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": "\\sqrt{A+B}",
"budget": 2079
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005353",
"normalized_example_id": "ex_005353",
"source_idx": 5353,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2599,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{A+B}",
"budget": 2599
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005353",
"normalized_example_id": "ex_005353",
"source_idx": 5353,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2599,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 2), (2, 13), (3, 3), (3, 7), (13, 2), (7, 3)",
"budget": 5541
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005359",
"normalized_example_id": "ex_005359",
"source_idx": 5359,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9235,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 2), (2, 13), (3, 3), (3, 7), (13, 2), (7, 3)",
"budget": 7388
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005359",
"normalized_example_id": "ex_005359",
"source_idx": 5359,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9235,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 2), (2, 13), (3, 3), (3, 7), (13, 2), (7, 3)",
"budget": 9235
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005359",
"normalized_example_id": "ex_005359",
"source_idx": 5359,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9235,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 2277
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005360",
"normalized_example_id": "ex_005360",
"source_idx": 5360,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3795,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 3036
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005360",
"normalized_example_id": "ex_005360",
"source_idx": 5360,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3795,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 3795
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005360",
"normalized_example_id": "ex_005360",
"source_idx": 5360,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3795,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)\\equivx^{2},f(x)\\equiv0,f(x)\\equiv-x^{2}",
"budget": 4354
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005365",
"normalized_example_id": "ex_005365",
"source_idx": 5365,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7257,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)\\equivx^{2},f(x)\\equiv0,f(x)\\equiv-x^{2}",
"budget": 5806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005365",
"normalized_example_id": "ex_005365",
"source_idx": 5365,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7257,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)\\equivx^{2},f(x)\\equiv0,f(x)\\equiv-x^{2}",
"budget": 7257
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005365",
"normalized_example_id": "ex_005365",
"source_idx": 5365,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7257,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "162",
"budget": 6058
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005367",
"normalized_example_id": "ex_005367",
"source_idx": 5367,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10097,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "162",
"budget": 8078
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005367",
"normalized_example_id": "ex_005367",
"source_idx": 5367,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10097,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "162",
"budget": 10097
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005367",
"normalized_example_id": "ex_005367",
"source_idx": 5367,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10097,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{3}",
"budget": 1981
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005369",
"normalized_example_id": "ex_005369",
"source_idx": 5369,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3302,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{3}",
"budget": 2642
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005369",
"normalized_example_id": "ex_005369",
"source_idx": 5369,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3302,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{3}",
"budget": 3302
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005369",
"normalized_example_id": "ex_005369",
"source_idx": 5369,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3302,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4835
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005372",
"normalized_example_id": "ex_005372",
"source_idx": 5372,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8058,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005372",
"normalized_example_id": "ex_005372",
"source_idx": 5372,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8058,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8058
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005372",
"normalized_example_id": "ex_005372",
"source_idx": 5372,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8058,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "35",
"budget": 657
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005373",
"normalized_example_id": "ex_005373",
"source_idx": 5373,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1095,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "35",
"budget": 876
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005373",
"normalized_example_id": "ex_005373",
"source_idx": 5373,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1095,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "35",
"budget": 1095
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005373",
"normalized_example_id": "ex_005373",
"source_idx": 5373,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1095,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha=-1+\\mathrm{i},\\beta=-3",
"budget": 3958
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005376",
"normalized_example_id": "ex_005376",
"source_idx": 5376,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha=-1+\\mathrm{i},\\beta=-3",
"budget": 5278
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005376",
"normalized_example_id": "ex_005376",
"source_idx": 5376,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha=-1+\\mathrm{i},\\beta=-3",
"budget": 6597
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005376",
"normalized_example_id": "ex_005376",
"source_idx": 5376,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 3649
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005378",
"normalized_example_id": "ex_005378",
"source_idx": 5378,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6082,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 4866
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005378",
"normalized_example_id": "ex_005378",
"source_idx": 5378,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6082,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 6082
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005378",
"normalized_example_id": "ex_005378",
"source_idx": 5378,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6082,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3518
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005379",
"normalized_example_id": "ex_005379",
"source_idx": 5379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5863,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4690
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005379",
"normalized_example_id": "ex_005379",
"source_idx": 5379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5863,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5863
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005379",
"normalized_example_id": "ex_005379",
"source_idx": 5379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5863,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3}}{2}",
"budget": 3999
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005380",
"normalized_example_id": "ex_005380",
"source_idx": 5380,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6665,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3}}{2}",
