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": "\\ln\\frac{7^{3}}{3^{2}}",
"budget": 3414
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005842",
"normalized_example_id": "ex_005842",
"source_idx": 5842,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln\\frac{7^{3}}{3^{2}}",
"budget": 4552
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005842",
"normalized_example_id": "ex_005842",
"source_idx": 5842,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln\\frac{7^{3}}{3^{2}}",
"budget": 5690
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005842",
"normalized_example_id": "ex_005842",
"source_idx": 5842,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5690,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "47",
"budget": 5330
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005843",
"normalized_example_id": "ex_005843",
"source_idx": 5843,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8884,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "47",
"budget": 7107
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005843",
"normalized_example_id": "ex_005843",
"source_idx": 5843,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8884,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "47",
"budget": 8884
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005843",
"normalized_example_id": "ex_005843",
"source_idx": 5843,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8884,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3,1",
"budget": 5076
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005844",
"normalized_example_id": "ex_005844",
"source_idx": 5844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8460,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3,1",
"budget": 6768
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005844",
"normalized_example_id": "ex_005844",
"source_idx": 5844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8460,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3,1",
"budget": 8460
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005844",
"normalized_example_id": "ex_005844",
"source_idx": 5844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8460,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 709
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005845",
"normalized_example_id": "ex_005845",
"source_idx": 5845,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1182,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 946
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005845",
"normalized_example_id": "ex_005845",
"source_idx": 5845,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1182,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1182
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005845",
"normalized_example_id": "ex_005845",
"source_idx": 5845,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1182,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1463
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005848",
"normalized_example_id": "ex_005848",
"source_idx": 5848,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2438,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1950
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005848",
"normalized_example_id": "ex_005848",
"source_idx": 5848,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2438,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2438
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005848",
"normalized_example_id": "ex_005848",
"source_idx": 5848,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2438,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1, 1, 1)",
"budget": 4513
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005849",
"normalized_example_id": "ex_005849",
"source_idx": 5849,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7522,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1, 1, 1)",
"budget": 6018
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005849",
"normalized_example_id": "ex_005849",
"source_idx": 5849,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7522,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1, 1, 1)",
"budget": 7522
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005849",
"normalized_example_id": "ex_005849",
"source_idx": 5849,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7522,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{1}=0,x_{2}=-10",
"budget": 1787
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005850",
"normalized_example_id": "ex_005850",
"source_idx": 5850,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2979,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{1}=0,x_{2}=-10",
"budget": 2383
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005850",
"normalized_example_id": "ex_005850",
"source_idx": 5850,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2979,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{1}=0,x_{2}=-10",
"budget": 2979
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005850",
"normalized_example_id": "ex_005850",
"source_idx": 5850,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2979,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 4184
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005851",
"normalized_example_id": "ex_005851",
"source_idx": 5851,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6974,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 5579
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005851",
"normalized_example_id": "ex_005851",
"source_idx": 5851,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6974,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}",
"budget": 6974
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005851",
"normalized_example_id": "ex_005851",
"source_idx": 5851,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6974,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2365
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005852",
"normalized_example_id": "ex_005852",
"source_idx": 5852,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3154
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005852",
"normalized_example_id": "ex_005852",
"source_idx": 5852,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005852",
"normalized_example_id": "ex_005852",
"source_idx": 5852,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "192",
"budget": 4536
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005853",
"normalized_example_id": "ex_005853",
"source_idx": 5853,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7560,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "192",
"budget": 6048
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005853",
"normalized_example_id": "ex_005853",
"source_idx": 5853,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7560,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "192",
"budget": 7560
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005853",
"normalized_example_id": "ex_005853",
"source_idx": 5853,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7560,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n}+2}{3}",
"budget": 4463
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005855",
"normalized_example_id": "ex_005855",
"source_idx": 5855,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7439,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n}+2}{3}",
"budget": 5951
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005855",
"normalized_example_id": "ex_005855",
"source_idx": 5855,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7439,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n}+2}{3}",
"budget": 7439
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005855",
"normalized_example_id": "ex_005855",
"source_idx": 5855,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7439,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.9232",
"budget": 2940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005857",
"normalized_example_id": "ex_005857",
"source_idx": 5857,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4900,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.9232",
