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": "208",
"budget": 2629
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001019",
"normalized_example_id": "ex_001019",
"source_idx": 1019,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3286,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "208",
"budget": 3286
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001019",
"normalized_example_id": "ex_001019",
"source_idx": 1019,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3286,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\frac{1}{3},10\\frac{2}{3}",
"budget": 1936
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001022",
"normalized_example_id": "ex_001022",
"source_idx": 1022,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3226,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\frac{1}{3},10\\frac{2}{3}",
"budget": 2581
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001022",
"normalized_example_id": "ex_001022",
"source_idx": 1022,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3226,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\frac{1}{3},10\\frac{2}{3}",
"budget": 3226
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001022",
"normalized_example_id": "ex_001022",
"source_idx": 1022,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3226,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 3161
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001023",
"normalized_example_id": "ex_001023",
"source_idx": 1023,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5269,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 4215
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001023",
"normalized_example_id": "ex_001023",
"source_idx": 1023,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5269,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 5269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001023",
"normalized_example_id": "ex_001023",
"source_idx": 1023,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5269,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2:1",
"budget": 2182
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001024",
"normalized_example_id": "ex_001024",
"source_idx": 1024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3636,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2:1",
"budget": 2909
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001024",
"normalized_example_id": "ex_001024",
"source_idx": 1024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3636,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2:1",
"budget": 3636
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001024",
"normalized_example_id": "ex_001024",
"source_idx": 1024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3636,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2000}",
"budget": 2810
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001026",
"normalized_example_id": "ex_001026",
"source_idx": 1026,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4684,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2000}",
"budget": 3747
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001026",
"normalized_example_id": "ex_001026",
"source_idx": 1026,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4684,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2000}",
"budget": 4684
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001026",
"normalized_example_id": "ex_001026",
"source_idx": 1026,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4684,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7or14",
"budget": 4435
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001030",
"normalized_example_id": "ex_001030",
"source_idx": 1030,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7392,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7or14",
"budget": 5914
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001030",
"normalized_example_id": "ex_001030",
"source_idx": 1030,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7392,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7or14",
"budget": 7392
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001030",
"normalized_example_id": "ex_001030",
"source_idx": 1030,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7392,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{(1+e^{x})^{2}}",
"budget": 2915
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001033",
"normalized_example_id": "ex_001033",
"source_idx": 1033,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4858,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{(1+e^{x})^{2}}",
"budget": 3886
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001033",
"normalized_example_id": "ex_001033",
"source_idx": 1033,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4858,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{(1+e^{x})^{2}}",
"budget": 4858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001033",
"normalized_example_id": "ex_001033",
"source_idx": 1033,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4858,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18\\sqrt{2}",
"budget": 626
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001039",
"normalized_example_id": "ex_001039",
"source_idx": 1039,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1044,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18\\sqrt{2}",
"budget": 835
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001039",
"normalized_example_id": "ex_001039",
"source_idx": 1039,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1044,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18\\sqrt{2}",
"budget": 1044
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001039",
"normalized_example_id": "ex_001039",
"source_idx": 1039,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1044,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{23}{90}",
"budget": 1783
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001040",
"normalized_example_id": "ex_001040",
"source_idx": 1040,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2972,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{23}{90}",
"budget": 2378
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001040",
"normalized_example_id": "ex_001040",
"source_idx": 1040,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2972,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{23}{90}",
"budget": 2972
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001040",
"normalized_example_id": "ex_001040",
"source_idx": 1040,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2972,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "237.5",
"budget": 1692
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001041",
"normalized_example_id": "ex_001041",
"source_idx": 1041,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2820,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "237.5",
"budget": 2256
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001041",
"normalized_example_id": "ex_001041",
"source_idx": 1041,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2820,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "237.5",
"budget": 2820
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001041",
"normalized_example_id": "ex_001041",
"source_idx": 1041,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2820,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 4971
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001042",
"normalized_example_id": "ex_001042",
"source_idx": 1042,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8285,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 6628
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001042",
"normalized_example_id": "ex_001042",
"source_idx": 1042,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8285,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 8285
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001042",
"normalized_example_id": "ex_001042",
"source_idx": 1042,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8285,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "512",
"budget": 5800
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001044",
"normalized_example_id": "ex_001044",
"source_idx": 1044,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9666,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "512",