"budget": 5332
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005380",
"normalized_example_id": "ex_005380",
"source_idx": 5380,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6665,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3}}{2}",
"budget": 6665
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005380",
"normalized_example_id": "ex_005380",
"source_idx": 5380,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6665,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "231",
"budget": 694
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005381",
"normalized_example_id": "ex_005381",
"source_idx": 5381,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1156,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "231",
"budget": 925
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005381",
"normalized_example_id": "ex_005381",
"source_idx": 5381,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1156,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "231",
"budget": 1156
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005381",
"normalized_example_id": "ex_005381",
"source_idx": 5381,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1156,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2^{n}}{(n+1)!}",
"budget": 3224
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005383",
"normalized_example_id": "ex_005383",
"source_idx": 5383,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5373,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2^{n}}{(n+1)!}",
"budget": 4298
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005383",
"normalized_example_id": "ex_005383",
"source_idx": 5383,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5373,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2^{n}}{(n+1)!}",
"budget": 5373
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005383",
"normalized_example_id": "ex_005383",
"source_idx": 5383,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5373,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16 \\pi",
"budget": 2104
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005387",
"normalized_example_id": "ex_005387",
"source_idx": 5387,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3507,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16 \\pi",
"budget": 2806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005387",
"normalized_example_id": "ex_005387",
"source_idx": 5387,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3507,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16 \\pi",
"budget": 3507
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005387",
"normalized_example_id": "ex_005387",
"source_idx": 5387,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3507,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11}{8}",
"budget": 2989
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005392",
"normalized_example_id": "ex_005392",
"source_idx": 5392,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4981,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11}{8}",
"budget": 3985
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005392",
"normalized_example_id": "ex_005392",
"source_idx": 5392,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4981,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11}{8}",
"budget": 4981
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005392",
"normalized_example_id": "ex_005392",
"source_idx": 5392,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4981,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "42",
"budget": 1546
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005395",
"normalized_example_id": "ex_005395",
"source_idx": 5395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2577,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "42",
"budget": 2062
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005395",
"normalized_example_id": "ex_005395",
"source_idx": 5395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2577,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "42",
"budget": 2577
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005395",
"normalized_example_id": "ex_005395",
"source_idx": 5395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2577,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1444
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005399",
"normalized_example_id": "ex_005399",
"source_idx": 5399,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2406,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1925
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005399",
"normalized_example_id": "ex_005399",
"source_idx": 5399,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2406,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2406
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005399",
"normalized_example_id": "ex_005399",
"source_idx": 5399,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2406,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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) = \\frac{1}{2} \\text{ for all } x \\in \\mathbb{R}",
"budget": 1960
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005402",
"normalized_example_id": "ex_005402",
"source_idx": 5402,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3266,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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) = \\frac{1}{2} \\text{ for all } x \\in \\mathbb{R}",
"budget": 2613
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005402",
"normalized_example_id": "ex_005402",
"source_idx": 5402,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3266,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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) = \\frac{1}{2} \\text{ for all } x \\in \\mathbb{R}",
"budget": 3266
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005402",
"normalized_example_id": "ex_005402",
"source_idx": 5402,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3266,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{72}",
"budget": 3961
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005403",
"normalized_example_id": "ex_005403",
"source_idx": 5403,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6601,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{72}",
"budget": 5281
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005403",
"normalized_example_id": "ex_005403",
"source_idx": 5403,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6601,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{72}",
"budget": 6601
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005403",
"normalized_example_id": "ex_005403",
"source_idx": 5403,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6601,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4526
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005405",
"normalized_example_id": "ex_005405",
"source_idx": 5405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7543,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005405",
"normalized_example_id": "ex_005405",
"source_idx": 5405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7543,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7543
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005405",
"normalized_example_id": "ex_005405",
"source_idx": 5405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7543,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3805
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005406",
"normalized_example_id": "ex_005406",
"source_idx": 5406,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6341,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5073
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005406",
"normalized_example_id": "ex_005406",
"source_idx": 5406,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6341,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6341
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005406",
"normalized_example_id": "ex_005406",
"source_idx": 5406,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6341,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\text{E}",
