prompt listlengths 2 2 | label dict | metadata dict |
|---|---|---|
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{3}",
"budget": 7472
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003380",
"normalized_example_id": "ex_003380",
"source_idx": 3380,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3916",
"budget": 769
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003382",
"normalized_example_id": "ex_003382",
"source_idx": 3382,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1281,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3916",
"budget": 1025
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003382",
"normalized_example_id": "ex_003382",
"source_idx": 3382,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1281,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3916",
"budget": 1281
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003382",
"normalized_example_id": "ex_003382",
"source_idx": 3382,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1281,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1351",
"budget": 3376
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003383",
"normalized_example_id": "ex_003383",
"source_idx": 3383,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5627,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1351",
"budget": 4502
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003383",
"normalized_example_id": "ex_003383",
"source_idx": 3383,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5627,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1351",
"budget": 5627
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003383",
"normalized_example_id": "ex_003383",
"source_idx": 3383,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5627,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "Heidrun",
"budget": 4876
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003385",
"normalized_example_id": "ex_003385",
"source_idx": 3385,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8126,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "Heidrun",
"budget": 6501
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003385",
"normalized_example_id": "ex_003385",
"source_idx": 3385,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8126,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "Heidrun",
"budget": 8126
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003385",
"normalized_example_id": "ex_003385",
"source_idx": 3385,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8126,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1373
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003386",
"normalized_example_id": "ex_003386",
"source_idx": 3386,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1830
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003386",
"normalized_example_id": "ex_003386",
"source_idx": 3386,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003386",
"normalized_example_id": "ex_003386",
"source_idx": 3386,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1209
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003388",
"normalized_example_id": "ex_003388",
"source_idx": 3388,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2015,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1612
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003388",
"normalized_example_id": "ex_003388",
"source_idx": 3388,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2015,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2015
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003388",
"normalized_example_id": "ex_003388",
"source_idx": 3388,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2015,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{136}",
"budget": 4098
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003390",
"normalized_example_id": "ex_003390",
"source_idx": 3390,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6830,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{136}",
"budget": 5464
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003390",
"normalized_example_id": "ex_003390",
"source_idx": 3390,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6830,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{136}",
"budget": 6830
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003390",
"normalized_example_id": "ex_003390",
"source_idx": 3390,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6830,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7.5",
"budget": 1208
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003395",
"normalized_example_id": "ex_003395",
"source_idx": 3395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2014,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7.5",
"budget": 1611
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003395",
"normalized_example_id": "ex_003395",
"source_idx": 3395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2014,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7.5",
"budget": 2014
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003395",
"normalized_example_id": "ex_003395",
"source_idx": 3395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2014,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{\\frac{4}{3}}",
"budget": 1775
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003396",
"normalized_example_id": "ex_003396",
"source_idx": 3396,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2958,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{\\frac{4}{3}}",
"budget": 2366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003396",
"normalized_example_id": "ex_003396",
"source_idx": 3396,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2958,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{\\frac{4}{3}}",
"budget": 2958
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003396",
"normalized_example_id": "ex_003396",
"source_idx": 3396,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2958,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x^{2}+y^{2}\\leq9",
"budget": 2909
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003400",
"normalized_example_id": "ex_003400",
"source_idx": 3400,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4849,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x^{2}+y^{2}\\leq9",
"budget": 3879
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003400",
"normalized_example_id": "ex_003400",
"source_idx": 3400,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4849,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x^{2}+y^{2}\\leq9",
"budget": 4849
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003400",
"normalized_example_id": "ex_003400",
"source_idx": 3400,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4849,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 1515
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003401",
"normalized_example_id": "ex_003401",
"source_idx": 3401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2525,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 2020
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003401",
"normalized_example_id": "ex_003401",
"source_idx": 3401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2525,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 2525
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003401",
"normalized_example_id": "ex_003401",
"source_idx": 3401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2525,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{501}",
"budget": 4767
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003402",
"normalized_example_id": "ex_003402",
"source_idx": 3402,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7945,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{501}",
"budget": 6356
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003402",
"normalized_example_id": "ex_003402",
"source_idx": 3402,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7945,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{501}",
"budget": 7945
