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": "(-1,1)",
"budget": 3829
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005208",
"normalized_example_id": "ex_005208",
"source_idx": 5208,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3829,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{3}",
"budget": 3807
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005209",
"normalized_example_id": "ex_005209",
"source_idx": 5209,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6345,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{3}",
"budget": 5076
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005209",
"normalized_example_id": "ex_005209",
"source_idx": 5209,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6345,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{3}",
"budget": 6345
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005209",
"normalized_example_id": "ex_005209",
"source_idx": 5209,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6345,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3338",
"budget": 2360
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005210",
"normalized_example_id": "ex_005210",
"source_idx": 5210,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3934,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3338",
"budget": 3147
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005210",
"normalized_example_id": "ex_005210",
"source_idx": 5210,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3934,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3338",
"budget": 3934
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005210",
"normalized_example_id": "ex_005210",
"source_idx": 5210,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3934,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1840
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005214",
"normalized_example_id": "ex_005214",
"source_idx": 5214,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3066,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2453
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005214",
"normalized_example_id": "ex_005214",
"source_idx": 5214,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3066,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3066
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005214",
"normalized_example_id": "ex_005214",
"source_idx": 5214,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3066,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 3834
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005216",
"normalized_example_id": "ex_005216",
"source_idx": 5216,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6390,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 5112
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005216",
"normalized_example_id": "ex_005216",
"source_idx": 5216,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6390,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 6390
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005216",
"normalized_example_id": "ex_005216",
"source_idx": 5216,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6390,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(\\begin{pmatrix}-35&30\\\\-45&10\\end{pmatrix})",
"budget": 833
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005217",
"normalized_example_id": "ex_005217",
"source_idx": 5217,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1389,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(\\begin{pmatrix}-35&30\\\\-45&10\\end{pmatrix})",
"budget": 1111
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005217",
"normalized_example_id": "ex_005217",
"source_idx": 5217,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1389,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(\\begin{pmatrix}-35&30\\\\-45&10\\end{pmatrix})",
"budget": 1389
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005217",
"normalized_example_id": "ex_005217",
"source_idx": 5217,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1389,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\lceil \\frac{n}{2} \\rceil",
"budget": 5818
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005220",
"normalized_example_id": "ex_005220",
"source_idx": 5220,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9697,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\lceil \\frac{n}{2} \\rceil",
"budget": 7758
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005220",
"normalized_example_id": "ex_005220",
"source_idx": 5220,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9697,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\lceil \\frac{n}{2} \\rceil",
"budget": 9697
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005220",
"normalized_example_id": "ex_005220",
"source_idx": 5220,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9697,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\sqrt{2}",
"budget": 4956
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005223",
"normalized_example_id": "ex_005223",
"source_idx": 5223,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8260,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\sqrt{2}",
"budget": 6608
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005223",
"normalized_example_id": "ex_005223",
"source_idx": 5223,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8260,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\sqrt{2}",
"budget": 8260
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005223",
"normalized_example_id": "ex_005223",
"source_idx": 5223,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8260,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8Q}{\\pi}",
"budget": 1997
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005224",
"normalized_example_id": "ex_005224",
"source_idx": 5224,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3329,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8Q}{\\pi}",
"budget": 2663
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005224",
"normalized_example_id": "ex_005224",
"source_idx": 5224,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3329,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8Q}{\\pi}",
"budget": 3329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005224",
"normalized_example_id": "ex_005224",
"source_idx": 5224,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3329,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34",
"budget": 2956
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005230",
"normalized_example_id": "ex_005230",
"source_idx": 5230,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4926,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34",
"budget": 3941
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005230",
"normalized_example_id": "ex_005230",
"source_idx": 5230,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4926,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34",
"budget": 4926
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005230",
"normalized_example_id": "ex_005230",
"source_idx": 5230,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4926,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 4522
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005231",
"normalized_example_id": "ex_005231",
"source_idx": 5231,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7536,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 6029
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005231",
"normalized_example_id": "ex_005231",
"source_idx": 5231,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7536,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 7536
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005231",
"normalized_example_id": "ex_005231",
"source_idx": 5231,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7536,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{21}{11}",
"budget": 3385
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005235",
"normalized_example_id": "ex_005235",
"source_idx": 5235,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5641,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{21}{11}",
