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=\\left(1-\\frac{\\sqrt{2}}{2}\\right) a",
"budget": 1067
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001578",
"normalized_example_id": "ex_001578",
"source_idx": 1578,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1334,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\left(1-\\frac{\\sqrt{2}}{2}\\right) a",
"budget": 1334
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001578",
"normalized_example_id": "ex_001578",
"source_idx": 1578,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1334,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2002",
"budget": 1646
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001583",
"normalized_example_id": "ex_001583",
"source_idx": 1583,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2744,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2002",
"budget": 2195
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001583",
"normalized_example_id": "ex_001583",
"source_idx": 1583,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2744,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2002",
"budget": 2744
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001583",
"normalized_example_id": "ex_001583",
"source_idx": 1583,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2744,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\in(0;1)\\cup(1;5/4)\\cup(5/4;3/2)",
"budget": 3251
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001586",
"normalized_example_id": "ex_001586",
"source_idx": 1586,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5418,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\in(0;1)\\cup(1;5/4)\\cup(5/4;3/2)",
"budget": 4334
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001586",
"normalized_example_id": "ex_001586",
"source_idx": 1586,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5418,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\in(0;1)\\cup(1;5/4)\\cup(5/4;3/2)",
"budget": 5418
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001586",
"normalized_example_id": "ex_001586",
"source_idx": 1586,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5418,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 2013
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001587",
"normalized_example_id": "ex_001587",
"source_idx": 1587,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3355,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 2684
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001587",
"normalized_example_id": "ex_001587",
"source_idx": 1587,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3355,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 3355
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001587",
"normalized_example_id": "ex_001587",
"source_idx": 1587,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3355,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2014",
"budget": 2053
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001589",
"normalized_example_id": "ex_001589",
"source_idx": 1589,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3421,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2014",
"budget": 2737
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001589",
"normalized_example_id": "ex_001589",
"source_idx": 1589,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3421,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2014",
"budget": 3421
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001589",
"normalized_example_id": "ex_001589",
"source_idx": 1589,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3421,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "510",
"budget": 2815
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001591",
"normalized_example_id": "ex_001591",
"source_idx": 1591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4691,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "510",
"budget": 3753
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001591",
"normalized_example_id": "ex_001591",
"source_idx": 1591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4691,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "510",
"budget": 4691
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001591",
"normalized_example_id": "ex_001591",
"source_idx": 1591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4691,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\cosx}",
"budget": 4378
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001593",
"normalized_example_id": "ex_001593",
"source_idx": 1593,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7296,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\cosx}",
"budget": 5837
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001593",
"normalized_example_id": "ex_001593",
"source_idx": 1593,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7296,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\cosx}",
"budget": 7296
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001593",
"normalized_example_id": "ex_001593",
"source_idx": 1593,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7296,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0,1,2",
"budget": 5575
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001594",
"normalized_example_id": "ex_001594",
"source_idx": 1594,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9291,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0,1,2",
"budget": 7433
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001594",
"normalized_example_id": "ex_001594",
"source_idx": 1594,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9291,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0,1,2",
"budget": 9291
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001594",
"normalized_example_id": "ex_001594",
"source_idx": 1594,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9291,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\sqrt{2}",
"budget": 5401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001595",
"normalized_example_id": "ex_001595",
"source_idx": 1595,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9002,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\sqrt{2}",
"budget": 7202
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001595",
"normalized_example_id": "ex_001595",
"source_idx": 1595,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9002,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\sqrt{2}",
"budget": 9002
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001595",
"normalized_example_id": "ex_001595",
"source_idx": 1595,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9002,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4032,8064,12096,16128",
"budget": 1482
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001597",
"normalized_example_id": "ex_001597",
"source_idx": 1597,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2470,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4032,8064,12096,16128",
"budget": 1976
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001597",
"normalized_example_id": "ex_001597",
"source_idx": 1597,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2470,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4032,8064,12096,16128",
"budget": 2470
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001597",
"normalized_example_id": "ex_001597",
"source_idx": 1597,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2470,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24,40,56,72,88,104,120",
"budget": 2357
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001598",
"normalized_example_id": "ex_001598",
"source_idx": 1598,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3928,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24,40,56,72,88,104,120",
"budget": 3142
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001598",
"normalized_example_id": "ex_001598",
"source_idx": 1598,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3928,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24,40,56,72,88,104,120",
"budget": 3928
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001598",
"normalized_example_id": "ex_001598",
