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": "5\\pi",
"budget": 1900
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000000",
"normalized_example_id": "ex_000000",
"source_idx": 0,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3166,
"ca... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 2533
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000000",
"normalized_example_id": "ex_000000",
"source_idx": 0,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3166,
"ca... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 3166
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000000",
"normalized_example_id": "ex_000000",
"source_idx": 0,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3166,
"ca... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1023
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000001",
"normalized_example_id": "ex_000001",
"source_idx": 1,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1705,
"ca... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1364
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000001",
"normalized_example_id": "ex_000001",
"source_idx": 1,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1705,
"ca... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1705
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000001",
"normalized_example_id": "ex_000001",
"source_idx": 1,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1705,
"ca... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4184
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000005",
"normalized_example_id": "ex_000005",
"source_idx": 5,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6974,
"ca... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5579
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000005",
"normalized_example_id": "ex_000005",
"source_idx": 5,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6974,
"ca... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6974
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000005",
"normalized_example_id": "ex_000005",
"source_idx": 5,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6974,
"ca... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x,y,z)\\in{(0,1,1),(1,0,1),(1,1,0)}",
"budget": 3879
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000008",
"normalized_example_id": "ex_000008",
"source_idx": 8,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6465,
"ca... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x,y,z)\\in{(0,1,1),(1,0,1),(1,1,0)}",
"budget": 5172
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000008",
"normalized_example_id": "ex_000008",
"source_idx": 8,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6465,
"ca... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x,y,z)\\in{(0,1,1),(1,0,1),(1,1,0)}",
"budget": 6465
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000008",
"normalized_example_id": "ex_000008",
"source_idx": 8,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6465,
"ca... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "216543",
"budget": 3569
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000011",
"normalized_example_id": "ex_000011",
"source_idx": 11,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5948,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "216543",
"budget": 4758
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000011",
"normalized_example_id": "ex_000011",
"source_idx": 11,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5948,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "216543",
"budget": 5948
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000011",
"normalized_example_id": "ex_000011",
"source_idx": 11,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5948,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n) = n + 1",
"budget": 5926
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000012",
"normalized_example_id": "ex_000012",
"source_idx": 12,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9876,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n) = n + 1",
"budget": 7901
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000012",
"normalized_example_id": "ex_000012",
"source_idx": 12,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9876,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n) = n + 1",
"budget": 9876
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000012",
"normalized_example_id": "ex_000012",
"source_idx": 12,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9876,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "441",
"budget": 1039
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000013",
"normalized_example_id": "ex_000013",
"source_idx": 13,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1732,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "441",
"budget": 1386
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000013",
"normalized_example_id": "ex_000013",
"source_idx": 13,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1732,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "441",
"budget": 1732
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000013",
"normalized_example_id": "ex_000013",
"source_idx": 13,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1732,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 4474
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000014",
"normalized_example_id": "ex_000014",
"source_idx": 14,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7457,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 5966
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000014",
"normalized_example_id": "ex_000014",
"source_idx": 14,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7457,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 7457
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000014",
"normalized_example_id": "ex_000014",
"source_idx": 14,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7457,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3820
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000017",
"normalized_example_id": "ex_000017",
"source_idx": 17,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6366,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5093
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000017",
"normalized_example_id": "ex_000017",
"source_idx": 17,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6366,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000017",
"normalized_example_id": "ex_000017",
"source_idx": 17,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6366,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 3414
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000020",
"normalized_example_id": "ex_000020",
"source_idx": 20,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5690,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 4552
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000020",
"normalized_example_id": "ex_000020",
"source_idx": 20,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5690,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 5690
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000020",
"normalized_example_id": "ex_000020",
"source_idx": 20,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5690,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18480",
"budget": 2070
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000021",
"normalized_example_id": "ex_000021",
"source_idx": 21,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3450,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18480",
"budget": 2760
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000021",
"normalized_example_id": "ex_000021",
"source_idx": 21,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3450,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18480",
"budget": 3450
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000021",
"normalized_example_id": "ex_000021",
"source_idx": 21,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3450,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}",
"budget": 2765
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000022",
"normalized_example_id": "ex_000022",
