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": "\\frac{105}{16}",
"budget": 4201
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004409",
"normalized_example_id": "ex_004409",
"source_idx": 4409,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4201,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "660",
"budget": 3723
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004410",
"normalized_example_id": "ex_004410",
"source_idx": 4410,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6205,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "660",
"budget": 4964
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004410",
"normalized_example_id": "ex_004410",
"source_idx": 4410,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6205,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "660",
"budget": 6205
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004410",
"normalized_example_id": "ex_004410",
"source_idx": 4410,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6205,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 1567
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004417",
"normalized_example_id": "ex_004417",
"source_idx": 4417,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2612,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 2090
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004417",
"normalized_example_id": "ex_004417",
"source_idx": 4417,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2612,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 2612
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004417",
"normalized_example_id": "ex_004417",
"source_idx": 4417,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2612,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}(y-z)",
"budget": 4803
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004418",
"normalized_example_id": "ex_004418",
"source_idx": 4418,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}(y-z)",
"budget": 6404
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004418",
"normalized_example_id": "ex_004418",
"source_idx": 4418,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}(y-z)",
"budget": 8005
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004418",
"normalized_example_id": "ex_004418",
"source_idx": 4418,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = \\frac{x^2 + 1}{2^x}",
"budget": 3387
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004419",
"normalized_example_id": "ex_004419",
"source_idx": 4419,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5645,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = \\frac{x^2 + 1}{2^x}",
"budget": 4516
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004419",
"normalized_example_id": "ex_004419",
"source_idx": 4419,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5645,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = \\frac{x^2 + 1}{2^x}",
"budget": 5645
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004419",
"normalized_example_id": "ex_004419",
"source_idx": 4419,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5645,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 2567
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004422",
"normalized_example_id": "ex_004422",
"source_idx": 4422,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4278,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 3422
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004422",
"normalized_example_id": "ex_004422",
"source_idx": 4422,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4278,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 4278
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004422",
"normalized_example_id": "ex_004422",
"source_idx": 4422,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4278,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 4091
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004426",
"normalized_example_id": "ex_004426",
"source_idx": 4426,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6818,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 5454
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004426",
"normalized_example_id": "ex_004426",
"source_idx": 4426,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6818,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 6818
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004426",
"normalized_example_id": "ex_004426",
"source_idx": 4426,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6818,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8}{3}\\pi(\\sqrt{10}-1)",
"budget": 3185
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004428",
"normalized_example_id": "ex_004428",
"source_idx": 4428,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5309,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8}{3}\\pi(\\sqrt{10}-1)",
"budget": 4247
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004428",
"normalized_example_id": "ex_004428",
"source_idx": 4428,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5309,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8}{3}\\pi(\\sqrt{10}-1)",
"budget": 5309
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004428",
"normalized_example_id": "ex_004428",
"source_idx": 4428,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5309,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10;12",
"budget": 3355
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004429",
"normalized_example_id": "ex_004429",
"source_idx": 4429,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5592,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10;12",
"budget": 4474
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004429",
"normalized_example_id": "ex_004429",
"source_idx": 4429,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5592,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10;12",
"budget": 5592
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004429",
"normalized_example_id": "ex_004429",
"source_idx": 4429,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5592,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "87526608",
"budget": 5021
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004431",
"normalized_example_id": "ex_004431",
"source_idx": 4431,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8368,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "87526608",
"budget": 6694
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004431",
"normalized_example_id": "ex_004431",
"source_idx": 4431,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8368,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "87526608",
"budget": 8368
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004431",
"normalized_example_id": "ex_004431",
"source_idx": 4431,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8368,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "999",
"budget": 5627
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004432",
"normalized_example_id": "ex_004432",
"source_idx": 4432,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9379,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "999",
"budget": 7503
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004432",
"normalized_example_id": "ex_004432",
"source_idx": 4432,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9379,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "999",
"budget": 9379
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004432",
"normalized_example_id": "ex_004432",
"source_idx": 4432,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9379,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 3065
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004435",
"normalized_example_id": "ex_004435",
"source_idx": 4435,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5108,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 4086
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004435",
"normalized_example_id": "ex_004435",
"source_idx": 4435,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5108,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 5108
