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": "147",
"budget": 4547
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003582",
"normalized_example_id": "ex_003582",
"source_idx": 3582,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4547,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4.89''",
"budget": 4345
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003584",
"normalized_example_id": "ex_003584",
"source_idx": 3584,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7241,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4.89''",
"budget": 5793
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003584",
"normalized_example_id": "ex_003584",
"source_idx": 3584,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7241,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4.89''",
"budget": 7241
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003584",
"normalized_example_id": "ex_003584",
"source_idx": 3584,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7241,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "727023",
"budget": 4775
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003588",
"normalized_example_id": "ex_003588",
"source_idx": 3588,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7958,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "727023",
"budget": 6366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003588",
"normalized_example_id": "ex_003588",
"source_idx": 3588,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7958,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "727023",
"budget": 7958
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003588",
"normalized_example_id": "ex_003588",
"source_idx": 3588,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7958,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1085
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003589",
"normalized_example_id": "ex_003589",
"source_idx": 3589,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1808,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003589",
"normalized_example_id": "ex_003589",
"source_idx": 3589,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1808,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1808
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003589",
"normalized_example_id": "ex_003589",
"source_idx": 3589,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1808,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14\\sqrt{5}",
"budget": 3149
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003596",
"normalized_example_id": "ex_003596",
"source_idx": 3596,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5249,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14\\sqrt{5}",
"budget": 4199
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003596",
"normalized_example_id": "ex_003596",
"source_idx": 3596,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5249,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14\\sqrt{5}",
"budget": 5249
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003596",
"normalized_example_id": "ex_003596",
"source_idx": 3596,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5249,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "49",
"budget": 5617
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003598",
"normalized_example_id": "ex_003598",
"source_idx": 3598,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9361,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "49",
"budget": 7489
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003598",
"normalized_example_id": "ex_003598",
"source_idx": 3598,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9361,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "49",
"budget": 9361
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003598",
"normalized_example_id": "ex_003598",
"source_idx": 3598,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9361,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^n",
"budget": 3595
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003599",
"normalized_example_id": "ex_003599",
"source_idx": 3599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5992,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^n",
"budget": 4794
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003599",
"normalized_example_id": "ex_003599",
"source_idx": 3599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5992,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^n",
"budget": 5992
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003599",
"normalized_example_id": "ex_003599",
"source_idx": 3599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5992,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5260
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003606",
"normalized_example_id": "ex_003606",
"source_idx": 3606,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8766,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7013
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003606",
"normalized_example_id": "ex_003606",
"source_idx": 3606,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8766,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8766
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003606",
"normalized_example_id": "ex_003606",
"source_idx": 3606,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8766,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 3896
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003607",
"normalized_example_id": "ex_003607",
"source_idx": 3607,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6494,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 5195
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003607",
"normalized_example_id": "ex_003607",
"source_idx": 3607,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6494,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 6494
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003607",
"normalized_example_id": "ex_003607",
"source_idx": 3607,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6494,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{4(2p+1)}",
"budget": 3166
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003609",
"normalized_example_id": "ex_003609",
"source_idx": 3609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5277,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{4(2p+1)}",
"budget": 4222
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003609",
"normalized_example_id": "ex_003609",
"source_idx": 3609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5277,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{4(2p+1)}",
"budget": 5277
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003609",
"normalized_example_id": "ex_003609",
"source_idx": 3609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5277,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(B)}\\\\frac{3}{8}",
"budget": 729
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003610",
"normalized_example_id": "ex_003610",
"source_idx": 3610,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1215,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(B)}\\\\frac{3}{8}",
"budget": 972
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003610",
"normalized_example_id": "ex_003610",
"source_idx": 3610,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1215,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(B)}\\\\frac{3}{8}",
"budget": 1215
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003610",
"normalized_example_id": "ex_003610",
"source_idx": 3610,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1215,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1444",
"budget": 4498
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003612",
"normalized_example_id": "ex_003612",
"source_idx": 3612,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7496,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1444",
"budget": 5997
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003612",
"normalized_example_id": "ex_003612",
"source_idx": 3612,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7496,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1444",
"budget": 7496
