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": "0.178",
"budget": 2228
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003507",
"normalized_example_id": "ex_003507",
"source_idx": 3507,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.178",
"budget": 2785
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003507",
"normalized_example_id": "ex_003507",
"source_idx": 3507,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "298",
"budget": 2065
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003508",
"normalized_example_id": "ex_003508",
"source_idx": 3508,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3441,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "298",
"budget": 2753
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003508",
"normalized_example_id": "ex_003508",
"source_idx": 3508,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3441,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "298",
"budget": 3441
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003508",
"normalized_example_id": "ex_003508",
"source_idx": 3508,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3441,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4658
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003511",
"normalized_example_id": "ex_003511",
"source_idx": 3511,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7764,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6211
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003511",
"normalized_example_id": "ex_003511",
"source_idx": 3511,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7764,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7764
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003511",
"normalized_example_id": "ex_003511",
"source_idx": 3511,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7764,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 1",
"budget": 1206
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003514",
"normalized_example_id": "ex_003514",
"source_idx": 3514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2010,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 1",
"budget": 1608
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003514",
"normalized_example_id": "ex_003514",
"source_idx": 3514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2010,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 1",
"budget": 2010
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003514",
"normalized_example_id": "ex_003514",
"source_idx": 3514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2010,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\leqx\\leq1,2x",
"budget": 5093
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003516",
"normalized_example_id": "ex_003516",
"source_idx": 3516,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8489,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\leqx\\leq1,2x",
"budget": 6791
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003516",
"normalized_example_id": "ex_003516",
"source_idx": 3516,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8489,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\leqx\\leq1,2x",
"budget": 8489
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003516",
"normalized_example_id": "ex_003516",
"source_idx": 3516,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8489,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\arcsin\\frac{\\sqrt{6}}{3}",
"budget": 4210
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003520",
"normalized_example_id": "ex_003520",
"source_idx": 3520,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7016,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\arcsin\\frac{\\sqrt{6}}{3}",
"budget": 5613
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003520",
"normalized_example_id": "ex_003520",
"source_idx": 3520,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7016,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\arcsin\\frac{\\sqrt{6}}{3}",
"budget": 7016
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003520",
"normalized_example_id": "ex_003520",
"source_idx": 3520,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7016,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1699
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003523",
"normalized_example_id": "ex_003523",
"source_idx": 3523,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2832,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2266
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003523",
"normalized_example_id": "ex_003523",
"source_idx": 3523,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2832,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2832
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003523",
"normalized_example_id": "ex_003523",
"source_idx": 3523,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2832,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 2626
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003528",
"normalized_example_id": "ex_003528",
"source_idx": 3528,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4376,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 3501
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003528",
"normalized_example_id": "ex_003528",
"source_idx": 3528,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4376,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 4376
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003528",
"normalized_example_id": "ex_003528",
"source_idx": 3528,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4376,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2D-AC",
"budget": 2520
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003529",
"normalized_example_id": "ex_003529",
"source_idx": 3529,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4200,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2D-AC",
"budget": 3360
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003529",
"normalized_example_id": "ex_003529",
"source_idx": 3529,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4200,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2D-AC",
"budget": 4200
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003529",
"normalized_example_id": "ex_003529",
"source_idx": 3529,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4200,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{12}{19}",
"budget": 2684
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003530",
"normalized_example_id": "ex_003530",
"source_idx": 3530,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4473,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{12}{19}",
"budget": 3578
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003530",
"normalized_example_id": "ex_003530",
"source_idx": 3530,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4473,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{12}{19}",
"budget": 4473
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003530",
"normalized_example_id": "ex_003530",
"source_idx": 3530,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4473,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "432",
"budget": 1259
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003532",
"normalized_example_id": "ex_003532",
"source_idx": 3532,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "432",
"budget": 1679
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003532",
"normalized_example_id": "ex_003532",
"source_idx": 3532,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "432",
"budget": 2099
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003532",
"normalized_example_id": "ex_003532",
"source_idx": 3532,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-\\infty;-1)\\cup{3}\\cup(5;+\\infty)",
"budget": 3557
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003533",
"normalized_example_id": "ex_003533",
"source_idx": 3533,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5928,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-\\infty;-1)\\cup{3}\\cup(5;+\\infty)",
"budget": 4742
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003533",
"normalized_example_id": "ex_003533",
