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": "(x, y, z)=(1,1,1),(-5,4,4),(4,-5,4),(4,4,-5)",
"budget": 3753
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001147",
"normalized_example_id": "ex_001147",
"source_idx": 1147,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6255,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)=(1,1,1),(-5,4,4),(4,-5,4),(4,4,-5)",
"budget": 5004
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001147",
"normalized_example_id": "ex_001147",
"source_idx": 1147,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6255,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)=(1,1,1),(-5,4,4),(4,-5,4),(4,4,-5)",
"budget": 6255
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001147",
"normalized_example_id": "ex_001147",
"source_idx": 1147,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6255,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "117",
"budget": 3626
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001150",
"normalized_example_id": "ex_001150",
"source_idx": 1150,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6043,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "117",
"budget": 4834
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001150",
"normalized_example_id": "ex_001150",
"source_idx": 1150,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6043,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "117",
"budget": 6043
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001150",
"normalized_example_id": "ex_001150",
"source_idx": 1150,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6043,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "29",
"budget": 628
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001151",
"normalized_example_id": "ex_001151",
"source_idx": 1151,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1047,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "29",
"budget": 838
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001151",
"normalized_example_id": "ex_001151",
"source_idx": 1151,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1047,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "29",
"budget": 1047
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001151",
"normalized_example_id": "ex_001151",
"source_idx": 1151,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1047,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{7}{10}",
"budget": 2044
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001155",
"normalized_example_id": "ex_001155",
"source_idx": 1155,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3407,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{7}{10}",
"budget": 2726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001155",
"normalized_example_id": "ex_001155",
"source_idx": 1155,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3407,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{7}{10}",
"budget": 3407
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001155",
"normalized_example_id": "ex_001155",
"source_idx": 1155,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3407,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2164
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001156",
"normalized_example_id": "ex_001156",
"source_idx": 1156,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3606,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2885
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001156",
"normalized_example_id": "ex_001156",
"source_idx": 1156,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3606,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3606
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001156",
"normalized_example_id": "ex_001156",
"source_idx": 1156,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3606,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,8,17,18,26,27",
"budget": 3331
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001158",
"normalized_example_id": "ex_001158",
"source_idx": 1158,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5551,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,8,17,18,26,27",
"budget": 4441
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001158",
"normalized_example_id": "ex_001158",
"source_idx": 1158,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5551,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,8,17,18,26,27",
"budget": 5551
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001158",
"normalized_example_id": "ex_001158",
"source_idx": 1158,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5551,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}e^{-\\frac{1}{3}}",
"budget": 3764
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001162",
"normalized_example_id": "ex_001162",
"source_idx": 1162,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6274,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}e^{-\\frac{1}{3}}",
"budget": 5019
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001162",
"normalized_example_id": "ex_001162",
"source_idx": 1162,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6274,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}e^{-\\frac{1}{3}}",
"budget": 6274
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001162",
"normalized_example_id": "ex_001162",
"source_idx": 1162,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6274,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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) = 2x + 1",
"budget": 4744
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001163",
"normalized_example_id": "ex_001163",
"source_idx": 1163,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7906,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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) = 2x + 1",
"budget": 6325
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001163",
"normalized_example_id": "ex_001163",
"source_idx": 1163,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7906,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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) = 2x + 1",
"budget": 7906
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001163",
"normalized_example_id": "ex_001163",
"source_idx": 1163,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7906,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1235
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001164",
"normalized_example_id": "ex_001164",
"source_idx": 1164,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2059,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1647
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001164",
"normalized_example_id": "ex_001164",
"source_idx": 1164,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2059,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2059
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001164",
"normalized_example_id": "ex_001164",
"source_idx": 1164,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2059,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "61",
"budget": 2466
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001165",
"normalized_example_id": "ex_001165",
"source_idx": 1165,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "61",
"budget": 3288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001165",
"normalized_example_id": "ex_001165",
"source_idx": 1165,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "61",
"budget": 4110
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001165",
"normalized_example_id": "ex_001165",
"source_idx": 1165,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 881
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001166",
"normalized_example_id": "ex_001166",
"source_idx": 1166,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1469,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 1175
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001166",
"normalized_example_id": "ex_001166",
"source_idx": 1166,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1469,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 1469
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001166",
"normalized_example_id": "ex_001166",
