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": "83",
"budget": 3010
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007437",
"normalized_example_id": "ex_007437",
"source_idx": 7437,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3763,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "83",
"budget": 3763
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007437",
"normalized_example_id": "ex_007437",
"source_idx": 7437,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3763,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{55}{162}",
"budget": 4951
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007439",
"normalized_example_id": "ex_007439",
"source_idx": 7439,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8251,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{55}{162}",
"budget": 6601
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007439",
"normalized_example_id": "ex_007439",
"source_idx": 7439,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8251,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{55}{162}",
"budget": 8251
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007439",
"normalized_example_id": "ex_007439",
"source_idx": 7439,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8251,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 3490
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007440",
"normalized_example_id": "ex_007440",
"source_idx": 7440,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5816,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 4653
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007440",
"normalized_example_id": "ex_007440",
"source_idx": 7440,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5816,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 5816
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007440",
"normalized_example_id": "ex_007440",
"source_idx": 7440,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5816,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-1",
"budget": 3615
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007444",
"normalized_example_id": "ex_007444",
"source_idx": 7444,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6025,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-1",
"budget": 4820
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007444",
"normalized_example_id": "ex_007444",
"source_idx": 7444,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6025,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-1",
"budget": 6025
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007444",
"normalized_example_id": "ex_007444",
"source_idx": 7444,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6025,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3409
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007445",
"normalized_example_id": "ex_007445",
"source_idx": 7445,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5682,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4546
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007445",
"normalized_example_id": "ex_007445",
"source_idx": 7445,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5682,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5682
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007445",
"normalized_example_id": "ex_007445",
"source_idx": 7445,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5682,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 4191
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007446",
"normalized_example_id": "ex_007446",
"source_idx": 7446,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6985,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 5588
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007446",
"normalized_example_id": "ex_007446",
"source_idx": 7446,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6985,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 6985
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007446",
"normalized_example_id": "ex_007446",
"source_idx": 7446,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6985,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "832040",
"budget": 6107
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007448",
"normalized_example_id": "ex_007448",
"source_idx": 7448,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10178,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "832040",
"budget": 8142
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007448",
"normalized_example_id": "ex_007448",
"source_idx": 7448,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10178,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "832040",
"budget": 10178
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007448",
"normalized_example_id": "ex_007448",
"source_idx": 7448,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10178,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "119",
"budget": 5464
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007449",
"normalized_example_id": "ex_007449",
"source_idx": 7449,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9107,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "119",
"budget": 7286
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007449",
"normalized_example_id": "ex_007449",
"source_idx": 7449,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9107,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "119",
"budget": 9107
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007449",
"normalized_example_id": "ex_007449",
"source_idx": 7449,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9107,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "250",
"budget": 2845
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007451",
"normalized_example_id": "ex_007451",
"source_idx": 7451,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4741,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "250",
"budget": 3793
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007451",
"normalized_example_id": "ex_007451",
"source_idx": 7451,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4741,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "250",
"budget": 4741
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007451",
"normalized_example_id": "ex_007451",
"source_idx": 7451,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4741,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19or20",
"budget": 5116
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007452",
"normalized_example_id": "ex_007452",
"source_idx": 7452,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8526,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19or20",
"budget": 6821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007452",
"normalized_example_id": "ex_007452",
"source_idx": 7452,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8526,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19or20",
"budget": 8526
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007452",
"normalized_example_id": "ex_007452",
"source_idx": 7452,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8526,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 3478
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007453",
"normalized_example_id": "ex_007453",
"source_idx": 7453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5796,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 4637
