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": "900",
"budget": 1075
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003772",
"normalized_example_id": "ex_003772",
"source_idx": 3772,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14",
"budget": 2163
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003774",
"normalized_example_id": "ex_003774",
"source_idx": 3774,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3605,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14",
"budget": 2884
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003774",
"normalized_example_id": "ex_003774",
"source_idx": 3774,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3605,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14",
"budget": 3605
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003774",
"normalized_example_id": "ex_003774",
"source_idx": 3774,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3605,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "133",
"budget": 1842
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003779",
"normalized_example_id": "ex_003779",
"source_idx": 3779,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3070,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "133",
"budget": 2456
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003779",
"normalized_example_id": "ex_003779",
"source_idx": 3779,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3070,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "133",
"budget": 3070
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003779",
"normalized_example_id": "ex_003779",
"source_idx": 3779,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3070,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{1}{4}",
"budget": 1335
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003781",
"normalized_example_id": "ex_003781",
"source_idx": 3781,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2225,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{1}{4}",
"budget": 1780
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003781",
"normalized_example_id": "ex_003781",
"source_idx": 3781,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2225,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{1}{4}",
"budget": 2225
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003781",
"normalized_example_id": "ex_003781",
"source_idx": 3781,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2225,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2017",
"budget": 2795
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003782",
"normalized_example_id": "ex_003782",
"source_idx": 3782,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4659,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2017",
"budget": 3727
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003782",
"normalized_example_id": "ex_003782",
"source_idx": 3782,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4659,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2017",
"budget": 4659
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003782",
"normalized_example_id": "ex_003782",
"source_idx": 3782,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4659,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1390",
"budget": 1372
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003789",
"normalized_example_id": "ex_003789",
"source_idx": 3789,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2286,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1390",
"budget": 1829
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003789",
"normalized_example_id": "ex_003789",
"source_idx": 3789,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2286,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1390",
"budget": 2286
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003789",
"normalized_example_id": "ex_003789",
"source_idx": 3789,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2286,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "46\\frac{2}{3},4\\sqrt{14}",
"budget": 1841
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003790",
"normalized_example_id": "ex_003790",
"source_idx": 3790,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3068,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "46\\frac{2}{3},4\\sqrt{14}",
"budget": 2454
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003790",
"normalized_example_id": "ex_003790",
"source_idx": 3790,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3068,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "46\\frac{2}{3},4\\sqrt{14}",
"budget": 3068
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003790",
"normalized_example_id": "ex_003790",
"source_idx": 3790,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3068,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 5023
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003793",
"normalized_example_id": "ex_003793",
"source_idx": 3793,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8371,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 6697
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003793",
"normalized_example_id": "ex_003793",
"source_idx": 3793,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8371,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 8371
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003793",
"normalized_example_id": "ex_003793",
"source_idx": 3793,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8371,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1972
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003794",
"normalized_example_id": "ex_003794",
"source_idx": 3794,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3287,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2630
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003794",
"normalized_example_id": "ex_003794",
"source_idx": 3794,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3287,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3287
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003794",
"normalized_example_id": "ex_003794",
"source_idx": 3794,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3287,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 2114
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003795",
"normalized_example_id": "ex_003795",
"source_idx": 3795,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3524,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 2819
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003795",
"normalized_example_id": "ex_003795",
"source_idx": 3795,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3524,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 3524
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003795",
"normalized_example_id": "ex_003795",
"source_idx": 3795,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3524,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "677",
"budget": 2150
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003798",
"normalized_example_id": "ex_003798",
"source_idx": 3798,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3584,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "677",
"budget": 2867
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003798",
"normalized_example_id": "ex_003798",
"source_idx": 3798,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3584,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "677",
"budget": 3584
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003798",
"normalized_example_id": "ex_003798",
"source_idx": 3798,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3584,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{3},\\frac{3+\\sqrt{13}}{2}",
"budget": 3695
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003799",
"normalized_example_id": "ex_003799",
"source_idx": 3799,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{3},\\frac{3+\\sqrt{13}}{2}",
"budget": 4927