"source_idx": 1166,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1469,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,17),(0,-3),(3,12),(-1,2),(6,9),(-4,5),(11,8),(-9,6)",
"budget": 1072
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001167",
"normalized_example_id": "ex_001167",
"source_idx": 1167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1786,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,17),(0,-3),(3,12),(-1,2),(6,9),(-4,5),(11,8),(-9,6)",
"budget": 1429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001167",
"normalized_example_id": "ex_001167",
"source_idx": 1167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1786,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,17),(0,-3),(3,12),(-1,2),(6,9),(-4,5),(11,8),(-9,6)",
"budget": 1786
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001167",
"normalized_example_id": "ex_001167",
"source_idx": 1167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1786,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{3}}{2}+\\frac{\\pi}{3}",
"budget": 4689
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001168",
"normalized_example_id": "ex_001168",
"source_idx": 1168,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7815,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{3}}{2}+\\frac{\\pi}{3}",
"budget": 6252
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001168",
"normalized_example_id": "ex_001168",
"source_idx": 1168,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7815,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{3}}{2}+\\frac{\\pi}{3}",
"budget": 7815
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001168",
"normalized_example_id": "ex_001168",
"source_idx": 1168,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7815,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "105",
"budget": 4574
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001169",
"normalized_example_id": "ex_001169",
"source_idx": 1169,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7624,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "105",
"budget": 6099
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001169",
"normalized_example_id": "ex_001169",
"source_idx": 1169,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7624,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "105",
"budget": 7624
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001169",
"normalized_example_id": "ex_001169",
"source_idx": 1169,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7624,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30000",
"budget": 2935
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001174",
"normalized_example_id": "ex_001174",
"source_idx": 1174,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4891,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30000",
"budget": 3913
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001174",
"normalized_example_id": "ex_001174",
"source_idx": 1174,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4891,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30000",
"budget": 4891
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001174",
"normalized_example_id": "ex_001174",
"source_idx": 1174,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4891,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{n+1}[(\\frac{3}{2})^{n+1}-1]",
"budget": 5708
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001175",
"normalized_example_id": "ex_001175",
"source_idx": 1175,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9514,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{n+1}[(\\frac{3}{2})^{n+1}-1]",
"budget": 7611
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001175",
"normalized_example_id": "ex_001175",
"source_idx": 1175,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9514,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{n+1}[(\\frac{3}{2})^{n+1}-1]",
"budget": 9514
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001175",
"normalized_example_id": "ex_001175",
"source_idx": 1175,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9514,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 1439
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001176",
"normalized_example_id": "ex_001176",
"source_idx": 1176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 1918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001176",
"normalized_example_id": "ex_001176",
"source_idx": 1176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 2398
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001176",
"normalized_example_id": "ex_001176",
"source_idx": 1176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{k^{2}+k+1}{(1+k)^{2}}",
"budget": 4010
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001178",
"normalized_example_id": "ex_001178",
"source_idx": 1178,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6683,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{k^{2}+k+1}{(1+k)^{2}}",
"budget": 5346
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001178",
"normalized_example_id": "ex_001178",
"source_idx": 1178,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6683,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{k^{2}+k+1}{(1+k)^{2}}",
"budget": 6683
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001178",
"normalized_example_id": "ex_001178",
"source_idx": 1178,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6683,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10},+\\infty)",
"budget": 4364
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001179",
"normalized_example_id": "ex_001179",
"source_idx": 1179,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7273,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10},+\\infty)",
"budget": 5818
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001179",
"normalized_example_id": "ex_001179",
"source_idx": 1179,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7273,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10},+\\infty)",
"budget": 7273
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001179",
"normalized_example_id": "ex_001179",
"source_idx": 1179,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7273,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1011",
"budget": 4724
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001180",
"normalized_example_id": "ex_001180",
"source_idx": 1180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7873,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1011",
"budget": 6298
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001180",
"normalized_example_id": "ex_001180",
"source_idx": 1180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7873,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1011",
"budget": 7873
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001180",
"normalized_example_id": "ex_001180",
"source_idx": 1180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7873,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1837
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001183",
"normalized_example_id": "ex_001183",
"source_idx": 1183,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3061,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2449
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001183",
"normalized_example_id": "ex_001183",
"source_idx": 1183,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3061,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3061
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001183",
"normalized_example_id": "ex_001183",
"source_idx": 1183,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3061,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "26",
"budget": 2479
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001184",
"normalized_example_id": "ex_001184",
"source_idx": 1184,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4132,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "26",
"budget": 3306
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001184",
"normalized_example_id": "ex_001184",
"source_idx": 1184,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4132,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "26",
"budget": 4132
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001184",
"normalized_example_id": "ex_001184",
