;2)",
"budget": 4001
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003309",
"normalized_example_id": "ex_003309",
"source_idx": 3309,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6668,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;3),(-1;2)",
"budget": 5334
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003309",
"normalized_example_id": "ex_003309",
"source_idx": 3309,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6668,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;3),(-1;2)",
"budget": 6668
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003309",
"normalized_example_id": "ex_003309",
"source_idx": 3309,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6668,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9}{8} \\sqrt[4]{3}",
"budget": 4253
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003311",
"normalized_example_id": "ex_003311",
"source_idx": 3311,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7088,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.