"budget": 3253
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005407",
"normalized_example_id": "ex_005407",
"source_idx": 5407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5421,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\text{E}",
"budget": 4337
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005407",
"normalized_example_id": "ex_005407",
"source_idx": 5407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5421,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\text{E}",
"budget": 5421
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005407",
"normalized_example_id": "ex_005407",
"source_idx": 5407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5421,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4007",
"budget": 3443
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005413",
"normalized_example_id": "ex_005413",
"source_idx": 5413,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5739,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4007",
"budget": 4591
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005413",
"normalized_example_id": "ex_005413",
"source_idx": 5413,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5739,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4007",
"budget": 5739
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005413",
"normalized_example_id": "ex_005413",
"source_idx": 5413,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5739,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 4024
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005414",
"normalized_example_id": "ex_005414",
"source_idx": 5414,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6707,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 5366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005414",
"normalized_example_id": "ex_005414",
"source_idx": 5414,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6707,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 6707
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005414",
"normalized_example_id": "ex_005414",
"source_idx": 5414,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6707,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C=\\frac{1}{8}",
"budget": 4333
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005415",
"normalized_example_id": "ex_005415",
"source_idx": 5415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C=\\frac{1}{8}",
"budget": 5777
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005415",
"normalized_example_id": "ex_005415",
"source_idx": 5415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C=\\frac{1}{8}",
"budget": 7221
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005415",
"normalized_example_id": "ex_005415",
"source_idx": 5415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "105",
"budget": 2864
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005422",
"normalized_example_id": "ex_005422",
"source_idx": 5422,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4774,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "105",
"budget": 3819
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005422",
"normalized_example_id": "ex_005422",
"source_idx": 5422,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4774,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "105",
"budget": 4774
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005422",
"normalized_example_id": "ex_005422",
"source_idx": 5422,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4774,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3222
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005423",
"normalized_example_id": "ex_005423",
"source_idx": 5423,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5370,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4296
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005423",
"normalized_example_id": "ex_005423",
"source_idx": 5423,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5370,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5370
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005423",
"normalized_example_id": "ex_005423",
"source_idx": 5423,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5370,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1381
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005424",
"normalized_example_id": "ex_005424",
"source_idx": 5424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2302,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1842
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005424",
"normalized_example_id": "ex_005424",
"source_idx": 5424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2302,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2302
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005424",
"normalized_example_id": "ex_005424",
"source_idx": 5424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2302,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5184",
"budget": 3790
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005425",
"normalized_example_id": "ex_005425",
"source_idx": 5425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5184",
"budget": 5054
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005425",
"normalized_example_id": "ex_005425",
"source_idx": 5425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5184",
"budget": 6317
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005425",
"normalized_example_id": "ex_005425",
"source_idx": 5425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,1),(2,3)",
"budget": 3616
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005428",
"normalized_example_id": "ex_005428",
"source_idx": 5428,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6027,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,1),(2,3)",
"budget": 4822
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005428",
"normalized_example_id": "ex_005428",
"source_idx": 5428,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6027,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,1),(2,3)",
"budget": 6027
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005428",
"normalized_example_id": "ex_005428",
"source_idx": 5428,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6027,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005431",
"normalized_example_id": "ex_005431",
"source_idx": 5431,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8339,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6671
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005431",
"normalized_example_id": "ex_005431",
"source_idx": 5431,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8339,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8339
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005431",
"normalized_example_id": "ex_005431",
"source_idx": 5431,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8339,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 985
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005432",
"normalized_example_id": "ex_005432",
"source_idx": 5432,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1642,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1314
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005432",
"normalized_example_id": "ex_005432",
"source_idx": 5432,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1642,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1642
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005432",
"normalized_example_id": "ex_005432",
"source_idx": 5432,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1642,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1738
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005433",
"normalized_example_id": "ex_005433",
"source_idx": 5433,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2896,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2317
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005433",
"normalized_example_id": "ex_005433",
"source_idx": 5433,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2896,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.