"source_idx": 1184,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4132,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "67.6\\mathrm{~atm}",
"budget": 5835
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001186",
"normalized_example_id": "ex_001186",
"source_idx": 1186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9725,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "67.6\\mathrm{~atm}",
"budget": 7780
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001186",
"normalized_example_id": "ex_001186",
"source_idx": 1186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9725,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "67.6\\mathrm{~atm}",
"budget": 9725
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001186",
"normalized_example_id": "ex_001186",
"source_idx": 1186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9725,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 1063
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001187",
"normalized_example_id": "ex_001187",
"source_idx": 1187,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1771,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 1417
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001187",
"normalized_example_id": "ex_001187",
"source_idx": 1187,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1771,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 1771
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001187",
"normalized_example_id": "ex_001187",
"source_idx": 1187,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1771,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 958
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001190",
"normalized_example_id": "ex_001190",
"source_idx": 1190,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 1278
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001190",
"normalized_example_id": "ex_001190",
"source_idx": 1190,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 1597
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001190",
"normalized_example_id": "ex_001190",
"source_idx": 1190,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "780",
"budget": 4657
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001191",
"normalized_example_id": "ex_001191",
"source_idx": 1191,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7761,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "780",
"budget": 6209
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001191",
"normalized_example_id": "ex_001191",
"source_idx": 1191,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7761,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "780",
"budget": 7761
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001191",
"normalized_example_id": "ex_001191",
"source_idx": 1191,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7761,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2001",
"budget": 5180
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001196",
"normalized_example_id": "ex_001196",
"source_idx": 1196,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8634,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2001",
"budget": 6907
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001196",
"normalized_example_id": "ex_001196",
"source_idx": 1196,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8634,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2001",
"budget": 8634
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001196",
"normalized_example_id": "ex_001196",
"source_idx": 1196,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8634,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1146
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001198",
"normalized_example_id": "ex_001198",
"source_idx": 1198,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1910,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1528
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001198",
"normalized_example_id": "ex_001198",
"source_idx": 1198,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1910,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1910
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001198",
"normalized_example_id": "ex_001198",
"source_idx": 1198,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1910,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 715
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001200",
"normalized_example_id": "ex_001200",
"source_idx": 1200,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1191,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 953
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001200",
"normalized_example_id": "ex_001200",
"source_idx": 1200,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1191,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1191
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001200",
"normalized_example_id": "ex_001200",
"source_idx": 1200,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1191,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2n+n^{2}}{3}",
"budget": 2407
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001202",
"normalized_example_id": "ex_001202",
"source_idx": 1202,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4012,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2n+n^{2}}{3}",
"budget": 3210
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001202",
"normalized_example_id": "ex_001202",
"source_idx": 1202,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4012,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2n+n^{2}}{3}",
"budget": 4012
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001202",
"normalized_example_id": "ex_001202",
"source_idx": 1202,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4012,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3.6",
"budget": 993
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001203",
"normalized_example_id": "ex_001203",
"source_idx": 1203,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1655,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3.6",
"budget": 1324
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001203",
"normalized_example_id": "ex_001203",
"source_idx": 1203,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1655,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3.6",
"budget": 1655
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001203",
"normalized_example_id": "ex_001203",
"source_idx": 1203,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1655,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(B)}\\\\frac{5}{3}",
"budget": 614
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001205",
"normalized_example_id": "ex_001205",
"source_idx": 1205,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1024,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(B)}\\\\frac{5}{3}",
"budget": 819
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001205",
"normalized_example_id": "ex_001205",
"source_idx": 1205,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1024,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(B)}\\\\frac{5}{3}",
"budget": 1024
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001205",
"normalized_example_id": "ex_001205",
"source_idx": 1205,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1024,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1267
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001210",
"normalized_example_id": "ex_001210",
"source_idx": 1210,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2112,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1690
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001210",
"normalized_example_id": "ex_001210",
"source_idx": 1210,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2112,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2112
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001210",
"normalized_example_id": "ex_001210",
"source_idx": 1210,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2112,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "No",
"budget": 3919
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001211",
"normalized_example_id": "ex_001211",
"source_idx": 1211,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6531,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.