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": "100",
"budget": 1407
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004734",
"normalized_example_id": "ex_004734",
"source_idx": 4734,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1759,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 1759
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004734",
"normalized_example_id": "ex_004734",
"source_idx": 4734,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1759,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 3710
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004735",
"normalized_example_id": "ex_004735",
"source_idx": 4735,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6184,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 4947
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004735",
"normalized_example_id": "ex_004735",
"source_idx": 4735,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6184,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 6184
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004735",
"normalized_example_id": "ex_004735",
"source_idx": 4735,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6184,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{1 + a}",
"budget": 1350
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004737",
"normalized_example_id": "ex_004737",
"source_idx": 4737,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2250,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{1 + a}",
"budget": 1800
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004737",
"normalized_example_id": "ex_004737",
"source_idx": 4737,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2250,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{1 + a}",
"budget": 2250
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004737",
"normalized_example_id": "ex_004737",
"source_idx": 4737,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2250,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "43",
"budget": 1980
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004738",
"normalized_example_id": "ex_004738",
"source_idx": 4738,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3300,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "43",
"budget": 2640
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004738",
"normalized_example_id": "ex_004738",
"source_idx": 4738,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3300,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "43",
"budget": 3300
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004738",
"normalized_example_id": "ex_004738",
"source_idx": 4738,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3300,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p=5, m=9",
"budget": 4004
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004739",
"normalized_example_id": "ex_004739",
"source_idx": 4739,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6673,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p=5, m=9",
"budget": 5338
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004739",
"normalized_example_id": "ex_004739",
"source_idx": 4739,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6673,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p=5, m=9",
"budget": 6673
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004739",
"normalized_example_id": "ex_004739",
"source_idx": 4739,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6673,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4}",
"budget": 6001
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004741",
"normalized_example_id": "ex_004741",
"source_idx": 4741,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4}",
"budget": 8001
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004741",
"normalized_example_id": "ex_004741",
"source_idx": 4741,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4}",
"budget": 10001
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004741",
"normalized_example_id": "ex_004741",
"source_idx": 4741,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2024}-1}{4\\cdot3^{2023}}",
"budget": 3419
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004742",
"normalized_example_id": "ex_004742",
"source_idx": 4742,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5698,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2024}-1}{4\\cdot3^{2023}}",
"budget": 4558
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004742",
"normalized_example_id": "ex_004742",
"source_idx": 4742,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5698,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2024}-1}{4\\cdot3^{2023}}",
"budget": 5698
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004742",
"normalized_example_id": "ex_004742",
"source_idx": 4742,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5698,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,9)",
"budget": 3259
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004743",
"normalized_example_id": "ex_004743",
"source_idx": 4743,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5431,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,9)",
"budget": 4345
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004743",
"normalized_example_id": "ex_004743",
"source_idx": 4743,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5431,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,9)",
"budget": 5431
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004743",
"normalized_example_id": "ex_004743",
"source_idx": 4743,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5431,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\log_{2}3",
"budget": 872
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004745",
"normalized_example_id": "ex_004745",
"source_idx": 4745,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1454,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\log_{2}3",
"budget": 1163
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004745",
"normalized_example_id": "ex_004745",
"source_idx": 4745,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1454,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\log_{2}3",
"budget": 1454
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004745",
"normalized_example_id": "ex_004745",
"source_idx": 4745,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1454,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1024",
"budget": 3806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004747",
"normalized_example_id": "ex_004747",
"source_idx": 4747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6344,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1024",
"budget": 5075
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004747",
"normalized_example_id": "ex_004747",
"source_idx": 4747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6344,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1024",
"budget": 6344
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004747",
"normalized_example_id": "ex_004747",
"source_idx": 4747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6344,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4,22,14",
"budget": 1684
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004749",
"normalized_example_id": "ex_004749",
"source_idx": 4749,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2806,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4,22,14",
"budget": 2245
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004749",
"normalized_example_id": "ex_004749",
"source_idx": 4749,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2806,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4,22,14",
"budget": 2806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004749",
"normalized_example_id": "ex_004749",
"source_idx": 4749,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2806,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}",
"budget": 862
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004751",
"normalized_example_id": "ex_004751",
"source_idx": 4751,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1437,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}",
