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": "\\frac{1}{2}n(n+1)",
"budget": 3173
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006202",
"normalized_example_id": "ex_006202",
"source_idx": 6202,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}n(n+1)",
"budget": 4230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006202",
"normalized_example_id": "ex_006202",
"source_idx": 6202,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}n(n+1)",
"budget": 5288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006202",
"normalized_example_id": "ex_006202",
"source_idx": 6202,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "511",
"budget": 3899
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006203",
"normalized_example_id": "ex_006203",
"source_idx": 6203,
"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": "511",
"budget": 5198
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006203",
"normalized_example_id": "ex_006203",
"source_idx": 6203,
"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": "511",
"budget": 6498
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006203",
"normalized_example_id": "ex_006203",
"source_idx": 6203,
"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": "9",
"budget": 2239
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006207",
"normalized_example_id": "ex_006207",
"source_idx": 6207,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3731,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2985
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006207",
"normalized_example_id": "ex_006207",
"source_idx": 6207,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3731,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3731
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006207",
"normalized_example_id": "ex_006207",
"source_idx": 6207,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3731,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\sqrt{2} + 1}",
"budget": 934
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006210",
"normalized_example_id": "ex_006210",
"source_idx": 6210,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1556,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\sqrt{2} + 1}",
"budget": 1245
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006210",
"normalized_example_id": "ex_006210",
"source_idx": 6210,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1556,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\sqrt{2} + 1}",
"budget": 1556
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006210",
"normalized_example_id": "ex_006210",
"source_idx": 6210,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1556,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 5563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006211",
"normalized_example_id": "ex_006211",
"source_idx": 6211,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9271,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 7417
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006211",
"normalized_example_id": "ex_006211",
"source_idx": 6211,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9271,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 9271
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006211",
"normalized_example_id": "ex_006211",
"source_idx": 6211,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9271,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[\\frac{\\sqrt{5}}{5},\\frac{1}{2}]",
"budget": 4453
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006212",
"normalized_example_id": "ex_006212",
"source_idx": 6212,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7422,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[\\frac{\\sqrt{5}}{5},\\frac{1}{2}]",
"budget": 5938
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006212",
"normalized_example_id": "ex_006212",
"source_idx": 6212,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7422,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[\\frac{\\sqrt{5}}{5},\\frac{1}{2}]",
"budget": 7422
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006212",
"normalized_example_id": "ex_006212",
"source_idx": 6212,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7422,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "254",
"budget": 5726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006218",
"normalized_example_id": "ex_006218",
"source_idx": 6218,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9543,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "254",
"budget": 7634
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006218",
"normalized_example_id": "ex_006218",
"source_idx": 6218,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9543,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "254",
"budget": 9543
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006218",
"normalized_example_id": "ex_006218",
"source_idx": 6218,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9543,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{329}{100}",
"budget": 5057
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006223",
"normalized_example_id": "ex_006223",
"source_idx": 6223,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{329}{100}",
"budget": 6743
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006223",
"normalized_example_id": "ex_006223",
"source_idx": 6223,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{329}{100}",
"budget": 8429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006223",
"normalized_example_id": "ex_006223",
"source_idx": 6223,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3k}{k^{2}-2}",
"budget": 3066
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006224",
"normalized_example_id": "ex_006224",
"source_idx": 6224,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3k}{k^{2}-2}",
"budget": 4088
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006224",
"normalized_example_id": "ex_006224",
"source_idx": 6224,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3k}{k^{2}-2}",
"budget": 5110
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006224",
"normalized_example_id": "ex_006224",
"source_idx": 6224,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y,z)=(2,1,2)",
"budget": 4408
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006225",
"normalized_example_id": "ex_006225",
"source_idx": 6225,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7347,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y,z)=(2,1,2)",
"budget": 5878
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006225",
"normalized_example_id": "ex_006225",
"source_idx": 6225,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7347,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y,z)=(2,1,2)",
"budget": 7347
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006225",
"normalized_example_id": "ex_006225",
"source_idx": 6225,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7347,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_1=0,x_2=1",
"budget": 1585
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006226",
"normalized_example_id": "ex_006226",
"source_idx": 6226,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2641,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_1=0,x_2=1",
"budget": 2113
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006226",
"normalized_example_id": "ex_006226",
"source_idx": 6226,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2641,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_1=0,x_2=1",
"budget": 2641
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006226",
"normalized_example_id": "ex_006226",
"source_idx": 6226,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2641,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3994001",
"budget": 1663
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006227",
"normalized_example_id": "ex_006227",
"source_idx": 6227,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2771,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3994001",
"budget": 2217
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006227",
"normalized_example_id": "ex_006227",
