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": "5or-3or-7",
"budget": 5273
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006144",
"normalized_example_id": "ex_006144",
"source_idx": 6144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5273,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5662
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006146",
"normalized_example_id": "ex_006146",
"source_idx": 6146,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9436,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7549
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006146",
"normalized_example_id": "ex_006146",
"source_idx": 6146,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9436,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 9436
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006146",
"normalized_example_id": "ex_006146",
"source_idx": 6146,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9436,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{25\\pi}{12}-\\frac{25\\sqrt{3}}{8}",
"budget": 2203
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006148",
"normalized_example_id": "ex_006148",
"source_idx": 6148,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3672,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{25\\pi}{12}-\\frac{25\\sqrt{3}}{8}",
"budget": 2938
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006148",
"normalized_example_id": "ex_006148",
"source_idx": 6148,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3672,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{25\\pi}{12}-\\frac{25\\sqrt{3}}{8}",
"budget": 3672
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006148",
"normalized_example_id": "ex_006148",
"source_idx": 6148,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3672,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y=-\\frac{1}{2} x^{2}+\\frac{3}{2} x+2",
"budget": 3274
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006149",
"normalized_example_id": "ex_006149",
"source_idx": 6149,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5457,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y=-\\frac{1}{2} x^{2}+\\frac{3}{2} x+2",
"budget": 4366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006149",
"normalized_example_id": "ex_006149",
"source_idx": 6149,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5457,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y=-\\frac{1}{2} x^{2}+\\frac{3}{2} x+2",
"budget": 5457
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006149",
"normalized_example_id": "ex_006149",
"source_idx": 6149,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5457,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2n-1",
"budget": 5537
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006152",
"normalized_example_id": "ex_006152",
"source_idx": 6152,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2n-1",
"budget": 7383
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006152",
"normalized_example_id": "ex_006152",
"source_idx": 6152,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2n-1",
"budget": 9229
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006152",
"normalized_example_id": "ex_006152",
"source_idx": 6152,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1000(2^{n}-1)2^{999n}",
"budget": 2272
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006155",
"normalized_example_id": "ex_006155",
"source_idx": 6155,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3787,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1000(2^{n}-1)2^{999n}",
"budget": 3030
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006155",
"normalized_example_id": "ex_006155",
"source_idx": 6155,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3787,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1000(2^{n}-1)2^{999n}",
"budget": 3787
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006155",
"normalized_example_id": "ex_006155",
"source_idx": 6155,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3787,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 1640
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006156",
"normalized_example_id": "ex_006156",
"source_idx": 6156,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2734,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 2187
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006156",
"normalized_example_id": "ex_006156",
"source_idx": 6156,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2734,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 2734
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006156",
"normalized_example_id": "ex_006156",
"source_idx": 6156,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2734,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 628
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006158",
"normalized_example_id": "ex_006158",
"source_idx": 6158,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1046,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 837
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006158",
"normalized_example_id": "ex_006158",
"source_idx": 6158,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1046,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1046
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006158",
"normalized_example_id": "ex_006158",
"source_idx": 6158,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1046,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2402",
"budget": 2335
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006159",
"normalized_example_id": "ex_006159",
"source_idx": 6159,
"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": "2402",
"budget": 3114
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006159",
"normalized_example_id": "ex_006159",
"source_idx": 6159,
"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": "2402",
"budget": 3892
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006159",
"normalized_example_id": "ex_006159",
"source_idx": 6159,
"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": "9or11",
"budget": 2759
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006161",
"normalized_example_id": "ex_006161",
"source_idx": 6161,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4599,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9or11",
"budget": 3679
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006161",
"normalized_example_id": "ex_006161",
"source_idx": 6161,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4599,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9or11",
"budget": 4599
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006161",
"normalized_example_id": "ex_006161",
"source_idx": 6161,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4599,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2879
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006162",
"normalized_example_id": "ex_006162",
"source_idx": 6162,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4798,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3838
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006162",
"normalized_example_id": "ex_006162",
"source_idx": 6162,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4798,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4798
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006162",
"normalized_example_id": "ex_006162",
"source_idx": 6162,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4798,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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),(-1,-1),(-1,0),(0,-1),(0,0),(1,0),(1,-1),(2,1)",
"budget": 5794
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006165",
"normalized_example_id": "ex_006165",
"source_idx": 6165,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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),(-1,-1),(-1,0),(0,-1),(0,0),(1,0),(1,-1),(2,1)",
"budget": 7726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006165",
"normalized_example_id": "ex_006165",
"source_idx": 6165,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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),(-1,-1),(-1,0),(0,-1),(0,0),(1,0),(1,-1),(2,1)",
