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": "e",
"budget": 2850
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002702",
"normalized_example_id": "ex_002702",
"source_idx": 2702,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3562,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e",
"budget": 3562
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002702",
"normalized_example_id": "ex_002702",
"source_idx": 2702,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3562,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "331",
"budget": 3380
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002703",
"normalized_example_id": "ex_002703",
"source_idx": 2703,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5633,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "331",
"budget": 4506
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002703",
"normalized_example_id": "ex_002703",
"source_idx": 2703,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5633,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "331",
"budget": 5633
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002703",
"normalized_example_id": "ex_002703",
"source_idx": 2703,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5633,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 650
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002711",
"normalized_example_id": "ex_002711",
"source_idx": 2711,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 866
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002711",
"normalized_example_id": "ex_002711",
"source_idx": 2711,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 1083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002711",
"normalized_example_id": "ex_002711",
"source_idx": 2711,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[-\\frac{5\\pi}{2};\\frac{3\\pi}{2}]",
"budget": 3301
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002713",
"normalized_example_id": "ex_002713",
"source_idx": 2713,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5502,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[-\\frac{5\\pi}{2};\\frac{3\\pi}{2}]",
"budget": 4402
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002713",
"normalized_example_id": "ex_002713",
"source_idx": 2713,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5502,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[-\\frac{5\\pi}{2};\\frac{3\\pi}{2}]",
"budget": 5502
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002713",
"normalized_example_id": "ex_002713",
"source_idx": 2713,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5502,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}",
"budget": 2147
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002714",
"normalized_example_id": "ex_002714",
"source_idx": 2714,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3578,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}",
"budget": 2862
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002714",
"normalized_example_id": "ex_002714",
"source_idx": 2714,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3578,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}",
"budget": 3578
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002714",
"normalized_example_id": "ex_002714",
"source_idx": 2714,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3578,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}",
"budget": 5320
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002716",
"normalized_example_id": "ex_002716",
"source_idx": 2716,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8866,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}",
"budget": 7093
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002716",
"normalized_example_id": "ex_002716",
"source_idx": 2716,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8866,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}",
"budget": 8866
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002716",
"normalized_example_id": "ex_002716",
"source_idx": 2716,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8866,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "249",
"budget": 1267
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002717",
"normalized_example_id": "ex_002717",
"source_idx": 2717,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2112,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "249",
"budget": 1690
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002717",
"normalized_example_id": "ex_002717",
"source_idx": 2717,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2112,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "249",
"budget": 2112
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002717",
"normalized_example_id": "ex_002717",
"source_idx": 2717,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2112,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x^{4}+x^{3}+x^{2}+x+1",
"budget": 1186
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002719",
"normalized_example_id": "ex_002719",
"source_idx": 2719,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1976,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x^{4}+x^{3}+x^{2}+x+1",
"budget": 1581
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002719",
"normalized_example_id": "ex_002719",
"source_idx": 2719,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1976,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x^{4}+x^{3}+x^{2}+x+1",
"budget": 1976
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002719",
"normalized_example_id": "ex_002719",
"source_idx": 2719,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1976,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{27}-2^{11}",
"budget": 4586
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002722",
"normalized_example_id": "ex_002722",
"source_idx": 2722,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7643,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{27}-2^{11}",
"budget": 6114
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002722",
"normalized_example_id": "ex_002722",
"source_idx": 2722,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7643,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{27}-2^{11}",
"budget": 7643
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002722",
"normalized_example_id": "ex_002722",
"source_idx": 2722,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7643,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 1312
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002723",
"normalized_example_id": "ex_002723",
"source_idx": 2723,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2187,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 1750
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002723",
"normalized_example_id": "ex_002723",
"source_idx": 2723,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2187,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 2187
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002723",
"normalized_example_id": "ex_002723",
"source_idx": 2723,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2187,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2372
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002725",
"normalized_example_id": "ex_002725",
"source_idx": 2725,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3954,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3163
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002725",
"normalized_example_id": "ex_002725",
"source_idx": 2725,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3954,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002725",
"normalized_example_id": "ex_002725",
"source_idx": 2725,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3954,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{7}{15};\\frac{4}{5}",
"budget": 973
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002726",
"normalized_example_id": "ex_002726",
"source_idx": 2726,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1622,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{7}{15};\\frac{4}{5}",
"budget": 1298
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002726",
"normalized_example_id": "ex_002726",