"budget": 3920
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005857",
"normalized_example_id": "ex_005857",
"source_idx": 5857,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4900,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.9232",
"budget": 4900
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005857",
"normalized_example_id": "ex_005857",
"source_idx": 5857,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4900,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3712
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005861",
"normalized_example_id": "ex_005861",
"source_idx": 5861,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6187,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4950
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005861",
"normalized_example_id": "ex_005861",
"source_idx": 5861,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6187,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6187
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005861",
"normalized_example_id": "ex_005861",
"source_idx": 5861,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6187,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50",
"budget": 3566
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005862",
"normalized_example_id": "ex_005862",
"source_idx": 5862,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5943,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50",
"budget": 4754
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005862",
"normalized_example_id": "ex_005862",
"source_idx": 5862,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5943,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50",
"budget": 5943
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005862",
"normalized_example_id": "ex_005862",
"source_idx": 5862,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5943,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 2326
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005863",
"normalized_example_id": "ex_005863",
"source_idx": 5863,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3876,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3101
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005863",
"normalized_example_id": "ex_005863",
"source_idx": 5863,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3876,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3876
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005863",
"normalized_example_id": "ex_005863",
"source_idx": 5863,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3876,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{144}{\\sqrt{481}}\\approx6.5658",
"budget": 4013
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005864",
"normalized_example_id": "ex_005864",
"source_idx": 5864,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6688,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{144}{\\sqrt{481}}\\approx6.5658",
"budget": 5350
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005864",
"normalized_example_id": "ex_005864",
"source_idx": 5864,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6688,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{144}{\\sqrt{481}}\\approx6.5658",
"budget": 6688
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005864",
"normalized_example_id": "ex_005864",
"source_idx": 5864,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6688,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2 \\sqrt{2}",
"budget": 5737
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005865",
"normalized_example_id": "ex_005865",
"source_idx": 5865,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9561,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2 \\sqrt{2}",
"budget": 7649
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005865",
"normalized_example_id": "ex_005865",
"source_idx": 5865,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9561,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2 \\sqrt{2}",
"budget": 9561
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005865",
"normalized_example_id": "ex_005865",
"source_idx": 5865,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9561,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{9}",
"budget": 2110
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005866",
"normalized_example_id": "ex_005866",
"source_idx": 5866,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3517,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{9}",
"budget": 2814
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005866",
"normalized_example_id": "ex_005866",
"source_idx": 5866,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3517,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{9}",
"budget": 3517
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005866",
"normalized_example_id": "ex_005866",
"source_idx": 5866,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3517,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{17}{4};\\frac{5}{2})",
"budget": 2711
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005868",
"normalized_example_id": "ex_005868",
"source_idx": 5868,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4519,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{17}{4};\\frac{5}{2})",
"budget": 3615
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005868",
"normalized_example_id": "ex_005868",
"source_idx": 5868,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4519,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{17}{4};\\frac{5}{2})",
"budget": 4519
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005868",
"normalized_example_id": "ex_005868",
"source_idx": 5868,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4519,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3810
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005869",
"normalized_example_id": "ex_005869",
"source_idx": 5869,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6350,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5080
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005869",
"normalized_example_id": "ex_005869",
"source_idx": 5869,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6350,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6350
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005869",
"normalized_example_id": "ex_005869",
"source_idx": 5869,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6350,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005870",
"normalized_example_id": "ex_005870",
"source_idx": 5870,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3256,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2605
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005870",
"normalized_example_id": "ex_005870",
"source_idx": 5870,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3256,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3256
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005870",
"normalized_example_id": "ex_005870",
"source_idx": 5870,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3256,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12:40",
"budget": 956
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005873",
"normalized_example_id": "ex_005873",
"source_idx": 5873,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1593,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12:40",
"budget": 1274
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005873",
"normalized_example_id": "ex_005873",
"source_idx": 5873,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1593,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12:40",
"budget": 1593
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005873",
"normalized_example_id": "ex_005873",
"source_idx": 5873,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1593,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{1}=30,x_{2}=\\frac{1}{10000}",
"budget": 2219
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005874",
"normalized_example_id": "ex_005874",
