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": "f(x)=x",
"budget": 6093
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005544",
"normalized_example_id": "ex_005544",
"source_idx": 5544,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7616,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7616
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005544",
"normalized_example_id": "ex_005544",
"source_idx": 5544,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7616,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "P_{n}=F_{n+1},Q_{n}=F_{n}",
"budget": 2360
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005547",
"normalized_example_id": "ex_005547",
"source_idx": 5547,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3934,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "P_{n}=F_{n+1},Q_{n}=F_{n}",
"budget": 3147
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005547",
"normalized_example_id": "ex_005547",
"source_idx": 5547,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3934,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "P_{n}=F_{n+1},Q_{n}=F_{n}",
"budget": 3934
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005547",
"normalized_example_id": "ex_005547",
"source_idx": 5547,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3934,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4868
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005550",
"normalized_example_id": "ex_005550",
"source_idx": 5550,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8113,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6490
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005550",
"normalized_example_id": "ex_005550",
"source_idx": 5550,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8113,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8113
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005550",
"normalized_example_id": "ex_005550",
"source_idx": 5550,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8113,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.0000123",
"budget": 3907
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005551",
"normalized_example_id": "ex_005551",
"source_idx": 5551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6511,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.0000123",
"budget": 5209
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005551",
"normalized_example_id": "ex_005551",
"source_idx": 5551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6511,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.0000123",
"budget": 6511
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005551",
"normalized_example_id": "ex_005551",
"source_idx": 5551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6511,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "970",
"budget": 2450
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005553",
"normalized_example_id": "ex_005553",
"source_idx": 5553,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "970",
"budget": 3266
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005553",
"normalized_example_id": "ex_005553",
"source_idx": 5553,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "970",
"budget": 4083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005553",
"normalized_example_id": "ex_005553",
"source_idx": 5553,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}",
"budget": 2707
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005554",
"normalized_example_id": "ex_005554",
"source_idx": 5554,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4512,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}",
"budget": 3610
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005554",
"normalized_example_id": "ex_005554",
"source_idx": 5554,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4512,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}",
"budget": 4512
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005554",
"normalized_example_id": "ex_005554",
"source_idx": 5554,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4512,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 3529
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005555",
"normalized_example_id": "ex_005555",
"source_idx": 5555,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5882,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 4706
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005555",
"normalized_example_id": "ex_005555",
"source_idx": 5555,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5882,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 5882
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005555",
"normalized_example_id": "ex_005555",
"source_idx": 5555,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5882,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{(n)}=\\frac{2\\cdotn!}{(1-x)^{n+1}}",
"budget": 2354
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005557",
"normalized_example_id": "ex_005557",
"source_idx": 5557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3923,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{(n)}=\\frac{2\\cdotn!}{(1-x)^{n+1}}",
"budget": 3138
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005557",
"normalized_example_id": "ex_005557",
"source_idx": 5557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3923,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{(n)}=\\frac{2\\cdotn!}{(1-x)^{n+1}}",
"budget": 3923
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005557",
"normalized_example_id": "ex_005557",
"source_idx": 5557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3923,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{n+1}C_{2n}^{n}",
"budget": 726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005558",
"normalized_example_id": "ex_005558",
"source_idx": 5558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1210,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{n+1}C_{2n}^{n}",
"budget": 968
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005558",
"normalized_example_id": "ex_005558",
"source_idx": 5558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1210,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{n+1}C_{2n}^{n}",
"budget": 1210
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005558",
"normalized_example_id": "ex_005558",
"source_idx": 5558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1210,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\lambda=0.2",
"budget": 1801
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005560",
"normalized_example_id": "ex_005560",
"source_idx": 5560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\lambda=0.2",
"budget": 2401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005560",
"normalized_example_id": "ex_005560",
"source_idx": 5560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\lambda=0.2",
"budget": 3001
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005560",
"normalized_example_id": "ex_005560",
"source_idx": 5560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.3\\sqrt{34}",
"budget": 2228
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005561",
"normalized_example_id": "ex_005561",
"source_idx": 5561,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3713,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.3\\sqrt{34}",
"budget": 2970
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005561",
"normalized_example_id": "ex_005561",
"source_idx": 5561,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3713,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.3\\sqrt{34}",
"budget": 3713
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005561",
"normalized_example_id": "ex_005561",
"source_idx": 5561,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3713,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1986",
"budget": 2243
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005562",
"normalized_example_id": "ex_005562",
"source_idx": 5562,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3739,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1986",