"source_idx": 2726,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1622,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{7}{15};\\frac{4}{5}",
"budget": 1622
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002726",
"normalized_example_id": "ex_002726",
"source_idx": 2726,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1622,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "512",
"budget": 3907
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002729",
"normalized_example_id": "ex_002729",
"source_idx": 2729,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6511,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "512",
"budget": 5209
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002729",
"normalized_example_id": "ex_002729",
"source_idx": 2729,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6511,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "512",
"budget": 6511
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002729",
"normalized_example_id": "ex_002729",
"source_idx": 2729,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6511,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x=-\\frac{13}{4}",
"budget": 2455
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002730",
"normalized_example_id": "ex_002730",
"source_idx": 2730,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4092,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x=-\\frac{13}{4}",
"budget": 3274
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002730",
"normalized_example_id": "ex_002730",
"source_idx": 2730,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4092,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x=-\\frac{13}{4}",
"budget": 4092
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002730",
"normalized_example_id": "ex_002730",
"source_idx": 2730,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4092,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5866
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002731",
"normalized_example_id": "ex_002731",
"source_idx": 2731,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9776,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002731",
"normalized_example_id": "ex_002731",
"source_idx": 2731,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9776,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 9776
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002731",
"normalized_example_id": "ex_002731",
"source_idx": 2731,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9776,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "571",
"budget": 3367
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002732",
"normalized_example_id": "ex_002732",
"source_idx": 2732,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5612,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "571",
"budget": 4490
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002732",
"normalized_example_id": "ex_002732",
"source_idx": 2732,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5612,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "571",
"budget": 5612
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002732",
"normalized_example_id": "ex_002732",
"source_idx": 2732,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5612,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3}{2}",
"budget": 920
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002738",
"normalized_example_id": "ex_002738",
"source_idx": 2738,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1534,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3}{2}",
"budget": 1227
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002738",
"normalized_example_id": "ex_002738",
"source_idx": 2738,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1534,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{3}{2}",
"budget": 1534
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002738",
"normalized_example_id": "ex_002738",
"source_idx": 2738,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1534,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{24}{5}",
"budget": 3392
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002739",
"normalized_example_id": "ex_002739",
"source_idx": 2739,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5654,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{24}{5}",
"budget": 4523
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002739",
"normalized_example_id": "ex_002739",
"source_idx": 2739,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5654,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{24}{5}",
"budget": 5654
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002739",
"normalized_example_id": "ex_002739",
"source_idx": 2739,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5654,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{27}-2^{11}",
"budget": 2203
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002744",
"normalized_example_id": "ex_002744",
"source_idx": 2744,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3672,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{27}-2^{11}",
"budget": 2938
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002744",
"normalized_example_id": "ex_002744",
"source_idx": 2744,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3672,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{27}-2^{11}",
"budget": 3672
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002744",
"normalized_example_id": "ex_002744",
"source_idx": 2744,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3672,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "91,100,109,118,127,136,145",
"budget": 3269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002745",
"normalized_example_id": "ex_002745",
"source_idx": 2745,
"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": "91,100,109,118,127,136,145",
"budget": 4358
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002745",
"normalized_example_id": "ex_002745",
"source_idx": 2745,
"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": "91,100,109,118,127,136,145",
"budget": 5448
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002745",
"normalized_example_id": "ex_002745",
"source_idx": 2745,
"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": "EH:HG=2:3",
"budget": 1872
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002747",
"normalized_example_id": "ex_002747",
"source_idx": 2747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3120,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "EH:HG=2:3",
"budget": 2496
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002747",
"normalized_example_id": "ex_002747",
"source_idx": 2747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3120,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "EH:HG=2:3",
"budget": 3120
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002747",
"normalized_example_id": "ex_002747",
"source_idx": 2747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3120,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "900,1800",
"budget": 4688
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002751",
"normalized_example_id": "ex_002751",
"source_idx": 2751,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7814,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "900,1800",
"budget": 6251
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002751",
"normalized_example_id": "ex_002751",
"source_idx": 2751,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7814,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "900,1800",
"budget": 7814
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002751",
"normalized_example_id": "ex_002751",
"source_idx": 2751,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7814,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "b\\geqslant1",
"budget": 4509
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002752",
"normalized_example_id": "ex_002752",
"source_idx": 2752,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7515,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "b\\geqslant1",
"budget": 6012
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002752",
"normalized_example_id": "ex_002752",