"budget": 7733
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001044",
"normalized_example_id": "ex_001044",
"source_idx": 1044,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9666,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "512",
"budget": 9666
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001044",
"normalized_example_id": "ex_001044",
"source_idx": 1044,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9666,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3780
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001046",
"normalized_example_id": "ex_001046",
"source_idx": 1046,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6300,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5040
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001046",
"normalized_example_id": "ex_001046",
"source_idx": 1046,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6300,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6300
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001046",
"normalized_example_id": "ex_001046",
"source_idx": 1046,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6300,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5440
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001047",
"normalized_example_id": "ex_001047",
"source_idx": 1047,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9066,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7253
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001047",
"normalized_example_id": "ex_001047",
"source_idx": 1047,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9066,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 9066
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001047",
"normalized_example_id": "ex_001047",
"source_idx": 1047,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9066,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\frac{1}{3}, y=\\frac{2}{3}",
"budget": 1492
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001049",
"normalized_example_id": "ex_001049",
"source_idx": 1049,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2486,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\frac{1}{3}, y=\\frac{2}{3}",
"budget": 1989
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001049",
"normalized_example_id": "ex_001049",
"source_idx": 1049,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2486,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\frac{1}{3}, y=\\frac{2}{3}",
"budget": 2486
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001049",
"normalized_example_id": "ex_001049",
"source_idx": 1049,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2486,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,3,5,7",
"budget": 4987
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001050",
"normalized_example_id": "ex_001050",
"source_idx": 1050,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8311,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,3,5,7",
"budget": 6649
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001050",
"normalized_example_id": "ex_001050",
"source_idx": 1050,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8311,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,3,5,7",
"budget": 8311
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001050",
"normalized_example_id": "ex_001050",
"source_idx": 1050,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8311,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-3,2,-1)",
"budget": 888
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001053",
"normalized_example_id": "ex_001053",
"source_idx": 1053,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1480,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-3,2,-1)",
"budget": 1184
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001053",
"normalized_example_id": "ex_001053",
"source_idx": 1053,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1480,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-3,2,-1)",
"budget": 1480
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001053",
"normalized_example_id": "ex_001053",
"source_idx": 1053,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1480,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1014
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001056",
"normalized_example_id": "ex_001056",
"source_idx": 1056,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1352
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001056",
"normalized_example_id": "ex_001056",
"source_idx": 1056,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1690
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001056",
"normalized_example_id": "ex_001056",
"source_idx": 1056,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\leqslantx\\leqslant2",
"budget": 1087
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001057",
"normalized_example_id": "ex_001057",
"source_idx": 1057,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1811,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\leqslantx\\leqslant2",
"budget": 1449
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001057",
"normalized_example_id": "ex_001057",
"source_idx": 1057,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1811,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\leqslantx\\leqslant2",
"budget": 1811
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001057",
"normalized_example_id": "ex_001057",
"source_idx": 1057,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1811,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1/3,2/3",
"budget": 3566
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001060",
"normalized_example_id": "ex_001060",
"source_idx": 1060,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5943,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1/3,2/3",
"budget": 4754
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001060",
"normalized_example_id": "ex_001060",
"source_idx": 1060,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5943,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1/3,2/3",
"budget": 5943
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001060",
"normalized_example_id": "ex_001060",
"source_idx": 1060,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5943,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{0}=\\frac{1}{5}",
"budget": 3634
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001061",
"normalized_example_id": "ex_001061",
"source_idx": 1061,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6056,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{0}=\\frac{1}{5}",
"budget": 4845
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001061",
"normalized_example_id": "ex_001061",
"source_idx": 1061,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6056,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{0}=\\frac{1}{5}",
"budget": 6056
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001061",
"normalized_example_id": "ex_001061",
"source_idx": 1061,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6056,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0, 0, 1), (0, 1, 3), (2, 1, 5)",
"budget": 4868
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001064",
"normalized_example_id": "ex_001064",
"source_idx": 1064,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8114,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0, 0, 1), (0, 1, 3), (2, 1, 5)",
"budget": 6491
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001064",
"normalized_example_id": "ex_001064",
"source_idx": 1064,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8114,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0, 0, 1), (0, 1, 3), (2, 1, 5)",
"budget": 8114
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001064",
"normalized_example_id": "ex_001064",
"source_idx": 1064,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8114,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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),(2,1),(4,2)",
"budget": 3498
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001065",
"normalized_example_id": "ex_001065",
"source_idx": 1065,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5830,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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),(2,1),(4,2)",
"budget": 4664