"budget": 9657
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006165",
"normalized_example_id": "ex_006165",
"source_idx": 6165,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 3073
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006167",
"normalized_example_id": "ex_006167",
"source_idx": 6167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5121,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 4097
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006167",
"normalized_example_id": "ex_006167",
"source_idx": 6167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5121,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 5121
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006167",
"normalized_example_id": "ex_006167",
"source_idx": 6167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5121,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e^{-\\frac{5}{2}}",
"budget": 1426
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006168",
"normalized_example_id": "ex_006168",
"source_idx": 6168,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2376,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e^{-\\frac{5}{2}}",
"budget": 1901
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006168",
"normalized_example_id": "ex_006168",
"source_idx": 6168,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2376,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e^{-\\frac{5}{2}}",
"budget": 2376
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006168",
"normalized_example_id": "ex_006168",
"source_idx": 6168,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2376,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 6077
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006171",
"normalized_example_id": "ex_006171",
"source_idx": 6171,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10129,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 8103
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006171",
"normalized_example_id": "ex_006171",
"source_idx": 6171,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10129,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 10129
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006171",
"normalized_example_id": "ex_006171",
"source_idx": 6171,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10129,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1421
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006172",
"normalized_example_id": "ex_006172",
"source_idx": 6172,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2369,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1895
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006172",
"normalized_example_id": "ex_006172",
"source_idx": 6172,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2369,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2369
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006172",
"normalized_example_id": "ex_006172",
"source_idx": 6172,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2369,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 3268
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006173",
"normalized_example_id": "ex_006173",
"source_idx": 6173,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5447,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 4358
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006173",
"normalized_example_id": "ex_006173",
"source_idx": 6173,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5447,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 5447
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006173",
"normalized_example_id": "ex_006173",
"source_idx": 6173,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5447,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "positive",
"budget": 2036
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006174",
"normalized_example_id": "ex_006174",
"source_idx": 6174,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3393,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "positive",
"budget": 2714
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006174",
"normalized_example_id": "ex_006174",
"source_idx": 6174,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3393,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "positive",
"budget": 3393
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006174",
"normalized_example_id": "ex_006174",
"source_idx": 6174,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3393,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3.1415926534<\\pi<3.1415926540",
"budget": 3100
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006175",
"normalized_example_id": "ex_006175",
"source_idx": 6175,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5167,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3.1415926534<\\pi<3.1415926540",
"budget": 4134
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006175",
"normalized_example_id": "ex_006175",
"source_idx": 6175,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5167,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3.1415926534<\\pi<3.1415926540",
"budget": 5167
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006175",
"normalized_example_id": "ex_006175",
"source_idx": 6175,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5167,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "729",
"budget": 2987
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006176",
"normalized_example_id": "ex_006176",
"source_idx": 6176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4979,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "729",
"budget": 3983
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006176",
"normalized_example_id": "ex_006176",
"source_idx": 6176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4979,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "729",
"budget": 4979
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006176",
"normalized_example_id": "ex_006176",
"source_idx": 6176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4979,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y\\in{-2,-1,1}",
"budget": 2870
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006177",
"normalized_example_id": "ex_006177",
"source_idx": 6177,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4783,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y\\in{-2,-1,1}",
"budget": 3826
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006177",
"normalized_example_id": "ex_006177",
"source_idx": 6177,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4783,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y\\in{-2,-1,1}",
"budget": 4783
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006177",
"normalized_example_id": "ex_006177",
"source_idx": 6177,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4783,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(6,3),(6,-9),(1,1),(1,-2),(2,-1)",
"budget": 2624
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006180",
"normalized_example_id": "ex_006180",
"source_idx": 6180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4374,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(6,3),(6,-9),(1,1),(1,-2),(2,-1)",
"budget": 3499
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006180",
"normalized_example_id": "ex_006180",
"source_idx": 6180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4374,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(6,3),(6,-9),(1,1),(1,-2),(2,-1)",
"budget": 4374
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006180",
"normalized_example_id": "ex_006180",
"source_idx": 6180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4374,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{5}-1}{4}",
"budget": 6003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006182",
"normalized_example_id": "ex_006182",
"source_idx": 6182,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{5}-1}{4}",
"budget": 8004
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006182",
"normalized_example_id": "ex_006182",
"source_idx": 6182,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{5}-1}{4}",
"budget": 10005
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006182",