"source_idx": 1598,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3928,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3865
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001599",
"normalized_example_id": "ex_001599",
"source_idx": 1599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6441,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5153
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001599",
"normalized_example_id": "ex_001599",
"source_idx": 1599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6441,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6441
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001599",
"normalized_example_id": "ex_001599",
"source_idx": 1599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6441,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1496
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001601",
"normalized_example_id": "ex_001601",
"source_idx": 1601,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2493,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1994
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001601",
"normalized_example_id": "ex_001601",
"source_idx": 1601,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2493,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2493
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001601",
"normalized_example_id": "ex_001601",
"source_idx": 1601,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2493,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "360",
"budget": 726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001602",
"normalized_example_id": "ex_001602",
"source_idx": 1602,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1210,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "360",
"budget": 968
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001602",
"normalized_example_id": "ex_001602",
"source_idx": 1602,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1210,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "360",
"budget": 1210
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001602",
"normalized_example_id": "ex_001602",
"source_idx": 1602,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1210,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "53",
"budget": 3940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001603",
"normalized_example_id": "ex_001603",
"source_idx": 1603,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6566,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "53",
"budget": 5253
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001603",
"normalized_example_id": "ex_001603",
"source_idx": 1603,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6566,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "53",
"budget": 6566
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001603",
"normalized_example_id": "ex_001603",
"source_idx": 1603,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6566,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9792",
"budget": 2585
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001604",
"normalized_example_id": "ex_001604",
"source_idx": 1604,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4308,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9792",
"budget": 3446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001604",
"normalized_example_id": "ex_001604",
"source_idx": 1604,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4308,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9792",
"budget": 4308
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001604",
"normalized_example_id": "ex_001604",
"source_idx": 1604,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4308,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 1931
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001605",
"normalized_example_id": "ex_001605",
"source_idx": 1605,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 2575
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001605",
"normalized_example_id": "ex_001605",
"source_idx": 1605,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 3219
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001605",
"normalized_example_id": "ex_001605",
"source_idx": 1605,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a_n = n \\text{ for all } n \\in \\{1, 2, \\ldots, 1375\\}",
"budget": 4057
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001606",
"normalized_example_id": "ex_001606",
"source_idx": 1606,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6761,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a_n = n \\text{ for all } n \\in \\{1, 2, \\ldots, 1375\\}",
"budget": 5409
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001606",
"normalized_example_id": "ex_001606",
"source_idx": 1606,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6761,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a_n = n \\text{ for all } n \\in \\{1, 2, \\ldots, 1375\\}",
"budget": 6761
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001606",
"normalized_example_id": "ex_001606",
"source_idx": 1606,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6761,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2520",
"budget": 949
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001607",
"normalized_example_id": "ex_001607",
"source_idx": 1607,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1582,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2520",
"budget": 1266
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001607",
"normalized_example_id": "ex_001607",
"source_idx": 1607,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1582,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2520",
"budget": 1582
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001607",
"normalized_example_id": "ex_001607",
"source_idx": 1607,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1582,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4851",
"budget": 1048
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001608",
"normalized_example_id": "ex_001608",
"source_idx": 1608,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1747,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4851",
"budget": 1398
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001608",
"normalized_example_id": "ex_001608",
"source_idx": 1608,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1747,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4851",
"budget": 1747
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001608",
"normalized_example_id": "ex_001608",
"source_idx": 1608,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1747,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4169
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001609",
"normalized_example_id": "ex_001609",
"source_idx": 1609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6949,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5559
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001609",
"normalized_example_id": "ex_001609",
"source_idx": 1609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6949,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6949
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001609",
"normalized_example_id": "ex_001609",
"source_idx": 1609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6949,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "z_1=5,\\quadz_2=5i",
"budget": 3467
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001612",
"normalized_example_id": "ex_001612",
"source_idx": 1612,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5778,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "z_1=5,\\quadz_2=5i",
"budget": 4622
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001612",
"normalized_example_id": "ex_001612",
"source_idx": 1612,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5778,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "z_1=5,\\quadz_2=5i",
"budget": 5778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001612",
"normalized_example_id": "ex_001612",
"source_idx": 1612,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5778,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4736