"source_idx": 22,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4608,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}",
"budget": 3686
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000022",
"normalized_example_id": "ex_000022",
"source_idx": 22,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4608,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}",
"budget": 4608
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000022",
"normalized_example_id": "ex_000022",
"source_idx": 22,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4608,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2554
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000026",
"normalized_example_id": "ex_000026",
"source_idx": 26,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4256,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3405
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000026",
"normalized_example_id": "ex_000026",
"source_idx": 26,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4256,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4256
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000026",
"normalized_example_id": "ex_000026",
"source_idx": 26,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4256,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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<m<0",
"budget": 4573
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000027",
"normalized_example_id": "ex_000027",
"source_idx": 27,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7621,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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<m<0",
"budget": 6097
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000027",
"normalized_example_id": "ex_000027",
"source_idx": 27,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7621,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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<m<0",
"budget": 7621
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000027",
"normalized_example_id": "ex_000027",
"source_idx": 27,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7621,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3\\sqrt{2}",
"budget": 4078
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000028",
"normalized_example_id": "ex_000028",
"source_idx": 28,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6796,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3\\sqrt{2}",
"budget": 5437
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000028",
"normalized_example_id": "ex_000028",
"source_idx": 28,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6796,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3\\sqrt{2}",
"budget": 6796
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000028",
"normalized_example_id": "ex_000028",
"source_idx": 28,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6796,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "108",
"budget": 1825
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000031",
"normalized_example_id": "ex_000031",
"source_idx": 31,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3042,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "108",
"budget": 2434
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000031",
"normalized_example_id": "ex_000031",
"source_idx": 31,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3042,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "108",
"budget": 3042
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000031",
"normalized_example_id": "ex_000031",
"source_idx": 31,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3042,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "121",
"budget": 1454
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000033",
"normalized_example_id": "ex_000033",
"source_idx": 33,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2424,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "121",
"budget": 1939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000033",
"normalized_example_id": "ex_000033",
"source_idx": 33,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2424,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "121",
"budget": 2424
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000033",
"normalized_example_id": "ex_000033",
"source_idx": 33,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2424,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 2894
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000034",
"normalized_example_id": "ex_000034",
"source_idx": 34,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4824,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 3859
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000034",
"normalized_example_id": "ex_000034",
"source_idx": 34,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4824,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 4824
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000034",
"normalized_example_id": "ex_000034",
"source_idx": 34,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4824,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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:P=2:5",
"budget": 2283
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000035",
"normalized_example_id": "ex_000035",
"source_idx": 35,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3805,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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:P=2:5",
"budget": 3044
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000035",
"normalized_example_id": "ex_000035",
"source_idx": 35,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3805,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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:P=2:5",
"budget": 3805
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000035",
"normalized_example_id": "ex_000035",
"source_idx": 35,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3805,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "180",
"budget": 5565
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000037",
"normalized_example_id": "ex_000037",
"source_idx": 37,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9275,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "180",
"budget": 7420
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000037",
"normalized_example_id": "ex_000037",
"source_idx": 37,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9275,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "180",
"budget": 9275
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000037",
"normalized_example_id": "ex_000037",
"source_idx": 37,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9275,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2374
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000039",
"normalized_example_id": "ex_000039",
"source_idx": 39,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3956,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3165
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000039",
"normalized_example_id": "ex_000039",
"source_idx": 39,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3956,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3956
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000039",
"normalized_example_id": "ex_000039",
"source_idx": 39,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3956,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 2008
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000040",
"normalized_example_id": "ex_000040",
"source_idx": 40,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3347,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 2678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000040",
"normalized_example_id": "ex_000040",
"source_idx": 40,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3347,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 3347
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000040",
"normalized_example_id": "ex_000040",
"source_idx": 40,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3347,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25\\mathrm{~}",
"budget": 670
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000041",
"normalized_example_id": "ex_000041",