"budget": 1150
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004751",
"normalized_example_id": "ex_004751",
"source_idx": 4751,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1437,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}",
"budget": 1437
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004751",
"normalized_example_id": "ex_004751",
"source_idx": 4751,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1437,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 653
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004753",
"normalized_example_id": "ex_004753",
"source_idx": 4753,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1089,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 871
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004753",
"normalized_example_id": "ex_004753",
"source_idx": 4753,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1089,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 1089
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004753",
"normalized_example_id": "ex_004753",
"source_idx": 4753,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1089,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\infty",
"budget": 3979
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004755",
"normalized_example_id": "ex_004755",
"source_idx": 4755,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6631,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\infty",
"budget": 5305
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004755",
"normalized_example_id": "ex_004755",
"source_idx": 4755,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6631,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\infty",
"budget": 6631
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004755",
"normalized_example_id": "ex_004755",
"source_idx": 4755,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6631,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1188",
"budget": 3701
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004759",
"normalized_example_id": "ex_004759",
"source_idx": 4759,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6168,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1188",
"budget": 4934
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004759",
"normalized_example_id": "ex_004759",
"source_idx": 4759,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6168,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1188",
"budget": 6168
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004759",
"normalized_example_id": "ex_004759",
"source_idx": 4759,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6168,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "r:R=1:3",
"budget": 4583
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004760",
"normalized_example_id": "ex_004760",
"source_idx": 4760,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7638,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "r:R=1:3",
"budget": 6110
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004760",
"normalized_example_id": "ex_004760",
"source_idx": 4760,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7638,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "r:R=1:3",
"budget": 7638
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004760",
"normalized_example_id": "ex_004760",
"source_idx": 4760,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7638,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3796
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004761",
"normalized_example_id": "ex_004761",
"source_idx": 4761,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 5062
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004761",
"normalized_example_id": "ex_004761",
"source_idx": 4761,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 6327
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004761",
"normalized_example_id": "ex_004761",
"source_idx": 4761,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y \\leqslant 0 \\text{ or } y \\geqslant 4",
"budget": 2383
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004763",
"normalized_example_id": "ex_004763",
"source_idx": 4763,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3971,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y \\leqslant 0 \\text{ or } y \\geqslant 4",
"budget": 3177
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004763",
"normalized_example_id": "ex_004763",
"source_idx": 4763,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3971,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y \\leqslant 0 \\text{ or } y \\geqslant 4",
"budget": 3971
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004763",
"normalized_example_id": "ex_004763",
"source_idx": 4763,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3971,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+1)(2n+1)}{6}",
"budget": 1411
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004766",
"normalized_example_id": "ex_004766",
"source_idx": 4766,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2352,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+1)(2n+1)}{6}",
"budget": 1882
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004766",
"normalized_example_id": "ex_004766",
"source_idx": 4766,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2352,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+1)(2n+1)}{6}",
"budget": 2352
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004766",
"normalized_example_id": "ex_004766",
"source_idx": 4766,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2352,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1011^2",
"budget": 1258
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004768",
"normalized_example_id": "ex_004768",
"source_idx": 4768,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2096,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1011^2",
"budget": 1677
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004768",
"normalized_example_id": "ex_004768",
"source_idx": 4768,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2096,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1011^2",
"budget": 2096
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004768",
"normalized_example_id": "ex_004768",
"source_idx": 4768,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2096,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(\\frac{1983}{n}\\right)^n",
"budget": 5336
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004772",
"normalized_example_id": "ex_004772",
"source_idx": 4772,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(\\frac{1983}{n}\\right)^n",
"budget": 7114
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004772",
"normalized_example_id": "ex_004772",
"source_idx": 4772,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(\\frac{1983}{n}\\right)^n",
"budget": 8893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004772",
"normalized_example_id": "ex_004772",
"source_idx": 4772,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "496",
"budget": 3047
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004773",
"normalized_example_id": "ex_004773",
"source_idx": 4773,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5079,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "496",
"budget": 4063
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004773",
"normalized_example_id": "ex_004773",
"source_idx": 4773,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5079,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "496",
"budget": 5079
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004773",
"normalized_example_id": "ex_004773",
"source_idx": 4773,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5079,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}}{3}",
"budget": 4280
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004775",
"normalized_example_id": "ex_004775",
"source_idx": 4775,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7133,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}}{3}",
"budget": 5706
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004775",
"normalized_example_id": "ex_004775",