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003799",
"normalized_example_id": "ex_003799",
"source_idx": 3799,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{3},\\frac{3+\\sqrt{13}}{2}",
"budget": 6159
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003799",
"normalized_example_id": "ex_003799",
"source_idx": 3799,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{1}=1,q_{1}=-6;p_{2}=-1,q_{2}=-6",
"budget": 3238
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003801",
"normalized_example_id": "ex_003801",
"source_idx": 3801,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5396,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{1}=1,q_{1}=-6;p_{2}=-1,q_{2}=-6",
"budget": 4317
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003801",
"normalized_example_id": "ex_003801",
"source_idx": 3801,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5396,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{1}=1,q_{1}=-6;p_{2}=-1,q_{2}=-6",
"budget": 5396
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003801",
"normalized_example_id": "ex_003801",
"source_idx": 3801,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5396,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4731",
"budget": 2959
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003802",
"normalized_example_id": "ex_003802",
"source_idx": 3802,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4931,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4731",
"budget": 3945
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003802",
"normalized_example_id": "ex_003802",
"source_idx": 3802,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4931,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4731",
"budget": 4931
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003802",
"normalized_example_id": "ex_003802",
"source_idx": 3802,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4931,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "240",
"budget": 3679
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003805",
"normalized_example_id": "ex_003805",
"source_idx": 3805,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "240",
"budget": 4905
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003805",
"normalized_example_id": "ex_003805",
"source_idx": 3805,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "240",
"budget": 6131
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003805",
"normalized_example_id": "ex_003805",
"source_idx": 3805,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}",
"budget": 1207
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003807",
"normalized_example_id": "ex_003807",
"source_idx": 3807,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2011,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}",
"budget": 1609
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003807",
"normalized_example_id": "ex_003807",
"source_idx": 3807,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2011,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}",
"budget": 2011
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003807",
"normalized_example_id": "ex_003807",
"source_idx": 3807,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2011,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 a b}{a+b}",
"budget": 1566
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003808",
"normalized_example_id": "ex_003808",
"source_idx": 3808,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2610,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 a b}{a+b}",
"budget": 2088
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003808",
"normalized_example_id": "ex_003808",
"source_idx": 3808,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2610,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 a b}{a+b}",
"budget": 2610
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003808",
"normalized_example_id": "ex_003808",
"source_idx": 3808,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2610,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{8}{3}",
"budget": 1409
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003810",
"normalized_example_id": "ex_003810",
"source_idx": 3810,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2348,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{8}{3}",
"budget": 1878
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003810",
"normalized_example_id": "ex_003810",
"source_idx": 3810,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2348,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{8}{3}",
"budget": 2348
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003810",
"normalized_example_id": "ex_003810",
"source_idx": 3810,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2348,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1679
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003813",
"normalized_example_id": "ex_003813",
"source_idx": 3813,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2799,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2239
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003813",
"normalized_example_id": "ex_003813",
"source_idx": 3813,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2799,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2799
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003813",
"normalized_example_id": "ex_003813",
"source_idx": 3813,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2799,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1147
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003814",
"normalized_example_id": "ex_003814",
"source_idx": 3814,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1912,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1530
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003814",
"normalized_example_id": "ex_003814",
"source_idx": 3814,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1912,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1912
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003814",
"normalized_example_id": "ex_003814",
"source_idx": 3814,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1912,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 2418
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003818",
"normalized_example_id": "ex_003818",
"source_idx": 3818,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4030,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 3224
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003818",
"normalized_example_id": "ex_003818",
"source_idx": 3818,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4030,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 4030
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003818",
"normalized_example_id": "ex_003818",
"source_idx": 3818,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4030,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\cos ^{2} 2 x+2 \\cos 2 x-1=0",
"budget": 5834
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003822",
"normalized_example_id": "ex_003822",
"source_idx": 3822,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9723,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\cos ^{2} 2 x+2 \\cos 2 x-1=0",
"budget": 7778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003822",
"normalized_example_id": "ex_003822",
"source_idx": 3822,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9723,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\cos ^{2} 2 x+2 \\cos 2 x-1=0",
"budget": 9723
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003822",
"normalized_example_id": "ex_003822",
"source_idx": 3822,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9723,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4683
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003828",
"normalized_example_id": "ex_003828",
"source_idx": 3828,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7805,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6244
