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": "C",
"budget": 3559
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002635",
"normalized_example_id": "ex_002635",
"source_idx": 2635,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5931,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 4745
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002635",
"normalized_example_id": "ex_002635",
"source_idx": 2635,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5931,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 5931
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002635",
"normalized_example_id": "ex_002635",
"source_idx": 2635,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5931,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3914
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002636",
"normalized_example_id": "ex_002636",
"source_idx": 2636,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6523,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5218
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002636",
"normalized_example_id": "ex_002636",
"source_idx": 2636,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6523,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6523
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002636",
"normalized_example_id": "ex_002636",
"source_idx": 2636,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6523,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 3161
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002637",
"normalized_example_id": "ex_002637",
"source_idx": 2637,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5269,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 4215
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002637",
"normalized_example_id": "ex_002637",
"source_idx": 2637,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5269,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 5269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002637",
"normalized_example_id": "ex_002637",
"source_idx": 2637,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5269,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "144",
"budget": 5264
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002638",
"normalized_example_id": "ex_002638",
"source_idx": 2638,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8774,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "144",
"budget": 7019
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002638",
"normalized_example_id": "ex_002638",
"source_idx": 2638,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8774,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "144",
"budget": 8774
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002638",
"normalized_example_id": "ex_002638",
"source_idx": 2638,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8774,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(12,13,57)",
"budget": 4352
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002640",
"normalized_example_id": "ex_002640",
"source_idx": 2640,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7254,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(12,13,57)",
"budget": 5803
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002640",
"normalized_example_id": "ex_002640",
"source_idx": 2640,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7254,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(12,13,57)",
"budget": 7254
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002640",
"normalized_example_id": "ex_002640",
"source_idx": 2640,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7254,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "937",
"budget": 1311
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002643",
"normalized_example_id": "ex_002643",
"source_idx": 2643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2185,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "937",
"budget": 1748
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002643",
"normalized_example_id": "ex_002643",
"source_idx": 2643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2185,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "937",
"budget": 2185
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002643",
"normalized_example_id": "ex_002643",
"source_idx": 2643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2185,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{27}{2}",
"budget": 1435
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002646",
"normalized_example_id": "ex_002646",
"source_idx": 2646,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2391,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{27}{2}",
"budget": 1913
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002646",
"normalized_example_id": "ex_002646",
"source_idx": 2646,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2391,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{27}{2}",
"budget": 2391
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002646",
"normalized_example_id": "ex_002646",
"source_idx": 2646,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2391,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4158
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002649",
"normalized_example_id": "ex_002649",
"source_idx": 2649,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5544
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002649",
"normalized_example_id": "ex_002649",
"source_idx": 2649,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6930
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002649",
"normalized_example_id": "ex_002649",
"source_idx": 2649,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 1517
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002651",
"normalized_example_id": "ex_002651",
"source_idx": 2651,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2528,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 2022
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002651",
"normalized_example_id": "ex_002651",
"source_idx": 2651,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2528,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 2528
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002651",
"normalized_example_id": "ex_002651",
"source_idx": 2651,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2528,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2} \\times 3^{668}",
"budget": 1820
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002653",
"normalized_example_id": "ex_002653",
"source_idx": 2653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2} \\times 3^{668}",
"budget": 2427
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002653",
"normalized_example_id": "ex_002653",
"source_idx": 2653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2} \\times 3^{668}",
"budget": 3034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002653",
"normalized_example_id": "ex_002653",
"source_idx": 2653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16,1312,3112",
"budget": 4200
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002655",
"normalized_example_id": "ex_002655",
"source_idx": 2655,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7000,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16,1312,3112",
"budget": 5600
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002655",
"normalized_example_id": "ex_002655",
"source_idx": 2655,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7000,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16,1312,3112",
"budget": 7000
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002655",
"normalized_example_id": "ex_002655",
"source_idx": 2655,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7000,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}",
"budget": 1140
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002659",
"normalized_example_id": "ex_002659",
