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": "1090",
"budget": 1607
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000327",
"normalized_example_id": "ex_000327",
"source_idx": 327,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1607,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 1715
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000329",
"normalized_example_id": "ex_000329",
"source_idx": 329,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2858,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 2286
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000329",
"normalized_example_id": "ex_000329",
"source_idx": 329,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2858,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 2858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000329",
"normalized_example_id": "ex_000329",
"source_idx": 329,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2858,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{7}{2};",
"budget": 2316
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000330",
"normalized_example_id": "ex_000330",
"source_idx": 330,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3860,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{7}{2};",
"budget": 3088
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000330",
"normalized_example_id": "ex_000330",
"source_idx": 330,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3860,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{7}{2};",
"budget": 3860
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000330",
"normalized_example_id": "ex_000330",
"source_idx": 330,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3860,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3181
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000334",
"normalized_example_id": "ex_000334",
"source_idx": 334,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5302,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4242
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000334",
"normalized_example_id": "ex_000334",
"source_idx": 334,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5302,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5302
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000334",
"normalized_example_id": "ex_000334",
"source_idx": 334,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5302,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "160\\mathrm{~}",
"budget": 1995
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000335",
"normalized_example_id": "ex_000335",
"source_idx": 335,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3325,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "160\\mathrm{~}",
"budget": 2660
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000335",
"normalized_example_id": "ex_000335",
"source_idx": 335,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3325,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "160\\mathrm{~}",
"budget": 3325
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000335",
"normalized_example_id": "ex_000335",
"source_idx": 335,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3325,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "882",
"budget": 1409
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000337",
"normalized_example_id": "ex_000337",
"source_idx": 337,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2349,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "882",
"budget": 1879
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000337",
"normalized_example_id": "ex_000337",
"source_idx": 337,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2349,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "882",
"budget": 2349
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000337",
"normalized_example_id": "ex_000337",
"source_idx": 337,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2349,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sin\\alpha}{k-\\sin\\alpha};k>2\\sin\\alpha",
"budget": 4596
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000338",
"normalized_example_id": "ex_000338",
"source_idx": 338,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7660,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sin\\alpha}{k-\\sin\\alpha};k>2\\sin\\alpha",
"budget": 6128
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000338",
"normalized_example_id": "ex_000338",
"source_idx": 338,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7660,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sin\\alpha}{k-\\sin\\alpha};k>2\\sin\\alpha",
"budget": 7660
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000338",
"normalized_example_id": "ex_000338",
"source_idx": 338,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7660,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2990
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000341",
"normalized_example_id": "ex_000341",
"source_idx": 341,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4984,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3987
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000341",
"normalized_example_id": "ex_000341",
"source_idx": 341,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4984,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4984
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000341",
"normalized_example_id": "ex_000341",
"source_idx": 341,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4984,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19",
"budget": 3533
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000342",
"normalized_example_id": "ex_000342",
"source_idx": 342,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5888,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19",
"budget": 4710
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000342",
"normalized_example_id": "ex_000342",
"source_idx": 342,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5888,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19",
"budget": 5888
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000342",
"normalized_example_id": "ex_000342",
"source_idx": 342,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5888,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=3^{8},n=2^{8}",
"budget": 5781
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000347",
"normalized_example_id": "ex_000347",
"source_idx": 347,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9635,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=3^{8},n=2^{8}",
"budget": 7708
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000347",
"normalized_example_id": "ex_000347",
"source_idx": 347,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9635,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=3^{8},n=2^{8}",
"budget": 9635
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000347",
"normalized_example_id": "ex_000347",
"source_idx": 347,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9635,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12453",
"budget": 1599
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000348",
"normalized_example_id": "ex_000348",
"source_idx": 348,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2665,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12453",
"budget": 2132
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000348",
"normalized_example_id": "ex_000348",
"source_idx": 348,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2665,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12453",
"budget": 2665
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000348",
"normalized_example_id": "ex_000348",
"source_idx": 348,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2665,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 4157
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000349",
"normalized_example_id": "ex_000349",
"source_idx": 349,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6929,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 5543
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000349",
"normalized_example_id": "ex_000349",
"source_idx": 349,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6929,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 6929
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000349",
"normalized_example_id": "ex_000349",