"budget": 2991
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005562",
"normalized_example_id": "ex_005562",
"source_idx": 5562,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3739,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1986",
"budget": 3739
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005562",
"normalized_example_id": "ex_005562",
"source_idx": 5562,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3739,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "272",
"budget": 3314
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005564",
"normalized_example_id": "ex_005564",
"source_idx": 5564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5524,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "272",
"budget": 4419
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005564",
"normalized_example_id": "ex_005564",
"source_idx": 5564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5524,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "272",
"budget": 5524
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005564",
"normalized_example_id": "ex_005564",
"source_idx": 5564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5524,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{(n-1)^n}",
"budget": 3025
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005565",
"normalized_example_id": "ex_005565",
"source_idx": 5565,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5042,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{(n-1)^n}",
"budget": 4034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005565",
"normalized_example_id": "ex_005565",
"source_idx": 5565,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5042,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{(n-1)^n}",
"budget": 5042
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005565",
"normalized_example_id": "ex_005565",
"source_idx": 5565,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5042,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 4229
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005566",
"normalized_example_id": "ex_005566",
"source_idx": 5566,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7049,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 5639
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005566",
"normalized_example_id": "ex_005566",
"source_idx": 5566,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7049,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 7049
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005566",
"normalized_example_id": "ex_005566",
"source_idx": 5566,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7049,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,1,1,1),(-1,-1,-1,3)",
"budget": 2758
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005568",
"normalized_example_id": "ex_005568",
"source_idx": 5568,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,1,1,1),(-1,-1,-1,3)",
"budget": 3678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005568",
"normalized_example_id": "ex_005568",
"source_idx": 5568,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,1,1,1),(-1,-1,-1,3)",
"budget": 4597
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005568",
"normalized_example_id": "ex_005568",
"source_idx": 5568,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "X=\\{a, 2a\\}",
"budget": 2604
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005569",
"normalized_example_id": "ex_005569",
"source_idx": 5569,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4340,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "X=\\{a, 2a\\}",
"budget": 3472
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005569",
"normalized_example_id": "ex_005569",
"source_idx": 5569,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4340,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "X=\\{a, 2a\\}",
"budget": 4340
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005569",
"normalized_example_id": "ex_005569",
"source_idx": 5569,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4340,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sin^{3}x}{3}-\\frac{\\sin^{5}x}{5}+C",
"budget": 733
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005579",
"normalized_example_id": "ex_005579",
"source_idx": 5579,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sin^{3}x}{3}-\\frac{\\sin^{5}x}{5}+C",
"budget": 977
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005579",
"normalized_example_id": "ex_005579",
"source_idx": 5579,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sin^{3}x}{3}-\\frac{\\sin^{5}x}{5}+C",
"budget": 1221
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005579",
"normalized_example_id": "ex_005579",
"source_idx": 5579,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,4or4,2",
"budget": 4641
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005582",
"normalized_example_id": "ex_005582",
"source_idx": 5582,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7735,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,4or4,2",
"budget": 6188
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005582",
"normalized_example_id": "ex_005582",
"source_idx": 5582,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7735,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,4or4,2",
"budget": 7735
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005582",
"normalized_example_id": "ex_005582",
"source_idx": 5582,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7735,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 1860
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005584",
"normalized_example_id": "ex_005584",
"source_idx": 5584,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3100,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 2480
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005584",
"normalized_example_id": "ex_005584",
"source_idx": 5584,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3100,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 3100
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005584",
"normalized_example_id": "ex_005584",
"source_idx": 5584,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3100,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2813
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005587",
"normalized_example_id": "ex_005587",
"source_idx": 5587,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4688,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3750
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005587",
"normalized_example_id": "ex_005587",
"source_idx": 5587,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4688,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4688
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005587",
"normalized_example_id": "ex_005587",
"source_idx": 5587,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4688,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4826
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005588",
"normalized_example_id": "ex_005588",
"source_idx": 5588,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8043,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6434
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005588",
"normalized_example_id": "ex_005588",
"source_idx": 5588,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8043,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8043
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005588",
"normalized_example_id": "ex_005588",
"source_idx": 5588,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8043,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 2105
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005589",
"normalized_example_id": "ex_005589",
"source_idx": 5589,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3508,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 2806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005589",
"normalized_example_id": "ex_005589",