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003828",
"normalized_example_id": "ex_003828",
"source_idx": 3828,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7805,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7805
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003828",
"normalized_example_id": "ex_003828",
"source_idx": 3828,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7805,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12or75",
"budget": 3236
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003832",
"normalized_example_id": "ex_003832",
"source_idx": 3832,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12or75",
"budget": 4315
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003832",
"normalized_example_id": "ex_003832",
"source_idx": 3832,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12or75",
"budget": 5394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003832",
"normalized_example_id": "ex_003832",
"source_idx": 3832,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 959
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003833",
"normalized_example_id": "ex_003833",
"source_idx": 3833,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1598,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 1278
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003833",
"normalized_example_id": "ex_003833",
"source_idx": 3833,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1598,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 1598
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003833",
"normalized_example_id": "ex_003833",
"source_idx": 3833,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1598,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "104",
"budget": 1624
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003835",
"normalized_example_id": "ex_003835",
"source_idx": 3835,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2707,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "104",
"budget": 2166
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003835",
"normalized_example_id": "ex_003835",
"source_idx": 3835,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2707,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "104",
"budget": 2707
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003835",
"normalized_example_id": "ex_003835",
"source_idx": 3835,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2707,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2047
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003836",
"normalized_example_id": "ex_003836",
"source_idx": 3836,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3412,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2730
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003836",
"normalized_example_id": "ex_003836",
"source_idx": 3836,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3412,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3412
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003836",
"normalized_example_id": "ex_003836",
"source_idx": 3836,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3412,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2021",
"budget": 2808
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003837",
"normalized_example_id": "ex_003837",
"source_idx": 3837,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4680,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2021",
"budget": 3744
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003837",
"normalized_example_id": "ex_003837",
"source_idx": 3837,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4680,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2021",
"budget": 4680
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003837",
"normalized_example_id": "ex_003837",
"source_idx": 3837,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4680,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3587
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003838",
"normalized_example_id": "ex_003838",
"source_idx": 3838,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5979,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4783
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003838",
"normalized_example_id": "ex_003838",
"source_idx": 3838,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5979,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5979
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003838",
"normalized_example_id": "ex_003838",
"source_idx": 3838,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5979,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}}{2} abc",
"budget": 2924
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003839",
"normalized_example_id": "ex_003839",
"source_idx": 3839,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}}{2} abc",
"budget": 3899
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003839",
"normalized_example_id": "ex_003839",
"source_idx": 3839,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}}{2} abc",
"budget": 4874
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003839",
"normalized_example_id": "ex_003839",
"source_idx": 3839,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3,7,9,21,63",
"budget": 5378
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003841",
"normalized_example_id": "ex_003841",
"source_idx": 3841,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8963,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3,7,9,21,63",
"budget": 7170
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003841",
"normalized_example_id": "ex_003841",
"source_idx": 3841,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8963,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3,7,9,21,63",
"budget": 8963
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003841",
"normalized_example_id": "ex_003841",
"source_idx": 3841,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8963,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15,75",
"budget": 3169
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003842",
"normalized_example_id": "ex_003842",
"source_idx": 3842,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5281,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15,75",
"budget": 4225
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003842",
"normalized_example_id": "ex_003842",
"source_idx": 3842,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5281,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15,75",
"budget": 5281
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003842",
"normalized_example_id": "ex_003842",
"source_idx": 3842,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5281,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 4136
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003843",
"normalized_example_id": "ex_003843",
"source_idx": 3843,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 5514
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003843",
"normalized_example_id": "ex_003843",
"source_idx": 3843,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 6893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003843",
"normalized_example_id": "ex_003843",
"source_idx": 3843,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 4029
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003844",
"normalized_example_id": "ex_003844",
"source_idx": 3844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 5372
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003844",
"normalized_example_id": "ex_003844",
"source_idx": 3844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 6715
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003844",
"normalized_example_id": "ex_003844",
"source_idx": 3844,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6715,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.