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003612",
"normalized_example_id": "ex_003612",
"source_idx": 3612,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7496,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,3,4,5",
"budget": 2714
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003613",
"normalized_example_id": "ex_003613",
"source_idx": 3613,
"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": "2,3,4,5",
"budget": 3619
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003613",
"normalized_example_id": "ex_003613",
"source_idx": 3613,
"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": "2,3,4,5",
"budget": 4524
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003613",
"normalized_example_id": "ex_003613",
"source_idx": 3613,
"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": "\\frac{n^2}{2(n-1)(2n-1)}",
"budget": 4735
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003615",
"normalized_example_id": "ex_003615",
"source_idx": 3615,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n^2}{2(n-1)(2n-1)}",
"budget": 6314
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003615",
"normalized_example_id": "ex_003615",
"source_idx": 3615,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n^2}{2(n-1)(2n-1)}",
"budget": 7892
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003615",
"normalized_example_id": "ex_003615",
"source_idx": 3615,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi^{2}",
"budget": 2117
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003616",
"normalized_example_id": "ex_003616",
"source_idx": 3616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3528,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi^{2}",
"budget": 2822
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003616",
"normalized_example_id": "ex_003616",
"source_idx": 3616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3528,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi^{2}",
"budget": 3528
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003616",
"normalized_example_id": "ex_003616",
"source_idx": 3616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3528,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4907
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003617",
"normalized_example_id": "ex_003617",
"source_idx": 3617,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8178,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6542
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003617",
"normalized_example_id": "ex_003617",
"source_idx": 3617,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8178,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8178
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003617",
"normalized_example_id": "ex_003617",
"source_idx": 3617,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8178,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 1112
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003619",
"normalized_example_id": "ex_003619",
"source_idx": 3619,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1854,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 1483
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003619",
"normalized_example_id": "ex_003619",
"source_idx": 3619,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1854,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 1854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003619",
"normalized_example_id": "ex_003619",
"source_idx": 3619,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1854,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36n+3",
"budget": 3128
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003621",
"normalized_example_id": "ex_003621",
"source_idx": 3621,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5214,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36n+3",
"budget": 4171
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003621",
"normalized_example_id": "ex_003621",
"source_idx": 3621,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5214,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36n+3",
"budget": 5214
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003621",
"normalized_example_id": "ex_003621",
"source_idx": 3621,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5214,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 5",
"budget": 5537
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003624",
"normalized_example_id": "ex_003624",
"source_idx": 3624,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9228,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 5",
"budget": 7382
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003624",
"normalized_example_id": "ex_003624",
"source_idx": 3624,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9228,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 5",
"budget": 9228
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003624",
"normalized_example_id": "ex_003624",
"source_idx": 3624,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9228,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:3",
"budget": 2220
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003625",
"normalized_example_id": "ex_003625",
"source_idx": 3625,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3700,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:3",
"budget": 2960
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003625",
"normalized_example_id": "ex_003625",
"source_idx": 3625,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3700,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:3",
"budget": 3700
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003625",
"normalized_example_id": "ex_003625",
"source_idx": 3625,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3700,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{-154+120\\lnx}{x^{6}\\cdot\\ln3}",
"budget": 1517
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003626",
"normalized_example_id": "ex_003626",
"source_idx": 3626,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2529,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{-154+120\\lnx}{x^{6}\\cdot\\ln3}",
"budget": 2023
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003626",
"normalized_example_id": "ex_003626",
"source_idx": 3626,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2529,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{-154+120\\lnx}{x^{6}\\cdot\\ln3}",
"budget": 2529
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003626",
"normalized_example_id": "ex_003626",
"source_idx": 3626,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2529,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{23}",
"budget": 2317
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003629",
"normalized_example_id": "ex_003629",
"source_idx": 3629,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3862,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{23}",
"budget": 3090
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003629",
"normalized_example_id": "ex_003629",
"source_idx": 3629,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3862,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{23}",
"budget": 3862
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003629",
"normalized_example_id": "ex_003629",
"source_idx": 3629,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3862,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5x",
"budget": 1368
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003632",
"normalized_example_id": "ex_003632",
"source_idx": 3632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2280,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5x",
"budget": 1824
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003632",
"normalized_example_id": "ex_003632",
"source_idx": 3632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2280,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5x",
"budget": 2280
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003632",
"normalized_example_id": "ex_003632",
"source_idx": 3632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2280,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1549
