prompt listlengths 2 2 | label dict | metadata dict |
|---|---|---|
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.622",
"budget": 5607
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004798",
"normalized_example_id": "ex_004798",
"source_idx": 4798,
"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": "0",
"budget": 1393
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004802",
"normalized_example_id": "ex_004802",
"source_idx": 4802,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2321,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 1857
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004802",
"normalized_example_id": "ex_004802",
"source_idx": 4802,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2321,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 2321
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004802",
"normalized_example_id": "ex_004802",
"source_idx": 4802,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2321,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(74;592),(592;74)",
"budget": 4973
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004803",
"normalized_example_id": "ex_004803",
"source_idx": 4803,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8289,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(74;592),(592;74)",
"budget": 6631
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004803",
"normalized_example_id": "ex_004803",
"source_idx": 4803,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8289,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(74;592),(592;74)",
"budget": 8289
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004803",
"normalized_example_id": "ex_004803",
"source_idx": 4803,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8289,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.5",
"budget": 2395
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004808",
"normalized_example_id": "ex_004808",
"source_idx": 4808,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3991,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.5",
"budget": 3193
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004808",
"normalized_example_id": "ex_004808",
"source_idx": 4808,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3991,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.5",
"budget": 3991
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004808",
"normalized_example_id": "ex_004808",
"source_idx": 4808,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3991,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1534
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004809",
"normalized_example_id": "ex_004809",
"source_idx": 4809,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2556,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2045
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004809",
"normalized_example_id": "ex_004809",
"source_idx": 4809,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2556,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2556
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004809",
"normalized_example_id": "ex_004809",
"source_idx": 4809,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2556,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{7}, 0)",
"budget": 1969
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004811",
"normalized_example_id": "ex_004811",
"source_idx": 4811,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3282,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{7}, 0)",
"budget": 2626
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004811",
"normalized_example_id": "ex_004811",
"source_idx": 4811,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3282,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{7}, 0)",
"budget": 3282
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004811",
"normalized_example_id": "ex_004811",
"source_idx": 4811,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3282,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x, y) = \\left(\\frac{p-1}{2}, \\frac{p+1}{2}\\right)",
"budget": 5758
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004812",
"normalized_example_id": "ex_004812",
"source_idx": 4812,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x, y) = \\left(\\frac{p-1}{2}, \\frac{p+1}{2}\\right)",
"budget": 7678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004812",
"normalized_example_id": "ex_004812",
"source_idx": 4812,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x, y) = \\left(\\frac{p-1}{2}, \\frac{p+1}{2}\\right)",
"budget": 9597
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004812",
"normalized_example_id": "ex_004812",
"source_idx": 4812,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9597,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a=1, b=2",
"budget": 3802
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004815",
"normalized_example_id": "ex_004815",
"source_idx": 4815,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a=1, b=2",
"budget": 5070
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004815",
"normalized_example_id": "ex_004815",
"source_idx": 4815,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a=1, b=2",
"budget": 6337
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004815",
"normalized_example_id": "ex_004815",
"source_idx": 4815,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "No",
"budget": 1504
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004817",
"normalized_example_id": "ex_004817",
"source_idx": 4817,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2507,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "No",
"budget": 2006
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004817",
"normalized_example_id": "ex_004817",
"source_idx": 4817,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2507,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "No",
"budget": 2507
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004817",
"normalized_example_id": "ex_004817",
"source_idx": 4817,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2507,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5a",
"budget": 2878
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004818",
"normalized_example_id": "ex_004818",
"source_idx": 4818,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4796,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5a",
"budget": 3837
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004818",
"normalized_example_id": "ex_004818",
"source_idx": 4818,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4796,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5a",
"budget": 4796
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004818",
"normalized_example_id": "ex_004818",
"source_idx": 4818,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4796,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 763
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004820",
"normalized_example_id": "ex_004820",
"source_idx": 4820,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1271,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 1017
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004820",
"normalized_example_id": "ex_004820",
"source_idx": 4820,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1271,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 1271
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004820",
"normalized_example_id": "ex_004820",
"source_idx": 4820,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1271,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.6",
"budget": 1309
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004824",
"normalized_example_id": "ex_004824",
"source_idx": 4824,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2181,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.6",
"budget": 1745
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004824",
"normalized_example_id": "ex_004824",
"source_idx": 4824,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2181,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.6",