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007453",
"normalized_example_id": "ex_007453",
"source_idx": 7453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5796,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 5796
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007453",
"normalized_example_id": "ex_007453",
"source_idx": 7453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5796,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "41",
"budget": 5842
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007454",
"normalized_example_id": "ex_007454",
"source_idx": 7454,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9737,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "41",
"budget": 7790
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007454",
"normalized_example_id": "ex_007454",
"source_idx": 7454,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9737,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "41",
"budget": 9737
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007454",
"normalized_example_id": "ex_007454",
"source_idx": 7454,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9737,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3087",
"budget": 1534
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007456",
"normalized_example_id": "ex_007456",
"source_idx": 7456,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2557,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3087",
"budget": 2046
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007456",
"normalized_example_id": "ex_007456",
"source_idx": 7456,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2557,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3087",
"budget": 2557
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007456",
"normalized_example_id": "ex_007456",
"source_idx": 7456,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2557,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 2083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007457",
"normalized_example_id": "ex_007457",
"source_idx": 7457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 2778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007457",
"normalized_example_id": "ex_007457",
"source_idx": 7457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 3472
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007457",
"normalized_example_id": "ex_007457",
"source_idx": 7457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4012}{2007}",
"budget": 3338
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007460",
"normalized_example_id": "ex_007460",
"source_idx": 7460,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5564,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4012}{2007}",
"budget": 4451
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007460",
"normalized_example_id": "ex_007460",
"source_idx": 7460,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5564,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4012}{2007}",
"budget": 5564
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007460",
"normalized_example_id": "ex_007460",
"source_idx": 7460,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5564,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9:30",
"budget": 5880
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007461",
"normalized_example_id": "ex_007461",
"source_idx": 7461,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9800,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9:30",
"budget": 7840
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007461",
"normalized_example_id": "ex_007461",
"source_idx": 7461,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9800,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9:30",
"budget": 9800
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007461",
"normalized_example_id": "ex_007461",
"source_idx": 7461,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9800,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x-1)",
"budget": 4699
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007466",
"normalized_example_id": "ex_007466",
"source_idx": 7466,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7831,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x-1)",
"budget": 6265
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007466",
"normalized_example_id": "ex_007466",
"source_idx": 7466,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7831,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x-1)",
"budget": 7831
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007466",
"normalized_example_id": "ex_007466",
"source_idx": 7466,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7831,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4454
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007467",
"normalized_example_id": "ex_007467",
"source_idx": 7467,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7424,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007467",
"normalized_example_id": "ex_007467",
"source_idx": 7467,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7424,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7424
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007467",
"normalized_example_id": "ex_007467",
"source_idx": 7467,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7424,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}: 1:(1+\\sqrt{3}): \\sqrt{6}",
"budget": 2647
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007469",
"normalized_example_id": "ex_007469",
"source_idx": 7469,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}: 1:(1+\\sqrt{3}): \\sqrt{6}",
"budget": 3529
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007469",
"normalized_example_id": "ex_007469",
"source_idx": 7469,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}: 1:(1+\\sqrt{3}): \\sqrt{6}",
"budget": 4411
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007469",
"normalized_example_id": "ex_007469",
"source_idx": 7469,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x \\in (-\\infty, 0) \\cup (0, \\frac{1}{2}] \\cup [2, +\\infty)",
"budget": 3596
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007470",
"normalized_example_id": "ex_007470",
"source_idx": 7470,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5994,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x \\in (-\\infty, 0) \\cup (0, \\frac{1}{2}] \\cup [2, +\\infty)",
"budget": 4795
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007470",
"normalized_example_id": "ex_007470",
"source_idx": 7470,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5994,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x \\in (-\\infty, 0) \\cup (0, \\frac{1}{2}] \\cup [2, +\\infty)",
"budget": 5994
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007470",
"normalized_example_id": "ex_007470",
"source_idx": 7470,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5994,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n(n-4)(n-5)}{6}",
"budget": 3055
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007471",
"normalized_example_id": "ex_007471",
"source_idx": 7471,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5092,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n(n-4)(n-5)}{6}",
"budget": 4074
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007471",
"normalized_example_id": "ex_007471",