"budget": 4513
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005235",
"normalized_example_id": "ex_005235",
"source_idx": 5235,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5641,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{21}{11}",
"budget": 5641
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005235",
"normalized_example_id": "ex_005235",
"source_idx": 5235,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5641,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3906
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005238",
"normalized_example_id": "ex_005238",
"source_idx": 5238,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6510,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5208
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005238",
"normalized_example_id": "ex_005238",
"source_idx": 5238,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6510,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6510
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005238",
"normalized_example_id": "ex_005238",
"source_idx": 5238,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6510,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1589
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005239",
"normalized_example_id": "ex_005239",
"source_idx": 5239,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2649,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2119
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005239",
"normalized_example_id": "ex_005239",
"source_idx": 5239,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2649,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2649
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005239",
"normalized_example_id": "ex_005239",
"source_idx": 5239,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2649,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34",
"budget": 1439
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005245",
"normalized_example_id": "ex_005245",
"source_idx": 5245,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34",
"budget": 1918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005245",
"normalized_example_id": "ex_005245",
"source_idx": 5245,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34",
"budget": 2398
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005245",
"normalized_example_id": "ex_005245",
"source_idx": 5245,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{129}",
"budget": 3026
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005248",
"normalized_example_id": "ex_005248",
"source_idx": 5248,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5044,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{129}",
"budget": 4035
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005248",
"normalized_example_id": "ex_005248",
"source_idx": 5248,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5044,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{129}",
"budget": 5044
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005248",
"normalized_example_id": "ex_005248",
"source_idx": 5248,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5044,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 1768
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005249",
"normalized_example_id": "ex_005249",
"source_idx": 5249,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 2357
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005249",
"normalized_example_id": "ex_005249",
"source_idx": 5249,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 2946
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005249",
"normalized_example_id": "ex_005249",
"source_idx": 5249,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2401",
"budget": 2492
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005250",
"normalized_example_id": "ex_005250",
"source_idx": 5250,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4154,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2401",
"budget": 3323
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005250",
"normalized_example_id": "ex_005250",
"source_idx": 5250,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4154,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2401",
"budget": 4154
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005250",
"normalized_example_id": "ex_005250",
"source_idx": 5250,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4154,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = \\frac{1}{3}\\left(x + 2010 - 2\\frac{x+2009}{x-1}\\right)",
"budget": 4403
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005252",
"normalized_example_id": "ex_005252",
"source_idx": 5252,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7338,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = \\frac{1}{3}\\left(x + 2010 - 2\\frac{x+2009}{x-1}\\right)",
"budget": 5870
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005252",
"normalized_example_id": "ex_005252",
"source_idx": 5252,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7338,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = \\frac{1}{3}\\left(x + 2010 - 2\\frac{x+2009}{x-1}\\right)",
"budget": 7338
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005252",
"normalized_example_id": "ex_005252",
"source_idx": 5252,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7338,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 3634
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005256",
"normalized_example_id": "ex_005256",
"source_idx": 5256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6056,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 4845
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005256",
"normalized_example_id": "ex_005256",
"source_idx": 5256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6056,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 6056
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005256",
"normalized_example_id": "ex_005256",
"source_idx": 5256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6056,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{18\\sqrt{19}}{19}",
"budget": 4482
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005258",
"normalized_example_id": "ex_005258",
"source_idx": 5258,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7470,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{18\\sqrt{19}}{19}",
"budget": 5976
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005258",
"normalized_example_id": "ex_005258",
"source_idx": 5258,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7470,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{18\\sqrt{19}}{19}",
"budget": 7470
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005258",
"normalized_example_id": "ex_005258",
"source_idx": 5258,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7470,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "336",
"budget": 667
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005262",
"normalized_example_id": "ex_005262",
"source_idx": 5262,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1112,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "336",
"budget": 890
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005262",
"normalized_example_id": "ex_005262",
"source_idx": 5262,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1112,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "336",
"budget": 1112
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005262",
"normalized_example_id": "ex_005262",
"source_idx": 5262,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1112,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005264",
"normalized_example_id": "ex_005264",
"source_idx": 5264,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5448,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4358
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005264",
"normalized_example_id": "ex_005264",
"source_idx": 5264,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5448,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5448
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005264",