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004435",
"normalized_example_id": "ex_004435",
"source_idx": 4435,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5108,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}{7}",
"budget": 1365
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004436",
"normalized_example_id": "ex_004436",
"source_idx": 4436,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2275,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}{7}",
"budget": 1820
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004436",
"normalized_example_id": "ex_004436",
"source_idx": 4436,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2275,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}{7}",
"budget": 2275
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004436",
"normalized_example_id": "ex_004436",
"source_idx": 4436,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2275,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+(n+1)^{2}",
"budget": 2935
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004437",
"normalized_example_id": "ex_004437",
"source_idx": 4437,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+(n+1)^{2}",
"budget": 3914
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004437",
"normalized_example_id": "ex_004437",
"source_idx": 4437,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+(n+1)^{2}",
"budget": 4892
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004437",
"normalized_example_id": "ex_004437",
"source_idx": 4437,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{100}{11}",
"budget": 1300
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004438",
"normalized_example_id": "ex_004438",
"source_idx": 4438,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2167,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{100}{11}",
"budget": 1734
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004438",
"normalized_example_id": "ex_004438",
"source_idx": 4438,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2167,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{100}{11}",
"budget": 2167
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004438",
"normalized_example_id": "ex_004438",
"source_idx": 4438,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2167,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 2031
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004439",
"normalized_example_id": "ex_004439",
"source_idx": 4439,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3385,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 2708
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004439",
"normalized_example_id": "ex_004439",
"source_idx": 4439,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3385,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 3385
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004439",
"normalized_example_id": "ex_004439",
"source_idx": 4439,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3385,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "41",
"budget": 2175
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004440",
"normalized_example_id": "ex_004440",
"source_idx": 4440,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3625,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2900
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004440",
"normalized_example_id": "ex_004440",
"source_idx": 4440,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3625,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3625
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004440",
"normalized_example_id": "ex_004440",
"source_idx": 4440,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3625,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3535
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004441",
"normalized_example_id": "ex_004441",
"source_idx": 4441,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5891,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4713
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004441",
"normalized_example_id": "ex_004441",
"source_idx": 4441,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5891,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5891
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004441",
"normalized_example_id": "ex_004441",
"source_idx": 4441,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5891,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "156",
"budget": 3985
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004442",
"normalized_example_id": "ex_004442",
"source_idx": 4442,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6642,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "156",
"budget": 5314
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004442",
"normalized_example_id": "ex_004442",
"source_idx": 4442,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6642,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "156",
"budget": 6642
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004442",
"normalized_example_id": "ex_004442",
"source_idx": 4442,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6642,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3507
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004444",
"normalized_example_id": "ex_004444",
"source_idx": 4444,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5845,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4676
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004444",
"normalized_example_id": "ex_004444",
"source_idx": 4444,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5845,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 5845
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004444",
"normalized_example_id": "ex_004444",
"source_idx": 4444,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5845,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1211",
"budget": 6020
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004445",
"normalized_example_id": "ex_004445",
"source_idx": 4445,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10033,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1211",
"budget": 8026
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004445",
"normalized_example_id": "ex_004445",
"source_idx": 4445,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10033,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1211",
"budget": 10033
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004445",
"normalized_example_id": "ex_004445",
"source_idx": 4445,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10033,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{(x^{2}+1)^{3}}",
"budget": 1904
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004450",
"normalized_example_id": "ex_004450",
"source_idx": 4450,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3174,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{(x^{2}+1)^{3}}",
"budget": 2539
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004450",
"normalized_example_id": "ex_004450",
"source_idx": 4450,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3174,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{(x^{2}+1)^{3}}",
"budget": 3174
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004450",
"normalized_example_id": "ex_004450",
"source_idx": 4450,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3174,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2\\sqrt{3}}{3}",
"budget": 2002
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004451",
"normalized_example_id": "ex_004451",
"source_idx": 4451,
"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": "\\frac{2\\sqrt{3}}{3}",
"budget": 2670
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004451",
"normalized_example_id": "ex_004451",
"source_idx": 4451,
"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": "\\frac{2\\sqrt{3}}{3}",
"budget": 3337
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004451",
"normalized_example_id": "ex_004451",