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003402",
"normalized_example_id": "ex_003402",
"source_idx": 3402,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7945,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 3482
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003403",
"normalized_example_id": "ex_003403",
"source_idx": 3403,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5803,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 4642
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003403",
"normalized_example_id": "ex_003403",
"source_idx": 3403,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5803,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 5803
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003403",
"normalized_example_id": "ex_003403",
"source_idx": 3403,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5803,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\ln\\frac{3}{2}",
"budget": 1222
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003404",
"normalized_example_id": "ex_003404",
"source_idx": 3404,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2037,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\ln\\frac{3}{2}",
"budget": 1630
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003404",
"normalized_example_id": "ex_003404",
"source_idx": 3404,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2037,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\ln\\frac{3}{2}",
"budget": 2037
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003404",
"normalized_example_id": "ex_003404",
"source_idx": 3404,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2037,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "44",
"budget": 3604
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003409",
"normalized_example_id": "ex_003409",
"source_idx": 3409,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6007,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "44",
"budget": 4806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003409",
"normalized_example_id": "ex_003409",
"source_idx": 3409,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6007,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "44",
"budget": 6007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003409",
"normalized_example_id": "ex_003409",
"source_idx": 3409,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6007,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "634",
"budget": 944
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003410",
"normalized_example_id": "ex_003410",
"source_idx": 3410,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1573,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "634",
"budget": 1258
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003410",
"normalized_example_id": "ex_003410",
"source_idx": 3410,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1573,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "634",
"budget": 1573
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003410",
"normalized_example_id": "ex_003410",
"source_idx": 3410,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1573,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{6}",
"budget": 3099
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003411",
"normalized_example_id": "ex_003411",
"source_idx": 3411,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5165,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{6}",
"budget": 4132
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003411",
"normalized_example_id": "ex_003411",
"source_idx": 3411,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5165,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{6}",
"budget": 5165
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003411",
"normalized_example_id": "ex_003411",
"source_idx": 3411,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5165,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 11",
"budget": 3890
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003412",
"normalized_example_id": "ex_003412",
"source_idx": 3412,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6484,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 11",
"budget": 5187
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003412",
"normalized_example_id": "ex_003412",
"source_idx": 3412,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6484,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 11",
"budget": 6484
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003412",
"normalized_example_id": "ex_003412",
"source_idx": 3412,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6484,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x)=4\\left(\\frac{x^{2}(1+x)}{1-x}\\right)^{1/3}",
"budget": 2863
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003414",
"normalized_example_id": "ex_003414",
"source_idx": 3414,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4771,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x)=4\\left(\\frac{x^{2}(1+x)}{1-x}\\right)^{1/3}",
"budget": 3817
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003414",
"normalized_example_id": "ex_003414",
"source_idx": 3414,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4771,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x)=4\\left(\\frac{x^{2}(1+x)}{1-x}\\right)^{1/3}",
"budget": 4771
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003414",
"normalized_example_id": "ex_003414",
"source_idx": 3414,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4771,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 2167
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003415",
"normalized_example_id": "ex_003415",
"source_idx": 3415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3612,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 2890
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003415",
"normalized_example_id": "ex_003415",
"source_idx": 3415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3612,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 3612
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003415",
"normalized_example_id": "ex_003415",
"source_idx": 3415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3612,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3328",
"budget": 928
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003416",
"normalized_example_id": "ex_003416",
"source_idx": 3416,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3328",
"budget": 1238
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003416",
"normalized_example_id": "ex_003416",
"source_idx": 3416,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3328",
"budget": 1547
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003416",
"normalized_example_id": "ex_003416",
"source_idx": 3416,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 1657
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003417",
"normalized_example_id": "ex_003417",
"source_idx": 3417,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2761,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 2209
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003417",
"normalized_example_id": "ex_003417",
"source_idx": 3417,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2761,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 2761
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003417",
"normalized_example_id": "ex_003417",
"source_idx": 3417,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2761,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38\\%",
"budget": 793
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003418",
"normalized_example_id": "ex_003418",
"source_idx": 3418,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1322,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38\\%",
"budget": 1058
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003418",
"normalized_example_id": "ex_003418",
"source_idx": 3418,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1322,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38\\%",
"budget": 1322