"source_idx": 349,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6929,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 1858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000350",
"normalized_example_id": "ex_000350",
"source_idx": 350,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3097,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 2478
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000350",
"normalized_example_id": "ex_000350",
"source_idx": 350,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3097,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 3097
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000350",
"normalized_example_id": "ex_000350",
"source_idx": 350,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3097,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = 0",
"budget": 3469
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000351",
"normalized_example_id": "ex_000351",
"source_idx": 351,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5782,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = 0",
"budget": 4626
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000351",
"normalized_example_id": "ex_000351",
"source_idx": 351,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5782,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = 0",
"budget": 5782
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000351",
"normalized_example_id": "ex_000351",
"source_idx": 351,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5782,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, b, p) = (1, 1, 17)",
"budget": 5785
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000355",
"normalized_example_id": "ex_000355",
"source_idx": 355,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9641,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, b, p) = (1, 1, 17)",
"budget": 7713
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000355",
"normalized_example_id": "ex_000355",
"source_idx": 355,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9641,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, b, p) = (1, 1, 17)",
"budget": 9641
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000355",
"normalized_example_id": "ex_000355",
"source_idx": 355,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9641,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\pi}{2}-\\frac{2\\pi}{3\\sqrt{3}}",
"budget": 3367
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000356",
"normalized_example_id": "ex_000356",
"source_idx": 356,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5611,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\pi}{2}-\\frac{2\\pi}{3\\sqrt{3}}",
"budget": 4489
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000356",
"normalized_example_id": "ex_000356",
"source_idx": 356,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5611,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\pi}{2}-\\frac{2\\pi}{3\\sqrt{3}}",
"budget": 5611
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000356",
"normalized_example_id": "ex_000356",
"source_idx": 356,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5611,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1841
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000357",
"normalized_example_id": "ex_000357",
"source_idx": 357,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3068,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2454
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000357",
"normalized_example_id": "ex_000357",
"source_idx": 357,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3068,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3068
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000357",
"normalized_example_id": "ex_000357",
"source_idx": 357,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3068,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "105.75",
"budget": 5278
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000358",
"normalized_example_id": "ex_000358",
"source_idx": 358,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8796,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "105.75",
"budget": 7037
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000358",
"normalized_example_id": "ex_000358",
"source_idx": 358,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8796,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "105.75",
"budget": 8796
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000358",
"normalized_example_id": "ex_000358",
"source_idx": 358,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8796,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "184320",
"budget": 2705
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000360",
"normalized_example_id": "ex_000360",
"source_idx": 360,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4508,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "184320",
"budget": 3606
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000360",
"normalized_example_id": "ex_000360",
"source_idx": 360,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4508,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "184320",
"budget": 4508
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000360",
"normalized_example_id": "ex_000360",
"source_idx": 360,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4508,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{29 \\sqrt{29}}{2}",
"budget": 3997
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000362",
"normalized_example_id": "ex_000362",
"source_idx": 362,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6661,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{29 \\sqrt{29}}{2}",
"budget": 5329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000362",
"normalized_example_id": "ex_000362",
"source_idx": 362,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6661,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{29 \\sqrt{29}}{2}",
"budget": 6661
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000362",
"normalized_example_id": "ex_000362",
"source_idx": 362,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6661,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3722
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000364",
"normalized_example_id": "ex_000364",
"source_idx": 364,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6203,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4962
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000364",
"normalized_example_id": "ex_000364",
"source_idx": 364,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6203,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6203
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000364",
"normalized_example_id": "ex_000364",
"source_idx": 364,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6203,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 1235
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000366",
"normalized_example_id": "ex_000366",
"source_idx": 366,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2059,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 1647
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000366",
"normalized_example_id": "ex_000366",
"source_idx": 366,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2059,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 2059
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000366",
"normalized_example_id": "ex_000366",
"source_idx": 366,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2059,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{y}{x} = 6",
"budget": 4365
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000368",
"normalized_example_id": "ex_000368",
"source_idx": 368,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7275,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{y}{x} = 6",
"budget": 5820
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000368",
"normalized_example_id": "ex_000368",
"source_idx": 368,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7275,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{y}{x} = 6",
"budget": 7275
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000368",
"normalized_example_id": "ex_000368",
"source_idx": 368,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7275,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2917
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000370",
"normalized_example_id": "ex_000370",