"source_idx": 4451,
"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": "a \\in (-\\infty, 0] \\cup \\left\\{ \\frac{9}{4} \\right\\}",
"budget": 2657
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004453",
"normalized_example_id": "ex_004453",
"source_idx": 4453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a \\in (-\\infty, 0] \\cup \\left\\{ \\frac{9}{4} \\right\\}",
"budget": 3543
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004453",
"normalized_example_id": "ex_004453",
"source_idx": 4453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a \\in (-\\infty, 0] \\cup \\left\\{ \\frac{9}{4} \\right\\}",
"budget": 4429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004453",
"normalized_example_id": "ex_004453",
"source_idx": 4453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1990",
"budget": 3331
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004455",
"normalized_example_id": "ex_004455",
"source_idx": 4455,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5551,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1990",
"budget": 4441
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004455",
"normalized_example_id": "ex_004455",
"source_idx": 4455,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5551,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1990",
"budget": 5551
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004455",
"normalized_example_id": "ex_004455",
"source_idx": 4455,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5551,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2459
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004456",
"normalized_example_id": "ex_004456",
"source_idx": 4456,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4098,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3278
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004456",
"normalized_example_id": "ex_004456",
"source_idx": 4456,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4098,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4098
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004456",
"normalized_example_id": "ex_004456",
"source_idx": 4456,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4098,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\cdot6=78",
"budget": 2980
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004457",
"normalized_example_id": "ex_004457",
"source_idx": 4457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4966,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\cdot6=78",
"budget": 3973
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004457",
"normalized_example_id": "ex_004457",
"source_idx": 4457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4966,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\cdot6=78",
"budget": 4966
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004457",
"normalized_example_id": "ex_004457",
"source_idx": 4457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4966,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\sqrt{3} a b}{4}",
"budget": 6127
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004460",
"normalized_example_id": "ex_004460",
"source_idx": 4460,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10211,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\sqrt{3} a b}{4}",
"budget": 8169
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004460",
"normalized_example_id": "ex_004460",
"source_idx": 4460,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10211,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\sqrt{3} a b}{4}",
"budget": 10211
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004460",
"normalized_example_id": "ex_004460",
"source_idx": 4460,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10211,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "113",
"budget": 1803
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004462",
"normalized_example_id": "ex_004462",
"source_idx": 4462,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "113",
"budget": 2404
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004462",
"normalized_example_id": "ex_004462",
"source_idx": 4462,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "113",
"budget": 3005
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004462",
"normalized_example_id": "ex_004462",
"source_idx": 4462,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4415
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004466",
"normalized_example_id": "ex_004466",
"source_idx": 4466,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7358,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5886
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004466",
"normalized_example_id": "ex_004466",
"source_idx": 4466,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7358,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7358
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004466",
"normalized_example_id": "ex_004466",
"source_idx": 4466,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7358,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 2213
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004468",
"normalized_example_id": "ex_004468",
"source_idx": 4468,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3689,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 2951
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004468",
"normalized_example_id": "ex_004468",
"source_idx": 4468,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3689,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 3689
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004468",
"normalized_example_id": "ex_004468",
"source_idx": 4468,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3689,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1089",
"budget": 1486
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004472",
"normalized_example_id": "ex_004472",
"source_idx": 4472,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2476,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1089",
"budget": 1981
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004472",
"normalized_example_id": "ex_004472",
"source_idx": 4472,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2476,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1089",
"budget": 2476
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004472",
"normalized_example_id": "ex_004472",
"source_idx": 4472,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2476,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\sigma \\text{ and } 2 \\pi",
"budget": 813
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004474",
"normalized_example_id": "ex_004474",
"source_idx": 4474,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1355,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\sigma \\text{ and } 2 \\pi",
"budget": 1084
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004474",
"normalized_example_id": "ex_004474",
"source_idx": 4474,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1355,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\sigma \\text{ and } 2 \\pi",
"budget": 1355
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004474",
"normalized_example_id": "ex_004474",
"source_idx": 4474,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1355,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4652
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004475",
"normalized_example_id": "ex_004475",
"source_idx": 4475,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7754,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6203
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004475",
"normalized_example_id": "ex_004475",
"source_idx": 4475,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7754,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7754
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004475",
"normalized_example_id": "ex_004475",
"source_idx": 4475,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7754,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.