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003633",
"normalized_example_id": "ex_003633",
"source_idx": 3633,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2581,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2065
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003633",
"normalized_example_id": "ex_003633",
"source_idx": 3633,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2581,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2581
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003633",
"normalized_example_id": "ex_003633",
"source_idx": 3633,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2581,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 1854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003634",
"normalized_example_id": "ex_003634",
"source_idx": 3634,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3090,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 2472
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003634",
"normalized_example_id": "ex_003634",
"source_idx": 3634,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3090,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 3090
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003634",
"normalized_example_id": "ex_003634",
"source_idx": 3634,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3090,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1721
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003637",
"normalized_example_id": "ex_003637",
"source_idx": 3637,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2869,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2295
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003637",
"normalized_example_id": "ex_003637",
"source_idx": 3637,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2869,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2869
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003637",
"normalized_example_id": "ex_003637",
"source_idx": 3637,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2869,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 4026
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003640",
"normalized_example_id": "ex_003640",
"source_idx": 3640,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6710,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 5368
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003640",
"normalized_example_id": "ex_003640",
"source_idx": 3640,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6710,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 6710
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003640",
"normalized_example_id": "ex_003640",
"source_idx": 3640,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6710,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "300",
"budget": 2095
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003641",
"normalized_example_id": "ex_003641",
"source_idx": 3641,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3491,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "300",
"budget": 2793
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003641",
"normalized_example_id": "ex_003641",
"source_idx": 3641,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3491,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "300",
"budget": 3491
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003641",
"normalized_example_id": "ex_003641",
"source_idx": 3641,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3491,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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<x<1",
"budget": 2513
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003642",
"normalized_example_id": "ex_003642",
"source_idx": 3642,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4188,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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<x<1",
"budget": 3350
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003642",
"normalized_example_id": "ex_003642",
"source_idx": 3642,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4188,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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<x<1",
"budget": 4188
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003642",
"normalized_example_id": "ex_003642",
"source_idx": 3642,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4188,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{16}{5}",
"budget": 2222
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003643",
"normalized_example_id": "ex_003643",
"source_idx": 3643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3704,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{16}{5}",
"budget": 2963
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003643",
"normalized_example_id": "ex_003643",
"source_idx": 3643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3704,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{16}{5}",
"budget": 3704
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003643",
"normalized_example_id": "ex_003643",
"source_idx": 3643,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3704,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{25}",
"budget": 2620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003644",
"normalized_example_id": "ex_003644",
"source_idx": 3644,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4367,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{25}",
"budget": 3494
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003644",
"normalized_example_id": "ex_003644",
"source_idx": 3644,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4367,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{25}",
"budget": 4367
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003644",
"normalized_example_id": "ex_003644",
"source_idx": 3644,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4367,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\text{ and } 23",
"budget": 2701
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003645",
"normalized_example_id": "ex_003645",
"source_idx": 3645,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4502,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\text{ and } 23",
"budget": 3602
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003645",
"normalized_example_id": "ex_003645",
"source_idx": 3645,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4502,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\text{ and } 23",
"budget": 4502
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003645",
"normalized_example_id": "ex_003645",
"source_idx": 3645,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4502,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\mathrm{~}",
"budget": 1709
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003646",
"normalized_example_id": "ex_003646",
"source_idx": 3646,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2849,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\mathrm{~}",
"budget": 2279
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003646",
"normalized_example_id": "ex_003646",
"source_idx": 3646,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2849,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\mathrm{~}",
"budget": 2849
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003646",
"normalized_example_id": "ex_003646",
"source_idx": 3646,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2849,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1681
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003648",
"normalized_example_id": "ex_003648",
"source_idx": 3648,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2802,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2242
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003648",
"normalized_example_id": "ex_003648",
"source_idx": 3648,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2802,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2802
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003648",
"normalized_example_id": "ex_003648",
"source_idx": 3648,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2802,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.