"source_idx": 5589,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3508,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 3508
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005589",
"normalized_example_id": "ex_005589",
"source_idx": 5589,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3508,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 4188
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005590",
"normalized_example_id": "ex_005590",
"source_idx": 5590,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6980,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 5584
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005590",
"normalized_example_id": "ex_005590",
"source_idx": 5590,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6980,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 6980
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005590",
"normalized_example_id": "ex_005590",
"source_idx": 5590,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6980,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{3}",
"budget": 2363
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005592",
"normalized_example_id": "ex_005592",
"source_idx": 5592,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3938,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{3}",
"budget": 3150
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005592",
"normalized_example_id": "ex_005592",
"source_idx": 5592,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3938,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{3}",
"budget": 3938
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005592",
"normalized_example_id": "ex_005592",
"source_idx": 5592,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3938,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "125",
"budget": 3876
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005594",
"normalized_example_id": "ex_005594",
"source_idx": 5594,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6460,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "125",
"budget": 5168
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005594",
"normalized_example_id": "ex_005594",
"source_idx": 5594,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6460,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "125",
"budget": 6460
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005594",
"normalized_example_id": "ex_005594",
"source_idx": 5594,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6460,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{50}{37}",
"budget": 3737
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005595",
"normalized_example_id": "ex_005595",
"source_idx": 5595,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{50}{37}",
"budget": 4983
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005595",
"normalized_example_id": "ex_005595",
"source_idx": 5595,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{50}{37}",
"budget": 6229
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005595",
"normalized_example_id": "ex_005595",
"source_idx": 5595,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6229,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10\\frac{5}{41}",
"budget": 2365
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005598",
"normalized_example_id": "ex_005598",
"source_idx": 5598,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10\\frac{5}{41}",
"budget": 3154
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005598",
"normalized_example_id": "ex_005598",
"source_idx": 5598,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10\\frac{5}{41}",
"budget": 3942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005598",
"normalized_example_id": "ex_005598",
"source_idx": 5598,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)=0, f(x)=\\frac{1}{2}, f(x)=x^{2}",
"budget": 5944
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005599",
"normalized_example_id": "ex_005599",
"source_idx": 5599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9906,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)=0, f(x)=\\frac{1}{2}, f(x)=x^{2}",
"budget": 7925
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005599",
"normalized_example_id": "ex_005599",
"source_idx": 5599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9906,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)=0, f(x)=\\frac{1}{2}, f(x)=x^{2}",
"budget": 9906
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005599",
"normalized_example_id": "ex_005599",
"source_idx": 5599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9906,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1519",
"budget": 2983
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005600",
"normalized_example_id": "ex_005600",
"source_idx": 5600,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4972,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1519",
"budget": 3978
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005600",
"normalized_example_id": "ex_005600",
"source_idx": 5600,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4972,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1519",
"budget": 4972
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005600",
"normalized_example_id": "ex_005600",
"source_idx": 5600,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4972,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4500
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005601",
"normalized_example_id": "ex_005601",
"source_idx": 5601,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7500,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6000
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005601",
"normalized_example_id": "ex_005601",
"source_idx": 5601,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7500,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7500
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005601",
"normalized_example_id": "ex_005601",
"source_idx": 5601,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7500,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{x-16}{24}",
"budget": 1160
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005603",
"normalized_example_id": "ex_005603",
"source_idx": 5603,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1933,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{x-16}{24}",
"budget": 1546
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005603",
"normalized_example_id": "ex_005603",
"source_idx": 5603,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1933,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{x-16}{24}",
"budget": 1933
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005603",
"normalized_example_id": "ex_005603",
"source_idx": 5603,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1933,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 842
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005604",
"normalized_example_id": "ex_005604",
"source_idx": 5604,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1404,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 1123
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005604",
"normalized_example_id": "ex_005604",
"source_idx": 5604,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1404,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 1404
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005604",
"normalized_example_id": "ex_005604",
"source_idx": 5604,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1404,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{e}",
"budget": 2692
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005605",
"normalized_example_id": "ex_005605",
"source_idx": 5605,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4487,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{e}",
"budget": 3590
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005605",
"normalized_example_id": "ex_005605",
"source_idx": 5605,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4487,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.