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": "45",
"budget": 4631
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001691",
"normalized_example_id": "ex_001691",
"source_idx": 1691,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7719,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6175
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001691",
"normalized_example_id": "ex_001691",
"source_idx": 1691,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7719,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7719
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001691",
"normalized_example_id": "ex_001691",
"source_idx": 1691,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7719,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 5460
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001694",
"normalized_example_id": "ex_001694",
"source_idx": 1694,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9100,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 7280
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001694",
"normalized_example_id": "ex_001694",
"source_idx": 1694,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9100,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 9100
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001694",
"normalized_example_id": "ex_001694",
"source_idx": 1694,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9100,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "300 \\text{ meters}",
"budget": 1041
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001697",
"normalized_example_id": "ex_001697",
"source_idx": 1697,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1735,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "300 \\text{ meters}",
"budget": 1388
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001697",
"normalized_example_id": "ex_001697",
"source_idx": 1697,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1735,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "300 \\text{ meters}",
"budget": 1735
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001697",
"normalized_example_id": "ex_001697",
"source_idx": 1697,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1735,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "22",
"budget": 3559
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001698",
"normalized_example_id": "ex_001698",
"source_idx": 1698,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5932,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "22",
"budget": 4746
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001698",
"normalized_example_id": "ex_001698",
"source_idx": 1698,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5932,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "22",
"budget": 5932
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001698",
"normalized_example_id": "ex_001698",
"source_idx": 1698,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5932,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "444600",
"budget": 3651
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001699",
"normalized_example_id": "ex_001699",
"source_idx": 1699,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6085,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "444600",
"budget": 4868
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001699",
"normalized_example_id": "ex_001699",
"source_idx": 1699,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6085,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "444600",
"budget": 6085
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001699",
"normalized_example_id": "ex_001699",
"source_idx": 1699,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6085,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0,0),(-4,-8)",
"budget": 4386
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001701",
"normalized_example_id": "ex_001701",
"source_idx": 1701,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7310,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0,0),(-4,-8)",
"budget": 5848
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001701",
"normalized_example_id": "ex_001701",
"source_idx": 1701,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7310,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0,0),(-4,-8)",
"budget": 7310
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001701",
"normalized_example_id": "ex_001701",
"source_idx": 1701,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7310,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1011030",
"budget": 4203
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001702",
"normalized_example_id": "ex_001702",
"source_idx": 1702,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1011030",
"budget": 5604
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001702",
"normalized_example_id": "ex_001702",
"source_idx": 1702,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1011030",
"budget": 7005
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001702",
"normalized_example_id": "ex_001702",
"source_idx": 1702,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1488
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001703",
"normalized_example_id": "ex_001703",
"source_idx": 1703,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2480,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1984
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001703",
"normalized_example_id": "ex_001703",
"source_idx": 1703,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2480,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_001703",
"normalized_example_id": "ex_001703",
"source_idx": 1703,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2480,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-\\frac{7}{2}",
"budget": 1453
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001706",
"normalized_example_id": "ex_001706",
"source_idx": 1706,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2422,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-\\frac{7}{2}",
"budget": 1938
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001706",
"normalized_example_id": "ex_001706",
"source_idx": 1706,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2422,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-\\frac{7}{2}",
"budget": 2422
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001706",
"normalized_example_id": "ex_001706",
"source_idx": 1706,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2422,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 1528
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001707",
"normalized_example_id": "ex_001707",
"source_idx": 1707,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 2038
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001707",
"normalized_example_id": "ex_001707",
"source_idx": 1707,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 2547
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001707",
"normalized_example_id": "ex_001707",
"source_idx": 1707,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}",
"budget": 6077
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001709",
"normalized_example_id": "ex_001709",
"source_idx": 1709,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10129,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3}{2}",
"budget": 8103
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001709",
"normalized_example_id": "ex_001709",
"source_idx": 1709,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10129,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3}{2}",
"budget": 10129
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001709",
"normalized_example_id": "ex_001709",
"source_idx": 1709,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10129,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1-2^{-1/n}",
"budget": 2620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001714",
"normalized_example_id": "ex_001714",
"source_idx": 1714,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4366,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1-2^{-1/n}",