"source_idx": 2752,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7515,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "b\\geqslant1",
"budget": 7515
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002752",
"normalized_example_id": "ex_002752",
"source_idx": 2752,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7515,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "360000",
"budget": 2389
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002754",
"normalized_example_id": "ex_002754",
"source_idx": 2754,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3981,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "360000",
"budget": 3185
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002754",
"normalized_example_id": "ex_002754",
"source_idx": 2754,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3981,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "360000",
"budget": 3981
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002754",
"normalized_example_id": "ex_002754",
"source_idx": 2754,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3981,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}",
"budget": 4226
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002756",
"normalized_example_id": "ex_002756",
"source_idx": 2756,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7044,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}",
"budget": 5635
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002756",
"normalized_example_id": "ex_002756",
"source_idx": 2756,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7044,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}",
"budget": 7044
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002756",
"normalized_example_id": "ex_002756",
"source_idx": 2756,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7044,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5439
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002758",
"normalized_example_id": "ex_002758",
"source_idx": 2758,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9065,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7252
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002758",
"normalized_example_id": "ex_002758",
"source_idx": 2758,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9065,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 9065
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002758",
"normalized_example_id": "ex_002758",
"source_idx": 2758,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9065,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2}",
"budget": 1394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002760",
"normalized_example_id": "ex_002760",
"source_idx": 2760,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2324,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2}",
"budget": 1859
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002760",
"normalized_example_id": "ex_002760",
"source_idx": 2760,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2324,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2}",
"budget": 2324
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002760",
"normalized_example_id": "ex_002760",
"source_idx": 2760,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2324,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23",
"budget": 2952
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002763",
"normalized_example_id": "ex_002763",
"source_idx": 2763,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4920,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23",
"budget": 3936
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002763",
"normalized_example_id": "ex_002763",
"source_idx": 2763,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4920,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23",
"budget": 4920
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002763",
"normalized_example_id": "ex_002763",
"source_idx": 2763,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4920,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=5",
"budget": 2421
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002764",
"normalized_example_id": "ex_002764",
"source_idx": 2764,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4035,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=5",
"budget": 3228
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002764",
"normalized_example_id": "ex_002764",
"source_idx": 2764,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4035,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=5",
"budget": 4035
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002764",
"normalized_example_id": "ex_002764",
"source_idx": 2764,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4035,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "330",
"budget": 1202
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002766",
"normalized_example_id": "ex_002766",
"source_idx": 2766,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "330",
"budget": 1602
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002766",
"normalized_example_id": "ex_002766",
"source_idx": 2766,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "330",
"budget": 2003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002766",
"normalized_example_id": "ex_002766",
"source_idx": 2766,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x=\\frac{5}{2}, y=\\frac{5}{6}",
"budget": 3691
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002768",
"normalized_example_id": "ex_002768",
"source_idx": 2768,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6151,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x=\\frac{5}{2}, y=\\frac{5}{6}",
"budget": 4921
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002768",
"normalized_example_id": "ex_002768",
"source_idx": 2768,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6151,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x=\\frac{5}{2}, y=\\frac{5}{6}",
"budget": 6151
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002768",
"normalized_example_id": "ex_002768",
"source_idx": 2768,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6151,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11}",
"budget": 2549
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002769",
"normalized_example_id": "ex_002769",
"source_idx": 2769,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4249,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11}",
"budget": 3399
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002769",
"normalized_example_id": "ex_002769",
"source_idx": 2769,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4249,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11}",
"budget": 4249
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002769",
"normalized_example_id": "ex_002769",
"source_idx": 2769,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4249,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "37",
"budget": 4163
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002772",
"normalized_example_id": "ex_002772",
"source_idx": 2772,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6939,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "37",
"budget": 5551
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002772",
"normalized_example_id": "ex_002772",
"source_idx": 2772,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6939,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "37",
"budget": 6939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002772",
"normalized_example_id": "ex_002772",
"source_idx": 2772,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6939,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, -1, 0, 1, 2",
"budget": 2441
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002773",
"normalized_example_id": "ex_002773",
"source_idx": 2773,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4068,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, -1, 0, 1, 2",
"budget": 3254
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002773",
"normalized_example_id": "ex_002773",
"source_idx": 2773,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4068,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.