"source_idx": 6227,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2771,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3994001",
"budget": 2771
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006227",
"normalized_example_id": "ex_006227",
"source_idx": 6227,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2771,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 3392
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006234",
"normalized_example_id": "ex_006234",
"source_idx": 6234,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5654,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 4523
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006234",
"normalized_example_id": "ex_006234",
"source_idx": 6234,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5654,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 5654
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006234",
"normalized_example_id": "ex_006234",
"source_idx": 6234,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5654,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4052169",
"budget": 1360
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006240",
"normalized_example_id": "ex_006240",
"source_idx": 6240,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2267,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4052169",
"budget": 1814
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006240",
"normalized_example_id": "ex_006240",
"source_idx": 6240,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2267,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4052169",
"budget": 2267
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006240",
"normalized_example_id": "ex_006240",
"source_idx": 6240,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2267,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10200",
"budget": 905
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006241",
"normalized_example_id": "ex_006241",
"source_idx": 6241,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1508,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10200",
"budget": 1206
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006241",
"normalized_example_id": "ex_006241",
"source_idx": 6241,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1508,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10200",
"budget": 1508
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006241",
"normalized_example_id": "ex_006241",
"source_idx": 6241,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1508,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 6071
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006242",
"normalized_example_id": "ex_006242",
"source_idx": 6242,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10118,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 8094
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006242",
"normalized_example_id": "ex_006242",
"source_idx": 6242,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10118,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 10118
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006242",
"normalized_example_id": "ex_006242",
"source_idx": 6242,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10118,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 728
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006243",
"normalized_example_id": "ex_006243",
"source_idx": 6243,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1214,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 971
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006243",
"normalized_example_id": "ex_006243",
"source_idx": 6243,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1214,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 1214
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006243",
"normalized_example_id": "ex_006243",
"source_idx": 6243,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1214,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "243",
"budget": 1289
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006244",
"normalized_example_id": "ex_006244",
"source_idx": 6244,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2149,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "243",
"budget": 1719
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006244",
"normalized_example_id": "ex_006244",
"source_idx": 6244,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2149,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "243",
"budget": 2149
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006244",
"normalized_example_id": "ex_006244",
"source_idx": 6244,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2149,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4}",
"budget": 3769
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006246",
"normalized_example_id": "ex_006246",
"source_idx": 6246,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6281,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4}",
"budget": 5025
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006246",
"normalized_example_id": "ex_006246",
"source_idx": 6246,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6281,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4}",
"budget": 6281
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006246",
"normalized_example_id": "ex_006246",
"source_idx": 6246,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6281,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 5398
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006247",
"normalized_example_id": "ex_006247",
"source_idx": 6247,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8997,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 7198
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006247",
"normalized_example_id": "ex_006247",
"source_idx": 6247,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8997,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 8997
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006247",
"normalized_example_id": "ex_006247",
"source_idx": 6247,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8997,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{15\\sqrt{7}}{16}",
"budget": 3290
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006249",
"normalized_example_id": "ex_006249",
"source_idx": 6249,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5484,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{15\\sqrt{7}}{16}",
"budget": 4387
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006249",
"normalized_example_id": "ex_006249",
"source_idx": 6249,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5484,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{15\\sqrt{7}}{16}",
"budget": 5484
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006249",
"normalized_example_id": "ex_006249",
"source_idx": 6249,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5484,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12\\cdot28",
"budget": 2071
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006250",
"normalized_example_id": "ex_006250",
"source_idx": 6250,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3451,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12\\cdot28",
"budget": 2761
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006250",
"normalized_example_id": "ex_006250",
"source_idx": 6250,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3451,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12\\cdot28",
"budget": 3451
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006250",
"normalized_example_id": "ex_006250",
"source_idx": 6250,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3451,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\cdot5^{5}",
"budget": 932
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006251",
"normalized_example_id": "ex_006251",
"source_idx": 6251,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1553,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\cdot5^{5}",
"budget": 1242
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006251",
"normalized_example_id": "ex_006251",