"budget": 3493
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001714",
"normalized_example_id": "ex_001714",
"source_idx": 1714,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4366,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1-2^{-1/n}",
"budget": 4366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001714",
"normalized_example_id": "ex_001714",
"source_idx": 1714,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4366,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "64",
"budget": 3662
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001717",
"normalized_example_id": "ex_001717",
"source_idx": 1717,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6104,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "64",
"budget": 4883
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001717",
"normalized_example_id": "ex_001717",
"source_idx": 1717,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6104,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "64",
"budget": 6104
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001717",
"normalized_example_id": "ex_001717",
"source_idx": 1717,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6104,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{n(n+1)}{2} + 1",
"budget": 5499
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001718",
"normalized_example_id": "ex_001718",
"source_idx": 1718,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9165,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{n(n+1)}{2} + 1",
"budget": 7332
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001718",
"normalized_example_id": "ex_001718",
"source_idx": 1718,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9165,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{n(n+1)}{2} + 1",
"budget": 9165
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001718",
"normalized_example_id": "ex_001718",
"source_idx": 1718,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9165,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4438
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001719",
"normalized_example_id": "ex_001719",
"source_idx": 1719,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7396,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5917
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001719",
"normalized_example_id": "ex_001719",
"source_idx": 1719,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7396,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7396
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001719",
"normalized_example_id": "ex_001719",
"source_idx": 1719,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7396,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 758
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001720",
"normalized_example_id": "ex_001720",
"source_idx": 1720,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1263,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 1010
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001720",
"normalized_example_id": "ex_001720",
"source_idx": 1720,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1263,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 1263
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001720",
"normalized_example_id": "ex_001720",
"source_idx": 1720,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1263,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2783
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001722",
"normalized_example_id": "ex_001722",
"source_idx": 1722,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3711
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001722",
"normalized_example_id": "ex_001722",
"source_idx": 1722,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4639
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001722",
"normalized_example_id": "ex_001722",
"source_idx": 1722,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\varphi=\\operatorname{arctg}\\frac{3}{4}",
"budget": 2089
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001723",
"normalized_example_id": "ex_001723",
"source_idx": 1723,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3481,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\varphi=\\operatorname{arctg}\\frac{3}{4}",
"budget": 2785
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001723",
"normalized_example_id": "ex_001723",
"source_idx": 1723,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3481,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\varphi=\\operatorname{arctg}\\frac{3}{4}",
"budget": 3481
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001723",
"normalized_example_id": "ex_001723",
"source_idx": 1723,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3481,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}",
"budget": 1404
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001725",
"normalized_example_id": "ex_001725",
"source_idx": 1725,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2340,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}",
"budget": 1872
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001725",
"normalized_example_id": "ex_001725",
"source_idx": 1725,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2340,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}",
"budget": 2340
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001725",
"normalized_example_id": "ex_001725",
"source_idx": 1725,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2340,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2963
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001726",
"normalized_example_id": "ex_001726",
"source_idx": 1726,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4939,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3951
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001726",
"normalized_example_id": "ex_001726",
"source_idx": 1726,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4939,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001726",
"normalized_example_id": "ex_001726",
"source_idx": 1726,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4939,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.04",
"budget": 3284
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001732",
"normalized_example_id": "ex_001732",
"source_idx": 1732,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5473,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.04",
"budget": 4378
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001732",
"normalized_example_id": "ex_001732",
"source_idx": 1732,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5473,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.04",
"budget": 5473
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001732",
"normalized_example_id": "ex_001732",
"source_idx": 1732,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5473,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{16}{5}",
"budget": 1045
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001734",
"normalized_example_id": "ex_001734",
"source_idx": 1734,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1742,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{16}{5}",
"budget": 1394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001734",
"normalized_example_id": "ex_001734",
"source_idx": 1734,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1742,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{16}{5}",
"budget": 1742
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001734",
"normalized_example_id": "ex_001734",
"source_idx": 1734,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1742,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6,11,21,41",
"budget": 695
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001735",
"normalized_example_id": "ex_001735",
"source_idx": 1735,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1158,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6,11,21,41",
"budget": 926
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001735",
"normalized_example_id": "ex_001735",