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003418",
"normalized_example_id": "ex_003418",
"source_idx": 3418,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1322,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 1385
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003419",
"normalized_example_id": "ex_003419",
"source_idx": 3419,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2309,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 1847
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003419",
"normalized_example_id": "ex_003419",
"source_idx": 3419,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2309,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 2309
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003419",
"normalized_example_id": "ex_003419",
"source_idx": 3419,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2309,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38",
"budget": 5923
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003421",
"normalized_example_id": "ex_003421",
"source_idx": 3421,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9872,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38",
"budget": 7898
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003421",
"normalized_example_id": "ex_003421",
"source_idx": 3421,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9872,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38",
"budget": 9872
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003421",
"normalized_example_id": "ex_003421",
"source_idx": 3421,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9872,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\beta=\\frac{\\pi}{4}",
"budget": 3675
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003422",
"normalized_example_id": "ex_003422",
"source_idx": 3422,
"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": "\\beta=\\frac{\\pi}{4}",
"budget": 4900
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003422",
"normalized_example_id": "ex_003422",
"source_idx": 3422,
"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": "\\beta=\\frac{\\pi}{4}",
"budget": 6125
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003422",
"normalized_example_id": "ex_003422",
"source_idx": 3422,
"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": "3.5",
"budget": 2401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003423",
"normalized_example_id": "ex_003423",
"source_idx": 3423,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3.5",
"budget": 3201
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003423",
"normalized_example_id": "ex_003423",
"source_idx": 3423,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3.5",
"budget": 4001
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003423",
"normalized_example_id": "ex_003423",
"source_idx": 3423,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4001,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{AB \\cdot CD}{AB + CD}",
"budget": 2462
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003424",
"normalized_example_id": "ex_003424",
"source_idx": 3424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4104,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{AB \\cdot CD}{AB + CD}",
"budget": 3283
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003424",
"normalized_example_id": "ex_003424",
"source_idx": 3424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4104,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{AB \\cdot CD}{AB + CD}",
"budget": 4104
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003424",
"normalized_example_id": "ex_003424",
"source_idx": 3424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4104,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(A)}",
"budget": 995
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003425",
"normalized_example_id": "ex_003425",
"source_idx": 3425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1658,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(A)}",
"budget": 1326
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003425",
"normalized_example_id": "ex_003425",
"source_idx": 3425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1658,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(A)}",
"budget": 1658
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003425",
"normalized_example_id": "ex_003425",
"source_idx": 3425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1658,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5:3",
"budget": 1356
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003427",
"normalized_example_id": "ex_003427",
"source_idx": 3427,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2260,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5:3",
"budget": 1808
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003427",
"normalized_example_id": "ex_003427",
"source_idx": 3427,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2260,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5:3",
"budget": 2260
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003427",
"normalized_example_id": "ex_003427",
"source_idx": 3427,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2260,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(a, b) = a | b",
"budget": 1859
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003428",
"normalized_example_id": "ex_003428",
"source_idx": 3428,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(a, b) = a | b",
"budget": 2479
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003428",
"normalized_example_id": "ex_003428",
"source_idx": 3428,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(a, b) = a | b",
"budget": 3099
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003428",
"normalized_example_id": "ex_003428",
"source_idx": 3428,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "72",
"budget": 5603
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003430",
"normalized_example_id": "ex_003430",
"source_idx": 3430,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9339,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "72",
"budget": 7471
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003430",
"normalized_example_id": "ex_003430",
"source_idx": 3430,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9339,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "72",
"budget": 9339
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003430",
"normalized_example_id": "ex_003430",
"source_idx": 3430,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9339,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 2589
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003431",
"normalized_example_id": "ex_003431",
"source_idx": 3431,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4315,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 3452
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003431",
"normalized_example_id": "ex_003431",
"source_idx": 3431,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4315,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 4315
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003431",
"normalized_example_id": "ex_003431",
"source_idx": 3431,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4315,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{2}",
"budget": 4976
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003432",
"normalized_example_id": "ex_003432",
"source_idx": 3432,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8294,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{2}",
"budget": 6635
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003432",
"normalized_example_id": "ex_003432",
"source_idx": 3432,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8294,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{2}",
"budget": 8294
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003432",
"normalized_example_id": "ex_003432",
"source_idx": 3432,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8294,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.