"source_idx": 2659,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1900,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}",
"budget": 1520
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002659",
"normalized_example_id": "ex_002659",
"source_idx": 2659,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1900,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}",
"budget": 1900
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002659",
"normalized_example_id": "ex_002659",
"source_idx": 2659,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1900,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002663",
"normalized_example_id": "ex_002663",
"source_idx": 2663,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 827
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002663",
"normalized_example_id": "ex_002663",
"source_idx": 2663,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002663",
"normalized_example_id": "ex_002663",
"source_idx": 2663,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "175",
"budget": 3675
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002664",
"normalized_example_id": "ex_002664",
"source_idx": 2664,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6125,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "175",
"budget": 4900
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002664",
"normalized_example_id": "ex_002664",
"source_idx": 2664,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6125,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "175",
"budget": 6125
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002664",
"normalized_example_id": "ex_002664",
"source_idx": 2664,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6125,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 4691
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002665",
"normalized_example_id": "ex_002665",
"source_idx": 2665,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7818,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 6254
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002665",
"normalized_example_id": "ex_002665",
"source_idx": 2665,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7818,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 7818
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002665",
"normalized_example_id": "ex_002665",
"source_idx": 2665,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7818,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 4k - 1",
"budget": 2292
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002667",
"normalized_example_id": "ex_002667",
"source_idx": 2667,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3820,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 4k - 1",
"budget": 3056
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002667",
"normalized_example_id": "ex_002667",
"source_idx": 2667,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3820,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 4k - 1",
"budget": 3820
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002667",
"normalized_example_id": "ex_002667",
"source_idx": 2667,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3820,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "486",
"budget": 4694
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002668",
"normalized_example_id": "ex_002668",
"source_idx": 2668,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7824,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "486",
"budget": 6259
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002668",
"normalized_example_id": "ex_002668",
"source_idx": 2668,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7824,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "486",
"budget": 7824
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002668",
"normalized_example_id": "ex_002668",
"source_idx": 2668,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7824,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 2482
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002669",
"normalized_example_id": "ex_002669",
"source_idx": 2669,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4136,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 3309
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002669",
"normalized_example_id": "ex_002669",
"source_idx": 2669,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4136,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 4136
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002669",
"normalized_example_id": "ex_002669",
"source_idx": 2669,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4136,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1,-3,0,1,3",
"budget": 2171
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002670",
"normalized_example_id": "ex_002670",
"source_idx": 2670,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3619,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1,-3,0,1,3",
"budget": 2895
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002670",
"normalized_example_id": "ex_002670",
"source_idx": 2670,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3619,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1,-3,0,1,3",
"budget": 3619
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002670",
"normalized_example_id": "ex_002670",
"source_idx": 2670,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3619,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=3, b=-1",
"budget": 4282
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002672",
"normalized_example_id": "ex_002672",
"source_idx": 2672,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7136,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=3, b=-1",
"budget": 5709
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002672",
"normalized_example_id": "ex_002672",
"source_idx": 2672,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7136,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=3, b=-1",
"budget": 7136
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002672",
"normalized_example_id": "ex_002672",
"source_idx": 2672,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7136,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,3,0)",
"budget": 4915
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002673",
"normalized_example_id": "ex_002673",
"source_idx": 2673,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8191,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,3,0)",
"budget": 6553
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002673",
"normalized_example_id": "ex_002673",
"source_idx": 2673,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8191,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,3,0)",
"budget": 8191
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002673",
"normalized_example_id": "ex_002673",
"source_idx": 2673,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8191,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 1606
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002676",
"normalized_example_id": "ex_002676",
"source_idx": 2676,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2676,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 2141
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002676",
"normalized_example_id": "ex_002676",
"source_idx": 2676,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2676,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 2676
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002676",
"normalized_example_id": "ex_002676",
"source_idx": 2676,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2676,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90",
"budget": 3344
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002679",
"normalized_example_id": "ex_002679",
"source_idx": 2679,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5574,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90",
"budget": 4459