"source_idx": 6251,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1553,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\cdot5^{5}",
"budget": 1553
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006251",
"normalized_example_id": "ex_006251",
"source_idx": 6251,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1553,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006252",
"normalized_example_id": "ex_006252",
"source_idx": 6252,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3237,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2590
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006252",
"normalized_example_id": "ex_006252",
"source_idx": 6252,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3237,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3237
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006252",
"normalized_example_id": "ex_006252",
"source_idx": 6252,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3237,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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} \\sqrt{a^{2}+b^{2}}",
"budget": 2138
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006253",
"normalized_example_id": "ex_006253",
"source_idx": 6253,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3563,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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} \\sqrt{a^{2}+b^{2}}",
"budget": 2850
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006253",
"normalized_example_id": "ex_006253",
"source_idx": 6253,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3563,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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} \\sqrt{a^{2}+b^{2}}",
"budget": 3563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006253",
"normalized_example_id": "ex_006253",
"source_idx": 6253,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3563,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "508",
"budget": 1189
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006254",
"normalized_example_id": "ex_006254",
"source_idx": 6254,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1982,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "508",
"budget": 1586
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006254",
"normalized_example_id": "ex_006254",
"source_idx": 6254,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1982,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "508",
"budget": 1982
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006254",
"normalized_example_id": "ex_006254",
"source_idx": 6254,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1982,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 2036
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006255",
"normalized_example_id": "ex_006255",
"source_idx": 6255,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 2715
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006255",
"normalized_example_id": "ex_006255",
"source_idx": 6255,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 3394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006255",
"normalized_example_id": "ex_006255",
"source_idx": 6255,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "62\\frac{2}{9},46\\frac{2}{3}",
"budget": 2331
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006256",
"normalized_example_id": "ex_006256",
"source_idx": 6256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3885,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "62\\frac{2}{9},46\\frac{2}{3}",
"budget": 3108
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006256",
"normalized_example_id": "ex_006256",
"source_idx": 6256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3885,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "62\\frac{2}{9},46\\frac{2}{3}",
"budget": 3885
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006256",
"normalized_example_id": "ex_006256",
"source_idx": 6256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3885,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4200",
"budget": 3322
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006258",
"normalized_example_id": "ex_006258",
"source_idx": 6258,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5537,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4200",
"budget": 4430
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006258",
"normalized_example_id": "ex_006258",
"source_idx": 6258,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5537,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4200",
"budget": 5537
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006258",
"normalized_example_id": "ex_006258",
"source_idx": 6258,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5537,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2281
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006264",
"normalized_example_id": "ex_006264",
"source_idx": 6264,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3801,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3041
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006264",
"normalized_example_id": "ex_006264",
"source_idx": 6264,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3801,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3801
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006264",
"normalized_example_id": "ex_006264",
"source_idx": 6264,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3801,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2x^{2}-2x+1}{4}\\sin2x+\\frac{2x-1}{4}\\cos2x+C",
"budget": 1897
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006266",
"normalized_example_id": "ex_006266",
"source_idx": 6266,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3161,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2x^{2}-2x+1}{4}\\sin2x+\\frac{2x-1}{4}\\cos2x+C",
"budget": 2529
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006266",
"normalized_example_id": "ex_006266",
"source_idx": 6266,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3161,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2x^{2}-2x+1}{4}\\sin2x+\\frac{2x-1}{4}\\cos2x+C",
"budget": 3161
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006266",
"normalized_example_id": "ex_006266",
"source_idx": 6266,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3161,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 3889
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006267",
"normalized_example_id": "ex_006267",
"source_idx": 6267,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6482,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 5186
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006267",
"normalized_example_id": "ex_006267",
"source_idx": 6267,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6482,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 6482
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006267",
"normalized_example_id": "ex_006267",
"source_idx": 6267,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6482,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{11}}{\\sqrt{3}+3 \\sqrt{15}}",
"budget": 2617
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006268",
"normalized_example_id": "ex_006268",
"source_idx": 6268,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4361,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{11}}{\\sqrt{3}+3 \\sqrt{15}}",
"budget": 3489
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006268",
"normalized_example_id": "ex_006268",
"source_idx": 6268,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4361,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{11}}{\\sqrt{3}+3 \\sqrt{15}}",
"budget": 4361
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006268",
"normalized_example_id": "ex_006268",
"source_idx": 6268,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4361,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90",
"budget": 2275
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006271",
"normalized_example_id": "ex_006271",
"source_idx": 6271,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3792,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.