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": "20a",
"budget": 2155
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006591",
"normalized_example_id": "ex_006591",
"source_idx": 6591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3591,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20a",
"budget": 2873
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006591",
"normalized_example_id": "ex_006591",
"source_idx": 6591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3591,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20a",
"budget": 3591
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006591",
"normalized_example_id": "ex_006591",
"source_idx": 6591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3591,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2235",
"budget": 2506
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006592",
"normalized_example_id": "ex_006592",
"source_idx": 6592,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4176,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2235",
"budget": 3341
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006592",
"normalized_example_id": "ex_006592",
"source_idx": 6592,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4176,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2235",
"budget": 4176
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006592",
"normalized_example_id": "ex_006592",
"source_idx": 6592,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4176,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1093
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006593",
"normalized_example_id": "ex_006593",
"source_idx": 6593,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1822,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1458
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006593",
"normalized_example_id": "ex_006593",
"source_idx": 6593,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1822,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1822
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006593",
"normalized_example_id": "ex_006593",
"source_idx": 6593,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1822,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4457
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006597",
"normalized_example_id": "ex_006597",
"source_idx": 6597,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5943
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006597",
"normalized_example_id": "ex_006597",
"source_idx": 6597,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006597",
"normalized_example_id": "ex_006597",
"source_idx": 6597,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-10",
"budget": 2884
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006598",
"normalized_example_id": "ex_006598",
"source_idx": 6598,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4807,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-10",
"budget": 3846
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006598",
"normalized_example_id": "ex_006598",
"source_idx": 6598,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4807,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,-10",
"budget": 4807
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006598",
"normalized_example_id": "ex_006598",
"source_idx": 6598,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4807,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4031
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006599",
"normalized_example_id": "ex_006599",
"source_idx": 6599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6718,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5374
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006599",
"normalized_example_id": "ex_006599",
"source_idx": 6599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6718,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6718
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006599",
"normalized_example_id": "ex_006599",
"source_idx": 6599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6718,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{5})^{2}+(y-\\frac{3}{5})^{2}=5or(x-4)^{2}+(y+1)^{2}=5",
"budget": 3952
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006600",
"normalized_example_id": "ex_006600",
"source_idx": 6600,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6586,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{5})^{2}+(y-\\frac{3}{5})^{2}=5or(x-4)^{2}+(y+1)^{2}=5",
"budget": 5269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006600",
"normalized_example_id": "ex_006600",
"source_idx": 6600,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6586,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{5})^{2}+(y-\\frac{3}{5})^{2}=5or(x-4)^{2}+(y+1)^{2}=5",
"budget": 6586
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006600",
"normalized_example_id": "ex_006600",
"source_idx": 6600,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6586,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[\\frac{n}{2}]+1",
"budget": 3681
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006601",
"normalized_example_id": "ex_006601",
"source_idx": 6601,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6135,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[\\frac{n}{2}]+1",
"budget": 4908
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006601",
"normalized_example_id": "ex_006601",
"source_idx": 6601,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6135,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[\\frac{n}{2}]+1",
"budget": 6135
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006601",
"normalized_example_id": "ex_006601",
"source_idx": 6601,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6135,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "179",
"budget": 4942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006603",
"normalized_example_id": "ex_006603",
"source_idx": 6603,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8237,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "179",
"budget": 6590
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006603",
"normalized_example_id": "ex_006603",
"source_idx": 6603,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8237,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "179",
"budget": 8237
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006603",
"normalized_example_id": "ex_006603",
"source_idx": 6603,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8237,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1296
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006604",
"normalized_example_id": "ex_006604",
"source_idx": 6604,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2160,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1728
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006604",
"normalized_example_id": "ex_006604",
"source_idx": 6604,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2160,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2160
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006604",
"normalized_example_id": "ex_006604",
"source_idx": 6604,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2160,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}}{4}",
"budget": 2385
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006609",
"normalized_example_id": "ex_006609",
"source_idx": 6609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3975,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}}{4}",
"budget": 3180
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006609",
"normalized_example_id": "ex_006609",
"source_idx": 6609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3975,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}}{4}",
"budget": 3975
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006609",
"normalized_example_id": "ex_006609",
"source_idx": 6609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3975,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "64",
"budget": 5924
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006610",