"source_idx": 4775,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7133,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}}{3}",
"budget": 7133
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004775",
"normalized_example_id": "ex_004775",
"source_idx": 4775,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7133,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+19i",
"budget": 1030
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004777",
"normalized_example_id": "ex_004777",
"source_idx": 4777,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1716,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+19i",
"budget": 1373
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004777",
"normalized_example_id": "ex_004777",
"source_idx": 4777,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1716,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+19i",
"budget": 1716
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004777",
"normalized_example_id": "ex_004777",
"source_idx": 4777,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1716,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "703",
"budget": 2933
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004782",
"normalized_example_id": "ex_004782",
"source_idx": 4782,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4889,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "703",
"budget": 3911
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004782",
"normalized_example_id": "ex_004782",
"source_idx": 4782,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4889,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "703",
"budget": 4889
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004782",
"normalized_example_id": "ex_004782",
"source_idx": 4782,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4889,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1002^2",
"budget": 3202
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004783",
"normalized_example_id": "ex_004783",
"source_idx": 4783,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5336,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1002^2",
"budget": 4269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004783",
"normalized_example_id": "ex_004783",
"source_idx": 4783,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5336,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1002^2",
"budget": 5336
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004783",
"normalized_example_id": "ex_004783",
"source_idx": 4783,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5336,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17",
"budget": 5142
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004785",
"normalized_example_id": "ex_004785",
"source_idx": 4785,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8570,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17",
"budget": 6856
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004785",
"normalized_example_id": "ex_004785",
"source_idx": 4785,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8570,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17",
"budget": 8570
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004785",
"normalized_example_id": "ex_004785",
"source_idx": 4785,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8570,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{26}",
"budget": 2363
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004788",
"normalized_example_id": "ex_004788",
"source_idx": 4788,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3939,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{26}",
"budget": 3151
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004788",
"normalized_example_id": "ex_004788",
"source_idx": 4788,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3939,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{26}",
"budget": 3939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004788",
"normalized_example_id": "ex_004788",
"source_idx": 4788,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3939,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1293
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004790",
"normalized_example_id": "ex_004790",
"source_idx": 4790,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2155,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1724
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004790",
"normalized_example_id": "ex_004790",
"source_idx": 4790,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2155,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2155
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004790",
"normalized_example_id": "ex_004790",
"source_idx": 4790,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2155,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1199
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004793",
"normalized_example_id": "ex_004793",
"source_idx": 4793,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1999,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1599
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004793",
"normalized_example_id": "ex_004793",
"source_idx": 4793,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1999,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1999
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004793",
"normalized_example_id": "ex_004793",
"source_idx": 4793,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1999,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "300",
"budget": 977
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004794",
"normalized_example_id": "ex_004794",
"source_idx": 4794,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1628,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "300",
"budget": 1302
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004794",
"normalized_example_id": "ex_004794",
"source_idx": 4794,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1628,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "300",
"budget": 1628
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004794",
"normalized_example_id": "ex_004794",
"source_idx": 4794,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1628,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5910
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004795",
"normalized_example_id": "ex_004795",
"source_idx": 4795,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9850,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7880
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004795",
"normalized_example_id": "ex_004795",
"source_idx": 4795,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9850,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 9850
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004795",
"normalized_example_id": "ex_004795",
"source_idx": 4795,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9850,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 2067
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004796",
"normalized_example_id": "ex_004796",
"source_idx": 4796,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3445,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 2756
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004796",
"normalized_example_id": "ex_004796",
"source_idx": 4796,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3445,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 3445
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004796",
"normalized_example_id": "ex_004796",
"source_idx": 4796,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3445,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.622",
"budget": 3364
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004798",
"normalized_example_id": "ex_004798",
"source_idx": 4798,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5607,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.622",
"budget": 4486
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004798",
"normalized_example_id": "ex_004798",
"source_idx": 4798,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5607,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.