"budget": 2181
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004824",
"normalized_example_id": "ex_004824",
"source_idx": 4824,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2181,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 986
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004825",
"normalized_example_id": "ex_004825",
"source_idx": 4825,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1643,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 1314
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004825",
"normalized_example_id": "ex_004825",
"source_idx": 4825,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1643,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 1643
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004825",
"normalized_example_id": "ex_004825",
"source_idx": 4825,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1643,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "625\\mathrm{~}^{2}",
"budget": 4268
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004829",
"normalized_example_id": "ex_004829",
"source_idx": 4829,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7113,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "625\\mathrm{~}^{2}",
"budget": 5690
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004829",
"normalized_example_id": "ex_004829",
"source_idx": 4829,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7113,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "625\\mathrm{~}^{2}",
"budget": 7113
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004829",
"normalized_example_id": "ex_004829",
"source_idx": 4829,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7113,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "310",
"budget": 3511
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004830",
"normalized_example_id": "ex_004830",
"source_idx": 4830,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5851,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "310",
"budget": 4681
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004830",
"normalized_example_id": "ex_004830",
"source_idx": 4830,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5851,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "310",
"budget": 5851
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004830",
"normalized_example_id": "ex_004830",
"source_idx": 4830,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5851,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{63}{64}",
"budget": 2031
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004833",
"normalized_example_id": "ex_004833",
"source_idx": 4833,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3385,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{63}{64}",
"budget": 2708
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004833",
"normalized_example_id": "ex_004833",
"source_idx": 4833,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3385,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{63}{64}",
"budget": 3385
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004833",
"normalized_example_id": "ex_004833",
"source_idx": 4833,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3385,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "N=63,X=3.6",
"budget": 1383
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004834",
"normalized_example_id": "ex_004834",
"source_idx": 4834,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2305,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "N=63,X=3.6",
"budget": 1844
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004834",
"normalized_example_id": "ex_004834",
"source_idx": 4834,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2305,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "N=63,X=3.6",
"budget": 2305
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004834",
"normalized_example_id": "ex_004834",
"source_idx": 4834,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2305,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 2545
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004835",
"normalized_example_id": "ex_004835",
"source_idx": 4835,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4241,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 3393
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004835",
"normalized_example_id": "ex_004835",
"source_idx": 4835,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4241,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 4241
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004835",
"normalized_example_id": "ex_004835",
"source_idx": 4835,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4241,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "384",
"budget": 3004
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004838",
"normalized_example_id": "ex_004838",
"source_idx": 4838,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5006,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "384",
"budget": 4005
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004838",
"normalized_example_id": "ex_004838",
"source_idx": 4838,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5006,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "384",
"budget": 5006
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004838",
"normalized_example_id": "ex_004838",
"source_idx": 4838,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5006,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "33",
"budget": 3167
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004839",
"normalized_example_id": "ex_004839",
"source_idx": 4839,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5279,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "33",
"budget": 4223
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004839",
"normalized_example_id": "ex_004839",
"source_idx": 4839,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5279,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "33",
"budget": 5279
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004839",
"normalized_example_id": "ex_004839",
"source_idx": 4839,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5279,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=7,\\quady=52",
"budget": 3836
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004840",
"normalized_example_id": "ex_004840",
"source_idx": 4840,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=7,\\quady=52",
"budget": 5115
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004840",
"normalized_example_id": "ex_004840",
"source_idx": 4840,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=7,\\quady=52",
"budget": 6394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004840",
"normalized_example_id": "ex_004840",
"source_idx": 4840,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3604
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004841",
"normalized_example_id": "ex_004841",
"source_idx": 4841,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6007,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004841",
"normalized_example_id": "ex_004841",
"source_idx": 4841,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6007,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004841",
"normalized_example_id": "ex_004841",
"source_idx": 4841,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6007,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "82",
"budget": 867
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004842",
"normalized_example_id": "ex_004842",
"source_idx": 4842,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1445,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "82",
"budget": 1156
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004842",
"normalized_example_id": "ex_004842",
"source_idx": 4842,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1445,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "82",
"budget": 1445
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004842",
"normalized_example_id": "ex_004842",