"normalized_example_id": "ex_006182",
"source_idx": 6182,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,3),(3,\\frac{1}{3})",
"budget": 956
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006184",
"normalized_example_id": "ex_006184",
"source_idx": 6184,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1593,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,3),(3,\\frac{1}{3})",
"budget": 1274
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006184",
"normalized_example_id": "ex_006184",
"source_idx": 6184,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1593,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,3),(3,\\frac{1}{3})",
"budget": 1593
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006184",
"normalized_example_id": "ex_006184",
"source_idx": 6184,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1593,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{3}}{3}",
"budget": 3566
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006186",
"normalized_example_id": "ex_006186",
"source_idx": 6186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5943,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}}{3}",
"budget": 4754
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006186",
"normalized_example_id": "ex_006186",
"source_idx": 6186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5943,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}}{3}",
"budget": 5943
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006186",
"normalized_example_id": "ex_006186",
"source_idx": 6186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5943,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}{4}",
"budget": 1071
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006189",
"normalized_example_id": "ex_006189",
"source_idx": 6189,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}{4}",
"budget": 1428
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006189",
"normalized_example_id": "ex_006189",
"source_idx": 6189,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}{4}",
"budget": 1785
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006189",
"normalized_example_id": "ex_006189",
"source_idx": 6189,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "180",
"budget": 3001
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006190",
"normalized_example_id": "ex_006190",
"source_idx": 6190,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5002,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "180",
"budget": 4002
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006190",
"normalized_example_id": "ex_006190",
"source_idx": 6190,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5002,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "180",
"budget": 5002
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006190",
"normalized_example_id": "ex_006190",
"source_idx": 6190,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5002,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}{84}",
"budget": 2495
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006191",
"normalized_example_id": "ex_006191",
"source_idx": 6191,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4158,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}{84}",
"budget": 3326
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006191",
"normalized_example_id": "ex_006191",
"source_idx": 6191,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4158,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}{84}",
"budget": 4158
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006191",
"normalized_example_id": "ex_006191",
"source_idx": 6191,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4158,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{3}",
"budget": 906
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006192",
"normalized_example_id": "ex_006192",
"source_idx": 6192,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1510,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{3}",
"budget": 1208
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006192",
"normalized_example_id": "ex_006192",
"source_idx": 6192,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1510,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{3}",
"budget": 1510
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006192",
"normalized_example_id": "ex_006192",
"source_idx": 6192,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1510,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}}{3}",
"budget": 2221
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006193",
"normalized_example_id": "ex_006193",
"source_idx": 6193,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3702,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}}{3}",
"budget": 2962
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006193",
"normalized_example_id": "ex_006193",
"source_idx": 6193,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3702,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}}{3}",
"budget": 3702
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006193",
"normalized_example_id": "ex_006193",
"source_idx": 6193,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3702,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25916",
"budget": 5751
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006194",
"normalized_example_id": "ex_006194",
"source_idx": 6194,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9585,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25916",
"budget": 7668
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006194",
"normalized_example_id": "ex_006194",
"source_idx": 6194,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9585,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25916",
"budget": 9585
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006194",
"normalized_example_id": "ex_006194",
"source_idx": 6194,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9585,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,2,4,8,16,32",
"budget": 6133
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006196",
"normalized_example_id": "ex_006196",
"source_idx": 6196,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10222,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,2,4,8,16,32",
"budget": 8178
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006196",
"normalized_example_id": "ex_006196",
"source_idx": 6196,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10222,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,2,4,8,16,32",
"budget": 10222
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006196",
"normalized_example_id": "ex_006196",
"source_idx": 6196,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10222,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 797
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006198",
"normalized_example_id": "ex_006198",
"source_idx": 6198,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1328,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1062
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006198",
"normalized_example_id": "ex_006198",
"source_idx": 6198,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1328,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1328
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006198",
"normalized_example_id": "ex_006198",
"source_idx": 6198,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1328,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "69",
"budget": 738
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006199",
"normalized_example_id": "ex_006199",
"source_idx": 6199,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1230,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "69",
"budget": 984
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006199",
"normalized_example_id": "ex_006199",
"source_idx": 6199,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1230,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "69",
"budget": 1230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006199",
"normalized_example_id": "ex_006199",
"source_idx": 6199,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1230,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.