"normalized_example_id": "ex_006610",
"source_idx": 6610,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9873,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "64",
"budget": 7898
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006610",
"normalized_example_id": "ex_006610",
"source_idx": 6610,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9873,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "64",
"budget": 9873
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006610",
"normalized_example_id": "ex_006610",
"source_idx": 6610,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9873,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12560",
"budget": 4856
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006611",
"normalized_example_id": "ex_006611",
"source_idx": 6611,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8094,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12560",
"budget": 6475
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006611",
"normalized_example_id": "ex_006611",
"source_idx": 6611,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8094,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12560",
"budget": 8094
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006611",
"normalized_example_id": "ex_006611",
"source_idx": 6611,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8094,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "667",
"budget": 1327
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006612",
"normalized_example_id": "ex_006612",
"source_idx": 6612,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2211,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "667",
"budget": 1769
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006612",
"normalized_example_id": "ex_006612",
"source_idx": 6612,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2211,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "667",
"budget": 2211
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006612",
"normalized_example_id": "ex_006612",
"source_idx": 6612,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2211,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "72",
"budget": 3661
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006613",
"normalized_example_id": "ex_006613",
"source_idx": 6613,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6101,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "72",
"budget": 4881
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006613",
"normalized_example_id": "ex_006613",
"source_idx": 6613,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6101,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "72",
"budget": 6101
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006613",
"normalized_example_id": "ex_006613",
"source_idx": 6613,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6101,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2826
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006615",
"normalized_example_id": "ex_006615",
"source_idx": 6615,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4710,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3768
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006615",
"normalized_example_id": "ex_006615",
"source_idx": 6615,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4710,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4710
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006615",
"normalized_example_id": "ex_006615",
"source_idx": 6615,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4710,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "52",
"budget": 2014
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006616",
"normalized_example_id": "ex_006616",
"source_idx": 6616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3357,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "52",
"budget": 2686
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006616",
"normalized_example_id": "ex_006616",
"source_idx": 6616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3357,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "52",
"budget": 3357
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006616",
"normalized_example_id": "ex_006616",
"source_idx": 6616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3357,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 2207
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006617",
"normalized_example_id": "ex_006617",
"source_idx": 6617,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 2942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006617",
"normalized_example_id": "ex_006617",
"source_idx": 6617,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 3678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006617",
"normalized_example_id": "ex_006617",
"source_idx": 6617,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1214
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006618",
"normalized_example_id": "ex_006618",
"source_idx": 6618,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2023,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1618
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006618",
"normalized_example_id": "ex_006618",
"source_idx": 6618,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2023,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2023
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006618",
"normalized_example_id": "ex_006618",
"source_idx": 6618,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2023,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1163
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006622",
"normalized_example_id": "ex_006622",
"source_idx": 6622,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1939,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1551
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006622",
"normalized_example_id": "ex_006622",
"source_idx": 6622,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1939,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006622",
"normalized_example_id": "ex_006622",
"source_idx": 6622,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1939,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 2359
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006623",
"normalized_example_id": "ex_006623",
"source_idx": 6623,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3932,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 3146
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006623",
"normalized_example_id": "ex_006623",
"source_idx": 6623,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3932,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 3932
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006623",
"normalized_example_id": "ex_006623",
"source_idx": 6623,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3932,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1197",
"budget": 3971
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006624",
"normalized_example_id": "ex_006624",
"source_idx": 6624,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6618,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1197",
"budget": 5294
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006624",
"normalized_example_id": "ex_006624",
"source_idx": 6624,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6618,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1197",
"budget": 6618
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006624",
"normalized_example_id": "ex_006624",
"source_idx": 6624,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6618,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{15}\\mathrm{~}^{2}",
"budget": 2155
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006629",
"normalized_example_id": "ex_006629",
"source_idx": 6629,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3591,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{15}\\mathrm{~}^{2}",
"budget": 2873
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006629",
"normalized_example_id": "ex_006629",