"normalized_example_id": "ex_005264",
"source_idx": 5264,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5448,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 2269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005270",
"normalized_example_id": "ex_005270",
"source_idx": 5270,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3781,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 3025
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005270",
"normalized_example_id": "ex_005270",
"source_idx": 5270,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3781,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 3781
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005270",
"normalized_example_id": "ex_005270",
"source_idx": 5270,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3781,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "110",
"budget": 1566
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005272",
"normalized_example_id": "ex_005272",
"source_idx": 5272,
"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": "110",
"budget": 2088
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005272",
"normalized_example_id": "ex_005272",
"source_idx": 5272,
"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": "110",
"budget": 2610
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005272",
"normalized_example_id": "ex_005272",
"source_idx": 5272,
"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": "0",
"budget": 5362
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005273",
"normalized_example_id": "ex_005273",
"source_idx": 5273,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8936,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7149
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005273",
"normalized_example_id": "ex_005273",
"source_idx": 5273,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8936,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8936
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005273",
"normalized_example_id": "ex_005273",
"source_idx": 5273,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8936,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A=B=C=60",
"budget": 2714
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005275",
"normalized_example_id": "ex_005275",
"source_idx": 5275,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4524,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A=B=C=60",
"budget": 3619
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005275",
"normalized_example_id": "ex_005275",
"source_idx": 5275,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4524,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A=B=C=60",
"budget": 4524
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005275",
"normalized_example_id": "ex_005275",
"source_idx": 5275,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4524,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 1597
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005276",
"normalized_example_id": "ex_005276",
"source_idx": 5276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2661,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 2129
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005276",
"normalized_example_id": "ex_005276",
"source_idx": 5276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2661,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 2661
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005276",
"normalized_example_id": "ex_005276",
"source_idx": 5276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2661,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 2351
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005290",
"normalized_example_id": "ex_005290",
"source_idx": 5290,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3918,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 3134
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005290",
"normalized_example_id": "ex_005290",
"source_idx": 5290,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3918,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 3918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005290",
"normalized_example_id": "ex_005290",
"source_idx": 5290,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3918,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4751
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005291",
"normalized_example_id": "ex_005291",
"source_idx": 5291,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7918,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6334
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005291",
"normalized_example_id": "ex_005291",
"source_idx": 5291,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7918,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005291",
"normalized_example_id": "ex_005291",
"source_idx": 5291,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7918,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "61",
"budget": 1959
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005293",
"normalized_example_id": "ex_005293",
"source_idx": 5293,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3265,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "61",
"budget": 2612
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005293",
"normalized_example_id": "ex_005293",
"source_idx": 5293,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3265,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "61",
"budget": 3265
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005293",
"normalized_example_id": "ex_005293",
"source_idx": 5293,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3265,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "750",
"budget": 868
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005296",
"normalized_example_id": "ex_005296",
"source_idx": 5296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1446,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "750",
"budget": 1157
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005296",
"normalized_example_id": "ex_005296",
"source_idx": 5296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1446,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "750",
"budget": 1446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005296",
"normalized_example_id": "ex_005296",
"source_idx": 5296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1446,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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} - 1",
"budget": 5272
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005297",
"normalized_example_id": "ex_005297",
"source_idx": 5297,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8786,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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} - 1",
"budget": 7029
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005297",
"normalized_example_id": "ex_005297",
"source_idx": 5297,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8786,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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} - 1",
"budget": 8786
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005297",
"normalized_example_id": "ex_005297",
"source_idx": 5297,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8786,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-1)^2",
"budget": 3218
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005298",
"normalized_example_id": "ex_005298",
"source_idx": 5298,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5364,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-1)^2",
"budget": 4291
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005298",
"normalized_example_id": "ex_005298",
"source_idx": 5298,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5364,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-1)^2",
"budget": 5364
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005298",
"normalized_example_id": "ex_005298",
"source_idx": 5298,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5364,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.