"source_idx": 3533,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5928,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-\\infty;-1)\\cup{3}\\cup(5;+\\infty)",
"budget": 5928
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003533",
"normalized_example_id": "ex_003533",
"source_idx": 3533,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5928,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 4790
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003535",
"normalized_example_id": "ex_003535",
"source_idx": 3535,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7984,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 6387
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003535",
"normalized_example_id": "ex_003535",
"source_idx": 3535,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7984,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 7984
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003535",
"normalized_example_id": "ex_003535",
"source_idx": 3535,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7984,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n-3}+3\\cdot2^{n-2}+3",
"budget": 4922
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003536",
"normalized_example_id": "ex_003536",
"source_idx": 3536,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8203,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n-3}+3\\cdot2^{n-2}+3",
"budget": 6562
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003536",
"normalized_example_id": "ex_003536",
"source_idx": 3536,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8203,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n-3}+3\\cdot2^{n-2}+3",
"budget": 8203
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003536",
"normalized_example_id": "ex_003536",
"source_idx": 3536,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8203,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 2144
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003537",
"normalized_example_id": "ex_003537",
"source_idx": 3537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3573,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 2858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003537",
"normalized_example_id": "ex_003537",
"source_idx": 3537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3573,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 3573
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003537",
"normalized_example_id": "ex_003537",
"source_idx": 3537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3573,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "54",
"budget": 5011
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003543",
"normalized_example_id": "ex_003543",
"source_idx": 3543,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8352,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "54",
"budget": 6682
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003543",
"normalized_example_id": "ex_003543",
"source_idx": 3543,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8352,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "54",
"budget": 8352
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003543",
"normalized_example_id": "ex_003543",
"source_idx": 3543,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8352,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "m=6, n=9",
"budget": 5716
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003550",
"normalized_example_id": "ex_003550",
"source_idx": 3550,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9526,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "m=6, n=9",
"budget": 7621
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003550",
"normalized_example_id": "ex_003550",
"source_idx": 3550,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9526,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "m=6, n=9",
"budget": 9526
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003550",
"normalized_example_id": "ex_003550",
"source_idx": 3550,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9526,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17328",
"budget": 4670
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003551",
"normalized_example_id": "ex_003551",
"source_idx": 3551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7783,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17328",
"budget": 6226
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003551",
"normalized_example_id": "ex_003551",
"source_idx": 3551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7783,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17328",
"budget": 7783
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003551",
"normalized_example_id": "ex_003551",
"source_idx": 3551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7783,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n \\cdot 7^{n-1}",
"budget": 3937
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003555",
"normalized_example_id": "ex_003555",
"source_idx": 3555,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6562,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n \\cdot 7^{n-1}",
"budget": 5250
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003555",
"normalized_example_id": "ex_003555",
"source_idx": 3555,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6562,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n \\cdot 7^{n-1}",
"budget": 6562
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003555",
"normalized_example_id": "ex_003555",
"source_idx": 3555,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6562,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 5811
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003558",
"normalized_example_id": "ex_003558",
"source_idx": 3558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9685,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 7748
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003558",
"normalized_example_id": "ex_003558",
"source_idx": 3558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9685,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 9685
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003558",
"normalized_example_id": "ex_003558",
"source_idx": 3558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9685,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(10,8,6)",
"budget": 4331
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003559",
"normalized_example_id": "ex_003559",
"source_idx": 3559,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(10,8,6)",
"budget": 5775
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003559",
"normalized_example_id": "ex_003559",
"source_idx": 3559,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(10,8,6)",
"budget": 7219
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003559",
"normalized_example_id": "ex_003559",
"source_idx": 3559,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "S\\in[-2,\\frac{9}{4}]",
"budget": 2734
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003563",
"normalized_example_id": "ex_003563",
"source_idx": 3563,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4557,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "S\\in[-2,\\frac{9}{4}]",
"budget": 3646
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003563",
"normalized_example_id": "ex_003563",
"source_idx": 3563,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4557,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "S\\in[-2,\\frac{9}{4}]",
"budget": 4557
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003563",
"normalized_example_id": "ex_003563",
"source_idx": 3563,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4557,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 3207
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003564",
"normalized_example_id": "ex_003564",
"source_idx": 3564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5345,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 4276
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003564",
"normalized_example_id": "ex_003564",
"source_idx": 3564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5345,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 5345
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003564",