"source_idx": 1735,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1158,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6,11,21,41",
"budget": 1158
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001735",
"normalized_example_id": "ex_001735",
"source_idx": 1735,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1158,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19.48\\mathrm{gr}",
"budget": 1880
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001736",
"normalized_example_id": "ex_001736",
"source_idx": 1736,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3134,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19.48\\mathrm{gr}",
"budget": 2507
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001736",
"normalized_example_id": "ex_001736",
"source_idx": 1736,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3134,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19.48\\mathrm{gr}",
"budget": 3134
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001736",
"normalized_example_id": "ex_001736",
"source_idx": 1736,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3134,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{182}{729}",
"budget": 3224
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001739",
"normalized_example_id": "ex_001739",
"source_idx": 1739,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5374,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{182}{729}",
"budget": 4299
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001739",
"normalized_example_id": "ex_001739",
"source_idx": 1739,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5374,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{182}{729}",
"budget": 5374
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001739",
"normalized_example_id": "ex_001739",
"source_idx": 1739,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5374,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "178",
"budget": 3235
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001740",
"normalized_example_id": "ex_001740",
"source_idx": 1740,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5391,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "178",
"budget": 4313
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001740",
"normalized_example_id": "ex_001740",
"source_idx": 1740,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5391,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "178",
"budget": 5391
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001740",
"normalized_example_id": "ex_001740",
"source_idx": 1740,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5391,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "28",
"budget": 2009
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001742",
"normalized_example_id": "ex_001742",
"source_idx": 1742,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3348,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "28",
"budget": 2678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001742",
"normalized_example_id": "ex_001742",
"source_idx": 1742,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3348,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "28",
"budget": 3348
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001742",
"normalized_example_id": "ex_001742",
"source_idx": 1742,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3348,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32\\mathrm{~}^{2}",
"budget": 1276
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001744",
"normalized_example_id": "ex_001744",
"source_idx": 1744,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2126,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32\\mathrm{~}^{2}",
"budget": 1701
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001744",
"normalized_example_id": "ex_001744",
"source_idx": 1744,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2126,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32\\mathrm{~}^{2}",
"budget": 2126
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001744",
"normalized_example_id": "ex_001744",
"source_idx": 1744,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2126,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 4271
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001747",
"normalized_example_id": "ex_001747",
"source_idx": 1747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7118,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 5694
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001747",
"normalized_example_id": "ex_001747",
"source_idx": 1747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7118,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 7118
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001747",
"normalized_example_id": "ex_001747",
"source_idx": 1747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7118,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 1208
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001748",
"normalized_example_id": "ex_001748",
"source_idx": 1748,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2013,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 1610
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001748",
"normalized_example_id": "ex_001748",
"source_idx": 1748,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2013,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 2013
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001748",
"normalized_example_id": "ex_001748",
"source_idx": 1748,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2013,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10,20,25,50,100",
"budget": 3899
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001750",
"normalized_example_id": "ex_001750",
"source_idx": 1750,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6498,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10,20,25,50,100",
"budget": 5198
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001750",
"normalized_example_id": "ex_001750",
"source_idx": 1750,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6498,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10,20,25,50,100",
"budget": 6498
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001750",
"normalized_example_id": "ex_001750",
"source_idx": 1750,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6498,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2186",
"budget": 5890
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001752",
"normalized_example_id": "ex_001752",
"source_idx": 1752,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9817,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2186",
"budget": 7854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001752",
"normalized_example_id": "ex_001752",
"source_idx": 1752,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9817,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2186",
"budget": 9817
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001752",
"normalized_example_id": "ex_001752",
"source_idx": 1752,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9817,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 1505
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001755",
"normalized_example_id": "ex_001755",
"source_idx": 1755,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2509,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 2007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001755",
"normalized_example_id": "ex_001755",
"source_idx": 1755,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2509,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 2509
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001755",
"normalized_example_id": "ex_001755",
"source_idx": 1755,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2509,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{x^{2}+2007x-6028}{3(x-1)}",
"budget": 2842
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001756",
"normalized_example_id": "ex_001756",
"source_idx": 1756,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4737,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.