"source_idx": 5874,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3698,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{1}=30,x_{2}=\\frac{1}{10000}",
"budget": 2958
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005874",
"normalized_example_id": "ex_005874",
"source_idx": 5874,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3698,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{1}=30,x_{2}=\\frac{1}{10000}",
"budget": 3698
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005874",
"normalized_example_id": "ex_005874",
"source_idx": 5874,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3698,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2.4",
"budget": 2087
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005875",
"normalized_example_id": "ex_005875",
"source_idx": 5875,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3479,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2.4",
"budget": 2783
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005875",
"normalized_example_id": "ex_005875",
"source_idx": 5875,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3479,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2.4",
"budget": 3479
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005875",
"normalized_example_id": "ex_005875",
"source_idx": 5875,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3479,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e - 1",
"budget": 1023
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005876",
"normalized_example_id": "ex_005876",
"source_idx": 5876,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1705,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e - 1",
"budget": 1364
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005876",
"normalized_example_id": "ex_005876",
"source_idx": 5876,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1705,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e - 1",
"budget": 1705
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005876",
"normalized_example_id": "ex_005876",
"source_idx": 5876,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1705,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{31}}{6}",
"budget": 2281
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005880",
"normalized_example_id": "ex_005880",
"source_idx": 5880,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3802,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{31}}{6}",
"budget": 3042
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005880",
"normalized_example_id": "ex_005880",
"source_idx": 5880,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3802,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{31}}{6}",
"budget": 3802
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005880",
"normalized_example_id": "ex_005880",
"source_idx": 5880,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3802,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2533
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005882",
"normalized_example_id": "ex_005882",
"source_idx": 5882,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3377
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005882",
"normalized_example_id": "ex_005882",
"source_idx": 5882,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4221
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005882",
"normalized_example_id": "ex_005882",
"source_idx": 5882,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4221,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}}{3}",
"budget": 2304
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005885",
"normalized_example_id": "ex_005885",
"source_idx": 5885,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3840,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}}{3}",
"budget": 3072
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005885",
"normalized_example_id": "ex_005885",
"source_idx": 5885,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3840,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}}{3}",
"budget": 3840
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005885",
"normalized_example_id": "ex_005885",
"source_idx": 5885,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3840,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "140",
"budget": 1939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005886",
"normalized_example_id": "ex_005886",
"source_idx": 5886,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3232,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "140",
"budget": 2586
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005886",
"normalized_example_id": "ex_005886",
"source_idx": 5886,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3232,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "140",
"budget": 3232
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005886",
"normalized_example_id": "ex_005886",
"source_idx": 5886,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3232,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3^n - 1}{2}",
"budget": 3438
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005889",
"normalized_example_id": "ex_005889",
"source_idx": 5889,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5730,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3^n - 1}{2}",
"budget": 4584
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005889",
"normalized_example_id": "ex_005889",
"source_idx": 5889,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5730,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3^n - 1}{2}",
"budget": 5730
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005889",
"normalized_example_id": "ex_005889",
"source_idx": 5889,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5730,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2509
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005891",
"normalized_example_id": "ex_005891",
"source_idx": 5891,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4181,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3345
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005891",
"normalized_example_id": "ex_005891",
"source_idx": 5891,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4181,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4181
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005891",
"normalized_example_id": "ex_005891",
"source_idx": 5891,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4181,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{e^{x}}{\\sqrt{1+e^{2x}}}",
"budget": 3187
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005892",
"normalized_example_id": "ex_005892",
"source_idx": 5892,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5312,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{e^{x}}{\\sqrt{1+e^{2x}}}",
"budget": 4250
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005892",
"normalized_example_id": "ex_005892",
"source_idx": 5892,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5312,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{e^{x}}{\\sqrt{1+e^{2x}}}",
"budget": 5312
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005892",
"normalized_example_id": "ex_005892",
"source_idx": 5892,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5312,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17",
"budget": 2057
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005893",
"normalized_example_id": "ex_005893",
"source_idx": 5893,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17",
"budget": 2743
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005893",
"normalized_example_id": "ex_005893",
"source_idx": 5893,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17",
"budget": 3429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005893",
"normalized_example_id": "ex_005893",
"source_idx": 5893,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4:3",
"budget": 1865
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005895",
"normalized_example_id": "ex_005895",
"source_idx": 5895,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3109,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.