"normalized_example_id": "ex_003564",
"source_idx": 3564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5345,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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), (2, 2), (5, 17)",
"budget": 4123
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003565",
"normalized_example_id": "ex_003565",
"source_idx": 3565,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6871,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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), (2, 2), (5, 17)",
"budget": 5497
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003565",
"normalized_example_id": "ex_003565",
"source_idx": 3565,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6871,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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), (2, 2), (5, 17)",
"budget": 6871
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003565",
"normalized_example_id": "ex_003565",
"source_idx": 3565,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6871,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{15}",
"budget": 3931
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003567",
"normalized_example_id": "ex_003567",
"source_idx": 3567,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6552,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{15}",
"budget": 5242
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003567",
"normalized_example_id": "ex_003567",
"source_idx": 3567,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6552,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{15}",
"budget": 6552
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003567",
"normalized_example_id": "ex_003567",
"source_idx": 3567,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6552,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2008,4016,-4016)",
"budget": 1357
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003569",
"normalized_example_id": "ex_003569",
"source_idx": 3569,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2262,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2008,4016,-4016)",
"budget": 1810
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003569",
"normalized_example_id": "ex_003569",
"source_idx": 3569,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2262,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2008,4016,-4016)",
"budget": 2262
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003569",
"normalized_example_id": "ex_003569",
"source_idx": 3569,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2262,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{3}",
"budget": 2447
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003570",
"normalized_example_id": "ex_003570",
"source_idx": 3570,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4079,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{3}",
"budget": 3263
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003570",
"normalized_example_id": "ex_003570",
"source_idx": 3570,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4079,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{3}",
"budget": 4079
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003570",
"normalized_example_id": "ex_003570",
"source_idx": 3570,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4079,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\angleBAC=61,\\angleBCA=29",
"budget": 3366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003571",
"normalized_example_id": "ex_003571",
"source_idx": 3571,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5610,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\angleBAC=61,\\angleBCA=29",
"budget": 4488
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003571",
"normalized_example_id": "ex_003571",
"source_idx": 3571,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5610,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\angleBAC=61,\\angleBCA=29",
"budget": 5610
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003571",
"normalized_example_id": "ex_003571",
"source_idx": 3571,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5610,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 771
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003573",
"normalized_example_id": "ex_003573",
"source_idx": 3573,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1285,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1028
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003573",
"normalized_example_id": "ex_003573",
"source_idx": 3573,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1285,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1285
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003573",
"normalized_example_id": "ex_003573",
"source_idx": 3573,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1285,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "pq",
"budget": 1573
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003574",
"normalized_example_id": "ex_003574",
"source_idx": 3574,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2622,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "pq",
"budget": 2098
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003574",
"normalized_example_id": "ex_003574",
"source_idx": 3574,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2622,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "pq",
"budget": 2622
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003574",
"normalized_example_id": "ex_003574",
"source_idx": 3574,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2622,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p^2+p",
"budget": 2400
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003575",
"normalized_example_id": "ex_003575",
"source_idx": 3575,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4000,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p^2+p",
"budget": 3200
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003575",
"normalized_example_id": "ex_003575",
"source_idx": 3575,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4000,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p^2+p",
"budget": 4000
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003575",
"normalized_example_id": "ex_003575",
"source_idx": 3575,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4000,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003576",
"normalized_example_id": "ex_003576",
"source_idx": 3576,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2410,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1928
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003576",
"normalized_example_id": "ex_003576",
"source_idx": 3576,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2410,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2410
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003576",
"normalized_example_id": "ex_003576",
"source_idx": 3576,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2410,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5123
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003580",
"normalized_example_id": "ex_003580",
"source_idx": 3580,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8539,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6831
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003580",
"normalized_example_id": "ex_003580",
"source_idx": 3580,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8539,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8539
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003580",
"normalized_example_id": "ex_003580",
"source_idx": 3580,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8539,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "147",
"budget": 2728
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003582",
"normalized_example_id": "ex_003582",
"source_idx": 3582,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "147",
"budget": 3638
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003582",
"normalized_example_id": "ex_003582",
"source_idx": 3582,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4547,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.