"source_idx": 7471,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5092,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n(n-4)(n-5)}{6}",
"budget": 5092
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007471",
"normalized_example_id": "ex_007471",
"source_idx": 7471,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5092,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2572
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007472",
"normalized_example_id": "ex_007472",
"source_idx": 7472,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4286,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007472",
"normalized_example_id": "ex_007472",
"source_idx": 7472,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4286,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4286
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007472",
"normalized_example_id": "ex_007472",
"source_idx": 7472,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4286,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\{(11, 8, 5), (8, 11, 5), (8, 5, 11), (5, 8, 11), (11, 5, 8), (5, 11, 8)\\}",
"budget": 3156
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007477",
"normalized_example_id": "ex_007477",
"source_idx": 7477,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5260,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\{(11, 8, 5), (8, 11, 5), (8, 5, 11), (5, 8, 11), (11, 5, 8), (5, 11, 8)\\}",
"budget": 4208
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007477",
"normalized_example_id": "ex_007477",
"source_idx": 7477,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5260,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\{(11, 8, 5), (8, 11, 5), (8, 5, 11), (5, 8, 11), (11, 5, 8), (5, 11, 8)\\}",
"budget": 5260
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007477",
"normalized_example_id": "ex_007477",
"source_idx": 7477,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5260,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[-1,1]",
"budget": 2761
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007480",
"normalized_example_id": "ex_007480",
"source_idx": 7480,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4602,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[-1,1]",
"budget": 3682
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007480",
"normalized_example_id": "ex_007480",
"source_idx": 7480,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4602,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[-1,1]",
"budget": 4602
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007480",
"normalized_example_id": "ex_007480",
"source_idx": 7480,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4602,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1/128<1/100",
"budget": 2002
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007484",
"normalized_example_id": "ex_007484",
"source_idx": 7484,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1/128<1/100",
"budget": 2670
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007484",
"normalized_example_id": "ex_007484",
"source_idx": 7484,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1/128<1/100",
"budget": 3337
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007484",
"normalized_example_id": "ex_007484",
"source_idx": 7484,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^n",
"budget": 5218
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007485",
"normalized_example_id": "ex_007485",
"source_idx": 7485,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8696,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^n",
"budget": 6957
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007485",
"normalized_example_id": "ex_007485",
"source_idx": 7485,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8696,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^n",
"budget": 8696
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007485",
"normalized_example_id": "ex_007485",
"source_idx": 7485,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8696,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 1583
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007488",
"normalized_example_id": "ex_007488",
"source_idx": 7488,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 2111
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007488",
"normalized_example_id": "ex_007488",
"source_idx": 7488,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 2639
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007488",
"normalized_example_id": "ex_007488",
"source_idx": 7488,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 2290
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007493",
"normalized_example_id": "ex_007493",
"source_idx": 7493,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3817,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 3054
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007493",
"normalized_example_id": "ex_007493",
"source_idx": 7493,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3817,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 3817
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007493",
"normalized_example_id": "ex_007493",
"source_idx": 7493,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3817,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3653
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007495",
"normalized_example_id": "ex_007495",
"source_idx": 7495,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6089,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4871
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007495",
"normalized_example_id": "ex_007495",
"source_idx": 7495,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6089,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6089
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007495",
"normalized_example_id": "ex_007495",
"source_idx": 7495,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6089,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_{1}=2",
"budget": 3971
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007498",
"normalized_example_id": "ex_007498",
"source_idx": 7498,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6619,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_{1}=2",
"budget": 5295
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007498",
"normalized_example_id": "ex_007498",
"source_idx": 7498,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6619,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_{1}=2",
"budget": 6619
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007498",
"normalized_example_id": "ex_007498",
"source_idx": 7498,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6619,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2024
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007499",
"normalized_example_id": "ex_007499",
"source_idx": 7499,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3374,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2699
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007499",
"normalized_example_id": "ex_007499",
"source_idx": 7499,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3374,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3374
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007499",
"normalized_example_id": "ex_007499",
"source_idx": 7499,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3374,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.