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002679",
"normalized_example_id": "ex_002679",
"source_idx": 2679,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5574,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90",
"budget": 5574
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002679",
"normalized_example_id": "ex_002679",
"source_idx": 2679,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5574,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "s = 4",
"budget": 2387
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002680",
"normalized_example_id": "ex_002680",
"source_idx": 2680,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3979,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "s = 4",
"budget": 3183
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002680",
"normalized_example_id": "ex_002680",
"source_idx": 2680,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3979,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "s = 4",
"budget": 3979
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002680",
"normalized_example_id": "ex_002680",
"source_idx": 2680,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3979,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1985",
"budget": 1936
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002682",
"normalized_example_id": "ex_002682",
"source_idx": 2682,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1985",
"budget": 2582
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002682",
"normalized_example_id": "ex_002682",
"source_idx": 2682,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1985",
"budget": 3227
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002682",
"normalized_example_id": "ex_002682",
"source_idx": 2682,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1336",
"budget": 1165
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002683",
"normalized_example_id": "ex_002683",
"source_idx": 2683,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1336",
"budget": 1554
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002683",
"normalized_example_id": "ex_002683",
"source_idx": 2683,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1336",
"budget": 1942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002683",
"normalized_example_id": "ex_002683",
"source_idx": 2683,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "500",
"budget": 3172
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002686",
"normalized_example_id": "ex_002686",
"source_idx": 2686,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5287,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "500",
"budget": 4230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002686",
"normalized_example_id": "ex_002686",
"source_idx": 2686,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5287,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "500",
"budget": 5287
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002686",
"normalized_example_id": "ex_002686",
"source_idx": 2686,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5287,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "312",
"budget": 4915
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002688",
"normalized_example_id": "ex_002688",
"source_idx": 2688,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8192,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "312",
"budget": 6554
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002688",
"normalized_example_id": "ex_002688",
"source_idx": 2688,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8192,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "312",
"budget": 8192
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002688",
"normalized_example_id": "ex_002688",
"source_idx": 2688,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8192,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "KN=R",
"budget": 5069
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002693",
"normalized_example_id": "ex_002693",
"source_idx": 2693,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8449,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "KN=R",
"budget": 6759
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002693",
"normalized_example_id": "ex_002693",
"source_idx": 2693,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8449,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "KN=R",
"budget": 8449
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002693",
"normalized_example_id": "ex_002693",
"source_idx": 2693,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8449,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(t, t, 4t), (2t, t, 6t), (t, 2t, 6t)",
"budget": 3540
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002694",
"normalized_example_id": "ex_002694",
"source_idx": 2694,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5900,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(t, t, 4t), (2t, t, 6t), (t, 2t, 6t)",
"budget": 4720
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002694",
"normalized_example_id": "ex_002694",
"source_idx": 2694,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5900,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(t, t, 4t), (2t, t, 6t), (t, 2t, 6t)",
"budget": 5900
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002694",
"normalized_example_id": "ex_002694",
"source_idx": 2694,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5900,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1999,2000,2001",
"budget": 2146
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002695",
"normalized_example_id": "ex_002695",
"source_idx": 2695,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3577,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1999,2000,2001",
"budget": 2862
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002695",
"normalized_example_id": "ex_002695",
"source_idx": 2695,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3577,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1999,2000,2001",
"budget": 3577
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002695",
"normalized_example_id": "ex_002695",
"source_idx": 2695,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3577,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70",
"budget": 3119
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002698",
"normalized_example_id": "ex_002698",
"source_idx": 2698,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5198,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70",
"budget": 4158
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002698",
"normalized_example_id": "ex_002698",
"source_idx": 2698,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5198,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70",
"budget": 5198
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002698",
"normalized_example_id": "ex_002698",
"source_idx": 2698,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5198,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1552
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002699",
"normalized_example_id": "ex_002699",
"source_idx": 2699,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2587,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2070
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002699",
"normalized_example_id": "ex_002699",
"source_idx": 2699,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2587,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2587
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002699",
"normalized_example_id": "ex_002699",
"source_idx": 2699,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2587,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e",
"budget": 2137
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002702",
"normalized_example_id": "ex_002702",
"source_idx": 2702,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3562,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.