"source_idx": 4842,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1445,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3568
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004844",
"normalized_example_id": "ex_004844",
"source_idx": 4844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4757
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004844",
"normalized_example_id": "ex_004844",
"source_idx": 4844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5946
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004844",
"normalized_example_id": "ex_004844",
"source_idx": 4844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 1442
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004845",
"normalized_example_id": "ex_004845",
"source_idx": 4845,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2404,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 1923
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004845",
"normalized_example_id": "ex_004845",
"source_idx": 4845,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2404,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 2404
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004845",
"normalized_example_id": "ex_004845",
"source_idx": 4845,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2404,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(498,498)",
"budget": 6056
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004847",
"normalized_example_id": "ex_004847",
"source_idx": 4847,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10093,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(498,498)",
"budget": 8074
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004847",
"normalized_example_id": "ex_004847",
"source_idx": 4847,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10093,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(498,498)",
"budget": 10093
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004847",
"normalized_example_id": "ex_004847",
"source_idx": 4847,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10093,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1718
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004848",
"normalized_example_id": "ex_004848",
"source_idx": 4848,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2864,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2291
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004848",
"normalized_example_id": "ex_004848",
"source_idx": 4848,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2864,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2864
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004848",
"normalized_example_id": "ex_004848",
"source_idx": 4848,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2864,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34",
"budget": 807
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004850",
"normalized_example_id": "ex_004850",
"source_idx": 4850,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1345,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34",
"budget": 1076
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004850",
"normalized_example_id": "ex_004850",
"source_idx": 4850,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1345,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34",
"budget": 1345
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004850",
"normalized_example_id": "ex_004850",
"source_idx": 4850,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1345,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3759
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004851",
"normalized_example_id": "ex_004851",
"source_idx": 4851,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6265,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5012
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004851",
"normalized_example_id": "ex_004851",
"source_idx": 4851,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6265,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6265
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004851",
"normalized_example_id": "ex_004851",
"source_idx": 4851,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6265,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(7,9)",
"budget": 3217
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004852",
"normalized_example_id": "ex_004852",
"source_idx": 4852,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5361,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(7,9)",
"budget": 4289
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004852",
"normalized_example_id": "ex_004852",
"source_idx": 4852,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5361,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(7,9)",
"budget": 5361
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004852",
"normalized_example_id": "ex_004852",
"source_idx": 4852,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5361,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2147
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004855",
"normalized_example_id": "ex_004855",
"source_idx": 4855,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3579,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2863
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004855",
"normalized_example_id": "ex_004855",
"source_idx": 4855,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3579,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3579
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004855",
"normalized_example_id": "ex_004855",
"source_idx": 4855,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3579,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90",
"budget": 3571
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004857",
"normalized_example_id": "ex_004857",
"source_idx": 4857,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5951,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90",
"budget": 4761
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004857",
"normalized_example_id": "ex_004857",
"source_idx": 4857,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5951,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90",
"budget": 5951
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004857",
"normalized_example_id": "ex_004857",
"source_idx": 4857,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5951,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{\\sqrt{3}}",
"budget": 5474
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004860",
"normalized_example_id": "ex_004860",
"source_idx": 4860,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9123,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{\\sqrt{3}}",
"budget": 7298
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004860",
"normalized_example_id": "ex_004860",
"source_idx": 4860,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9123,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{\\sqrt{3}}",
"budget": 9123
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004860",
"normalized_example_id": "ex_004860",
"source_idx": 4860,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9123,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(p, q, r, n) = (3, 2, 5, 1) \\text{ and } (p, q, r, n) = (5, 3, 2, 4)",
"budget": 6020
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004862",
"normalized_example_id": "ex_004862",
"source_idx": 4862,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(p, q, r, n) = (3, 2, 5, 1) \\text{ and } (p, q, r, n) = (5, 3, 2, 4)",
"budget": 8027
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004862",
"normalized_example_id": "ex_004862",
"source_idx": 4862,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(p, q, r, n) = (3, 2, 5, 1) \\text{ and } (p, q, r, n) = (5, 3, 2, 4)",
"budget": 10034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004862",
"normalized_example_id": "ex_004862",
"source_idx": 4862,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10034,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.