"source_idx": 6629,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3591,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{15}\\mathrm{~}^{2}",
"budget": 3591
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006629",
"normalized_example_id": "ex_006629",
"source_idx": 6629,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3591,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x\\in(-\\infty;-\\sqrt[3]{5})\\cup(\\sqrt[6]{21};+\\infty)",
"budget": 2918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006630",
"normalized_example_id": "ex_006630",
"source_idx": 6630,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4864,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x\\in(-\\infty;-\\sqrt[3]{5})\\cup(\\sqrt[6]{21};+\\infty)",
"budget": 3891
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006630",
"normalized_example_id": "ex_006630",
"source_idx": 6630,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4864,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x\\in(-\\infty;-\\sqrt[3]{5})\\cup(\\sqrt[6]{21};+\\infty)",
"budget": 4864
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006630",
"normalized_example_id": "ex_006630",
"source_idx": 6630,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4864,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 4099
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006632",
"normalized_example_id": "ex_006632",
"source_idx": 6632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6831,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 5465
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006632",
"normalized_example_id": "ex_006632",
"source_idx": 6632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6831,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 6831
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006632",
"normalized_example_id": "ex_006632",
"source_idx": 6632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6831,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{9}\\cdot2^{9}",
"budget": 3364
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006634",
"normalized_example_id": "ex_006634",
"source_idx": 6634,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5607,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{9}\\cdot2^{9}",
"budget": 4486
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006634",
"normalized_example_id": "ex_006634",
"source_idx": 6634,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5607,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{9}\\cdot2^{9}",
"budget": 5607
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006634",
"normalized_example_id": "ex_006634",
"source_idx": 6634,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5607,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "881",
"budget": 2393
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006636",
"normalized_example_id": "ex_006636",
"source_idx": 6636,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3989,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "881",
"budget": 3191
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006636",
"normalized_example_id": "ex_006636",
"source_idx": 6636,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3989,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "881",
"budget": 3989
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006636",
"normalized_example_id": "ex_006636",
"source_idx": 6636,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3989,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006638",
"normalized_example_id": "ex_006638",
"source_idx": 6638,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8471,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6777
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006638",
"normalized_example_id": "ex_006638",
"source_idx": 6638,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8471,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8471
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006638",
"normalized_example_id": "ex_006638",
"source_idx": 6638,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8471,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(995,1),(176,10),(80,21)",
"budget": 2725
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006640",
"normalized_example_id": "ex_006640",
"source_idx": 6640,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4541,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(995,1),(176,10),(80,21)",
"budget": 3633
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006640",
"normalized_example_id": "ex_006640",
"source_idx": 6640,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4541,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(995,1),(176,10),(80,21)",
"budget": 4541
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006640",
"normalized_example_id": "ex_006640",
"source_idx": 6640,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4541,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1100",
"budget": 1849
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006641",
"normalized_example_id": "ex_006641",
"source_idx": 6641,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3081,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1100",
"budget": 2465
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006641",
"normalized_example_id": "ex_006641",
"source_idx": 6641,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3081,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1100",
"budget": 3081
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006641",
"normalized_example_id": "ex_006641",
"source_idx": 6641,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3081,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11}{3}",
"budget": 1436
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006643",
"normalized_example_id": "ex_006643",
"source_idx": 6643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11}{3}",
"budget": 1915
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006643",
"normalized_example_id": "ex_006643",
"source_idx": 6643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11}{3}",
"budget": 2394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006643",
"normalized_example_id": "ex_006643",
"source_idx": 6643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}\\ln(1+e^{4})-1",
"budget": 4837
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006645",
"normalized_example_id": "ex_006645",
"source_idx": 6645,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8062,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}\\ln(1+e^{4})-1",
"budget": 6450
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006645",
"normalized_example_id": "ex_006645",
"source_idx": 6645,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8062,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}\\ln(1+e^{4})-1",
"budget": 8062
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006645",
"normalized_example_id": "ex_006645",
"source_idx": 6645,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8062,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{2}",
"budget": 1565
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006646",
"normalized_example_id": "ex_006646",
"source_idx": 6646,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2608,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{2}",
"budget": 2086
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006646",
"normalized_example_id": "ex_006646",
"source_idx": 6646,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2608,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{2}",
"budget": 2608
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006646",
"normalized_example_id": "ex_006646",
"source_idx": 6646,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2608,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5,6,8",
"budget": 3130
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006650",
"normalized_example_id": "ex_006650",
"source_idx": 6650,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5216,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.