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001065",
"normalized_example_id": "ex_001065",
"source_idx": 1065,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5830,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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),(2,1),(4,2)",
"budget": 5830
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001065",
"normalized_example_id": "ex_001065",
"source_idx": 1065,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5830,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,4,5,7",
"budget": 1933
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001066",
"normalized_example_id": "ex_001066",
"source_idx": 1066,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3222,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,4,5,7",
"budget": 2578
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001066",
"normalized_example_id": "ex_001066",
"source_idx": 1066,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3222,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,4,5,7",
"budget": 3222
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001066",
"normalized_example_id": "ex_001066",
"source_idx": 1066,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3222,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 1833
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001067",
"normalized_example_id": "ex_001067",
"source_idx": 1067,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3055,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 2444
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001067",
"normalized_example_id": "ex_001067",
"source_idx": 1067,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3055,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 3055
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001067",
"normalized_example_id": "ex_001067",
"source_idx": 1067,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3055,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{16}",
"budget": 1925
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001069",
"normalized_example_id": "ex_001069",
"source_idx": 1069,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3208,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{16}",
"budget": 2566
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001069",
"normalized_example_id": "ex_001069",
"source_idx": 1069,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3208,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{16}",
"budget": 3208
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001069",
"normalized_example_id": "ex_001069",
"source_idx": 1069,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3208,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{48}{5}\\sqrt{6}",
"budget": 2235
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001070",
"normalized_example_id": "ex_001070",
"source_idx": 1070,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3725,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{48}{5}\\sqrt{6}",
"budget": 2980
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001070",
"normalized_example_id": "ex_001070",
"source_idx": 1070,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3725,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{48}{5}\\sqrt{6}",
"budget": 3725
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001070",
"normalized_example_id": "ex_001070",
"source_idx": 1070,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3725,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 2329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001071",
"normalized_example_id": "ex_001071",
"source_idx": 1071,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3881,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 3105
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001071",
"normalized_example_id": "ex_001071",
"source_idx": 1071,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3881,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 3881
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001071",
"normalized_example_id": "ex_001071",
"source_idx": 1071,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3881,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{7}{15}",
"budget": 1170
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001072",
"normalized_example_id": "ex_001072",
"source_idx": 1072,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1950,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{7}{15}",
"budget": 1560
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001072",
"normalized_example_id": "ex_001072",
"source_idx": 1072,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1950,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{7}{15}",
"budget": 1950
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001072",
"normalized_example_id": "ex_001072",
"source_idx": 1072,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1950,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 4051
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001074",
"normalized_example_id": "ex_001074",
"source_idx": 1074,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6752,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 5402
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001074",
"normalized_example_id": "ex_001074",
"source_idx": 1074,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6752,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 6752
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001074",
"normalized_example_id": "ex_001074",
"source_idx": 1074,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6752,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 1724
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001075",
"normalized_example_id": "ex_001075",
"source_idx": 1075,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 2299
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001075",
"normalized_example_id": "ex_001075",
"source_idx": 1075,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 2874
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001075",
"normalized_example_id": "ex_001075",
"source_idx": 1075,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2561
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001076",
"normalized_example_id": "ex_001076",
"source_idx": 1076,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4268,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3414
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001076",
"normalized_example_id": "ex_001076",
"source_idx": 1076,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4268,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4268
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001076",
"normalized_example_id": "ex_001076",
"source_idx": 1076,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4268,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y^{(n)}=(-1)^{n+1}\\cdot\\frac{n!}{(x+1)^{n+1}}",
"budget": 1589
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001080",
"normalized_example_id": "ex_001080",
"source_idx": 1080,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2648,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y^{(n)}=(-1)^{n+1}\\cdot\\frac{n!}{(x+1)^{n+1}}",
"budget": 2118
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001080",
"normalized_example_id": "ex_001080",
"source_idx": 1080,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2648,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y^{(n)}=(-1)^{n+1}\\cdot\\frac{n!}{(x+1)^{n+1}}",
"budget": 2648
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001080",
"normalized_example_id": "ex_001080",
"source_idx": 1080,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2648,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4}\\cdot(\\arccosx)^{4}+\\arccosx+C",
"budget": 918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001081",
"normalized_example_id": "ex_001081",
"source_idx": 1081,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1530,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4}\\cdot(\\arccosx)^{4}+\\arccosx+C",
"budget": 1224
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001081",
"normalized_example_id": "ex_001081",
"source_idx": 1081,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1530,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.