"source_idx": 370,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4861,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3889
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000370",
"normalized_example_id": "ex_000370",
"source_idx": 370,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4861,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4861
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000370",
"normalized_example_id": "ex_000370",
"source_idx": 370,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4861,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "262, 458",
"budget": 3914
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000371",
"normalized_example_id": "ex_000371",
"source_idx": 371,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6524,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "262, 458",
"budget": 5219
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000371",
"normalized_example_id": "ex_000371",
"source_idx": 371,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6524,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "262, 458",
"budget": 6524
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000371",
"normalized_example_id": "ex_000371",
"source_idx": 371,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6524,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70",
"budget": 2095
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000372",
"normalized_example_id": "ex_000372",
"source_idx": 372,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3491,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70",
"budget": 2793
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000372",
"normalized_example_id": "ex_000372",
"source_idx": 372,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3491,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70",
"budget": 3491
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000372",
"normalized_example_id": "ex_000372",
"source_idx": 372,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3491,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-\\sqrt{5}}{2}",
"budget": 3758
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000373",
"normalized_example_id": "ex_000373",
"source_idx": 373,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6263,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-\\sqrt{5}}{2}",
"budget": 5010
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000373",
"normalized_example_id": "ex_000373",
"source_idx": 373,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6263,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-\\sqrt{5}}{2}",
"budget": 6263
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000373",
"normalized_example_id": "ex_000373",
"source_idx": 373,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6263,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2x}\\cdot\\sin^{2}x",
"budget": 1442
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000374",
"normalized_example_id": "ex_000374",
"source_idx": 374,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2403,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2x}\\cdot\\sin^{2}x",
"budget": 1922
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000374",
"normalized_example_id": "ex_000374",
"source_idx": 374,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2403,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2x}\\cdot\\sin^{2}x",
"budget": 2403
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000374",
"normalized_example_id": "ex_000374",
"source_idx": 374,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2403,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4068288",
"budget": 1136
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000377",
"normalized_example_id": "ex_000377",
"source_idx": 377,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1893,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4068288",
"budget": 1514
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000377",
"normalized_example_id": "ex_000377",
"source_idx": 377,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1893,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4068288",
"budget": 1893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000377",
"normalized_example_id": "ex_000377",
"source_idx": 377,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1893,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}\\ln(x+\\sqrt{1+x^{2}})+\\frac{x\\sqrt{1+x^{2}}}{2}+C",
"budget": 1427
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000379",
"normalized_example_id": "ex_000379",
"source_idx": 379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2378,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}\\ln(x+\\sqrt{1+x^{2}})+\\frac{x\\sqrt{1+x^{2}}}{2}+C",
"budget": 1902
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000379",
"normalized_example_id": "ex_000379",
"source_idx": 379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2378,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}\\ln(x+\\sqrt{1+x^{2}})+\\frac{x\\sqrt{1+x^{2}}}{2}+C",
"budget": 2378
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000379",
"normalized_example_id": "ex_000379",
"source_idx": 379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2378,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{x^{3}-x}{8\\sqrt{x^{2}-4}}+\\frac{x}{8}\\cdot\\arcsin\\frac{2}{x}",
"budget": 3359
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000389",
"normalized_example_id": "ex_000389",
"source_idx": 389,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5599,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{x^{3}-x}{8\\sqrt{x^{2}-4}}+\\frac{x}{8}\\cdot\\arcsin\\frac{2}{x}",
"budget": 4479
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000389",
"normalized_example_id": "ex_000389",
"source_idx": 389,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5599,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{x^{3}-x}{8\\sqrt{x^{2}-4}}+\\frac{x}{8}\\cdot\\arcsin\\frac{2}{x}",
"budget": 5599
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000389",
"normalized_example_id": "ex_000389",
"source_idx": 389,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5599,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\sqrt{2}}",
"budget": 772
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000391",
"normalized_example_id": "ex_000391",
"source_idx": 391,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1287,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\sqrt{2}}",
"budget": 1030
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000391",
"normalized_example_id": "ex_000391",
"source_idx": 391,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1287,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\sqrt{2}}",
"budget": 1287
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000391",
"normalized_example_id": "ex_000391",
"source_idx": 391,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1287,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 1517
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000393",
"normalized_example_id": "ex_000393",
"source_idx": 393,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2529,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 2023
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000393",
"normalized_example_id": "ex_000393",
"source_idx": 393,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2529,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 2529
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000393",
"normalized_example_id": "ex_000393",
"source_idx": 393,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2529,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2077
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000395",
"normalized_example_id": "ex_000395",
"source_idx": 395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3462,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2770
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000395",
"normalized_example_id": "ex_000395",
"source_idx": 395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3462,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3462
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000395",
"normalized_example_id": "ex_000395",
"source_idx": 395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3462,
"... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.