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001614",
"normalized_example_id": "ex_001614",
"source_idx": 1614,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6314
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001614",
"normalized_example_id": "ex_001614",
"source_idx": 1614,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001614",
"normalized_example_id": "ex_001614",
"source_idx": 1614,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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!)^3",
"budget": 3352
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001615",
"normalized_example_id": "ex_001615",
"source_idx": 1615,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5587,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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!)^3",
"budget": 4470
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001615",
"normalized_example_id": "ex_001615",
"source_idx": 1615,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5587,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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!)^3",
"budget": 5587
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001615",
"normalized_example_id": "ex_001615",
"source_idx": 1615,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5587,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2255
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001616",
"normalized_example_id": "ex_001616",
"source_idx": 1616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3759,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001616",
"normalized_example_id": "ex_001616",
"source_idx": 1616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3759,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3759
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001616",
"normalized_example_id": "ex_001616",
"source_idx": 1616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3759,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "28",
"budget": 706
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001618",
"normalized_example_id": "ex_001618",
"source_idx": 1618,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1176,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "28",
"budget": 941
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001618",
"normalized_example_id": "ex_001618",
"source_idx": 1618,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1176,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "28",
"budget": 1176
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001618",
"normalized_example_id": "ex_001618",
"source_idx": 1618,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1176,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 634
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001620",
"normalized_example_id": "ex_001620",
"source_idx": 1620,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1056,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 845
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001620",
"normalized_example_id": "ex_001620",
"source_idx": 1620,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1056,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 1056
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001620",
"normalized_example_id": "ex_001620",
"source_idx": 1620,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1056,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 5401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001622",
"normalized_example_id": "ex_001622",
"source_idx": 1622,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 7201
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001622",
"normalized_example_id": "ex_001622",
"source_idx": 1622,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 9001
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001622",
"normalized_example_id": "ex_001622",
"source_idx": 1622,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001624",
"normalized_example_id": "ex_001624",
"source_idx": 1624,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6590,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5272
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001624",
"normalized_example_id": "ex_001624",
"source_idx": 1624,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6590,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6590
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001624",
"normalized_example_id": "ex_001624",
"source_idx": 1624,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6590,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a_{n}=3^{n}+n^{2}+3n+2",
"budget": 1760
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001627",
"normalized_example_id": "ex_001627",
"source_idx": 1627,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2933,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a_{n}=3^{n}+n^{2}+3n+2",
"budget": 2346
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001627",
"normalized_example_id": "ex_001627",
"source_idx": 1627,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2933,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a_{n}=3^{n}+n^{2}+3n+2",
"budget": 2933
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001627",
"normalized_example_id": "ex_001627",
"source_idx": 1627,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2933,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "{1,-1}",
"budget": 3262
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001628",
"normalized_example_id": "ex_001628",
"source_idx": 1628,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5436,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "{1,-1}",
"budget": 4349
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001628",
"normalized_example_id": "ex_001628",
"source_idx": 1628,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5436,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "{1,-1}",
"budget": 5436
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001628",
"normalized_example_id": "ex_001628",
"source_idx": 1628,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5436,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1510
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001630",
"normalized_example_id": "ex_001630",
"source_idx": 1630,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2516,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2013
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001630",
"normalized_example_id": "ex_001630",
"source_idx": 1630,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2516,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2516
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001630",
"normalized_example_id": "ex_001630",
"source_idx": 1630,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2516,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "42",
"budget": 1514
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001631",
"normalized_example_id": "ex_001631",
"source_idx": 1631,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2523,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "42",
"budget": 2018
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001631",
"normalized_example_id": "ex_001631",
"source_idx": 1631,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2523,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "42",
"budget": 2523
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001631",
"normalized_example_id": "ex_001631",
"source_idx": 1631,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2523,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4002",
"budget": 2209
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001632",
"normalized_example_id": "ex_001632",
"source_idx": 1632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3681,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4002",
"budget": 2945
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001632",
"normalized_example_id": "ex_001632",
"source_idx": 1632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3681,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.