"source_idx": 41,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1117,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25\\mathrm{~}",
"budget": 894
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000041",
"normalized_example_id": "ex_000041",
"source_idx": 41,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1117,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25\\mathrm{~}",
"budget": 1117
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000041",
"normalized_example_id": "ex_000041",
"source_idx": 41,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1117,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1469
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000042",
"normalized_example_id": "ex_000042",
"source_idx": 42,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2448,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1958
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000042",
"normalized_example_id": "ex_000042",
"source_idx": 42,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2448,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2448
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000042",
"normalized_example_id": "ex_000042",
"source_idx": 42,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2448,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 773
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000043",
"normalized_example_id": "ex_000043",
"source_idx": 43,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1288,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 1030
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000043",
"normalized_example_id": "ex_000043",
"source_idx": 43,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1288,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 1288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000043",
"normalized_example_id": "ex_000043",
"source_idx": 43,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1288,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3974}{45}",
"budget": 3170
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000044",
"normalized_example_id": "ex_000044",
"source_idx": 44,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5283,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3974}{45}",
"budget": 4226
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000044",
"normalized_example_id": "ex_000044",
"source_idx": 44,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5283,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3974}{45}",
"budget": 5283
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000044",
"normalized_example_id": "ex_000044",
"source_idx": 44,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5283,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 3709
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000045",
"normalized_example_id": "ex_000045",
"source_idx": 45,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6182,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 4946
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000045",
"normalized_example_id": "ex_000045",
"source_idx": 45,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6182,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 6182
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000045",
"normalized_example_id": "ex_000045",
"source_idx": 45,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6182,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{r\\alpha}{r-\\alpha}",
"budget": 4232
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000046",
"normalized_example_id": "ex_000046",
"source_idx": 46,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7054,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{r\\alpha}{r-\\alpha}",
"budget": 5643
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000046",
"normalized_example_id": "ex_000046",
"source_idx": 46,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7054,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{r\\alpha}{r-\\alpha}",
"budget": 7054
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000046",
"normalized_example_id": "ex_000046",
"source_idx": 46,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7054,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 1965
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000047",
"normalized_example_id": "ex_000047",
"source_idx": 47,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3275,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 2620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000047",
"normalized_example_id": "ex_000047",
"source_idx": 47,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3275,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 3275
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000047",
"normalized_example_id": "ex_000047",
"source_idx": 47,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3275,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1000",
"budget": 3748
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000051",
"normalized_example_id": "ex_000051",
"source_idx": 51,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6246,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1000",
"budget": 4997
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000051",
"normalized_example_id": "ex_000051",
"source_idx": 51,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6246,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1000",
"budget": 6246
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000051",
"normalized_example_id": "ex_000051",
"source_idx": 51,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6246,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "132",
"budget": 5325
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000053",
"normalized_example_id": "ex_000053",
"source_idx": 53,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8875,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "132",
"budget": 7100
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000053",
"normalized_example_id": "ex_000053",
"source_idx": 53,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8875,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "132",
"budget": 8875
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000053",
"normalized_example_id": "ex_000053",
"source_idx": 53,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8875,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4032,8064,12096,16128",
"budget": 1327
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000055",
"normalized_example_id": "ex_000055",
"source_idx": 55,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2211,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4032,8064,12096,16128",
"budget": 1769
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000055",
"normalized_example_id": "ex_000055",
"source_idx": 55,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2211,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4032,8064,12096,16128",
"budget": 2211
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000055",
"normalized_example_id": "ex_000055",
"source_idx": 55,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2211,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{12}",
"budget": 1185
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000057",
"normalized_example_id": "ex_000057",
"source_idx": 57,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1975,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{12}",
"budget": 1580
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000057",
"normalized_example_id": "ex_000057",
"source_idx": 57,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1975,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{12}",
"budget": 1975
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000057",
"normalized_example_id": "ex_000057",
"source_idx": 57,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1975,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "BC",
"budget": 3488
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000058",
"normalized_example_id": "ex_000058",
"source_idx": 58,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5814,
"c... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.