prompt listlengths 2 2 | label dict | metadata dict |
|---|---|---|
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{7}",
"budget": 4497
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004921",
"normalized_example_id": "ex_004921",
"source_idx": 4921,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5621,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 5621
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004921",
"normalized_example_id": "ex_004921",
"source_idx": 4921,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5621,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10 \\sqrt{5}",
"budget": 1445
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004922",
"normalized_example_id": "ex_004922",
"source_idx": 4922,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2408,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10 \\sqrt{5}",
"budget": 1926
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004922",
"normalized_example_id": "ex_004922",
"source_idx": 4922,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2408,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10 \\sqrt{5}",
"budget": 2408
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004922",
"normalized_example_id": "ex_004922",
"source_idx": 4922,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2408,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2845
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004927",
"normalized_example_id": "ex_004927",
"source_idx": 4927,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4742,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3794
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004927",
"normalized_example_id": "ex_004927",
"source_idx": 4927,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4742,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4742
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004927",
"normalized_example_id": "ex_004927",
"source_idx": 4927,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4742,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "223",
"budget": 3656
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004932",
"normalized_example_id": "ex_004932",
"source_idx": 4932,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6093,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "223",
"budget": 4874
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004932",
"normalized_example_id": "ex_004932",
"source_idx": 4932,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6093,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "223",
"budget": 6093
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004932",
"normalized_example_id": "ex_004932",
"source_idx": 4932,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6093,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "216",
"budget": 1754
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004934",
"normalized_example_id": "ex_004934",
"source_idx": 4934,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2923,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "216",
"budget": 2338
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004934",
"normalized_example_id": "ex_004934",
"source_idx": 4934,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2923,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "216",
"budget": 2923
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004934",
"normalized_example_id": "ex_004934",
"source_idx": 4934,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2923,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha=45",
"budget": 1278
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004938",
"normalized_example_id": "ex_004938",
"source_idx": 4938,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2130,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha=45",
"budget": 1704
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004938",
"normalized_example_id": "ex_004938",
"source_idx": 4938,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2130,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha=45",
"budget": 2130
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004938",
"normalized_example_id": "ex_004938",
"source_idx": 4938,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2130,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\ln2-1",
"budget": 4495
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004939",
"normalized_example_id": "ex_004939",
"source_idx": 4939,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7492,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\ln2-1",
"budget": 5994
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004939",
"normalized_example_id": "ex_004939",
"source_idx": 4939,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7492,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\ln2-1",
"budget": 7492
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004939",
"normalized_example_id": "ex_004939",
"source_idx": 4939,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7492,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha=120",
"budget": 1765
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004940",
"normalized_example_id": "ex_004940",
"source_idx": 4940,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2941,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha=120",
"budget": 2353
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004940",
"normalized_example_id": "ex_004940",
"source_idx": 4940,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2941,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha=120",
"budget": 2941
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004940",
"normalized_example_id": "ex_004940",
"source_idx": 4940,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2941,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6!",
"budget": 1856
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004942",
"normalized_example_id": "ex_004942",
"source_idx": 4942,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3094,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6!",
"budget": 2475
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004942",
"normalized_example_id": "ex_004942",
"source_idx": 4942,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3094,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6!",
"budget": 3094
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004942",
"normalized_example_id": "ex_004942",
"source_idx": 4942,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3094,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27\\sqrt{3}",
"budget": 1648
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004947",
"normalized_example_id": "ex_004947",
"source_idx": 4947,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2746,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27\\sqrt{3}",
"budget": 2197
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004947",
"normalized_example_id": "ex_004947",
"source_idx": 4947,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2746,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27\\sqrt{3}",
"budget": 2746
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004947",
"normalized_example_id": "ex_004947",
"source_idx": 4947,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2746,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "192",
"budget": 2833
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004948",
"normalized_example_id": "ex_004948",
"source_idx": 4948,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4721,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "192",
"budget": 3777
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004948",
"normalized_example_id": "ex_004948",
"source_idx": 4948,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4721,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "192",
"budget": 4721
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004948",
"normalized_example_id": "ex_004948",
"source_idx": 4948,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4721,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 5125
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004951",
"normalized_example_id": "ex_004951",
"source_idx": 4951,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8542,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 6834
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004951",
"normalized_example_id": "ex_004951",
"source_idx": 4951,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8542,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 8542
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004951",
"normalized_example_id": "ex_004951",
"source_idx": 4951,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8542,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arccos\\frac{5}{8}",
"budget": 3190
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004954",
"normalized_example_id": "ex_004954",
"source_idx": 4954,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5316,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arccos\\frac{5}{8}",
"budget": 4253
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004954",
"normalized_example_id": "ex_004954",
"source_idx": 4954,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5316,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arccos\\frac{5}{8}",
"budget": 5316
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004954",
"normalized_example_id": "ex_004954",
"source_idx": 4954,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5316,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "29",
"budget": 1802
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004956",
"normalized_example_id": "ex_004956",
"source_idx": 4956,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "29",
"budget": 2402
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004956",
"normalized_example_id": "ex_004956",
"source_idx": 4956,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "29",
"budget": 3003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004956",
"normalized_example_id": "ex_004956",
"source_idx": 4956,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 1156
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004959",
"normalized_example_id": "ex_004959",
"source_idx": 4959,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1927,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 1542
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004959",
"normalized_example_id": "ex_004959",
"source_idx": 4959,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1927,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 1927
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004959",
"normalized_example_id": "ex_004959",
"source_idx": 4959,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1927,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2551",
"budget": 4893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004960",
"normalized_example_id": "ex_004960",
"source_idx": 4960,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8155,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2551",
"budget": 6524
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004960",
"normalized_example_id": "ex_004960",
"source_idx": 4960,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8155,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2551",
"budget": 8155
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004960",
"normalized_example_id": "ex_004960",
"source_idx": 4960,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8155,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "108",
"budget": 6045
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004961",
"normalized_example_id": "ex_004961",
"source_idx": 4961,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "108",
"budget": 8060
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004961",
"normalized_example_id": "ex_004961",
"source_idx": 4961,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "108",
"budget": 10075
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004961",
"normalized_example_id": "ex_004961",
"source_idx": 4961,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = \\lambda \\ln x",
"budget": 2644
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004963",
"normalized_example_id": "ex_004963",
"source_idx": 4963,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4407,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = \\lambda \\ln x",
"budget": 3526
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004963",
"normalized_example_id": "ex_004963",
"source_idx": 4963,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4407,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = \\lambda \\ln x",
"budget": 4407
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004963",
"normalized_example_id": "ex_004963",
"source_idx": 4963,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4407,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32.5\\leqslantp\\leqslant35",
"budget": 1507
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004965",
"normalized_example_id": "ex_004965",
"source_idx": 4965,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2511,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32.5\\leqslantp\\leqslant35",
"budget": 2009
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004965",
"normalized_example_id": "ex_004965",
"source_idx": 4965,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2511,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32.5\\leqslantp\\leqslant35",
"budget": 2511
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004965",
"normalized_example_id": "ex_004965",
"source_idx": 4965,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2511,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 2365
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004966",
"normalized_example_id": "ex_004966",
"source_idx": 4966,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3941,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 3153
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004966",
"normalized_example_id": "ex_004966",
"source_idx": 4966,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3941,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 3941
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004966",
"normalized_example_id": "ex_004966",
"source_idx": 4966,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3941,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 4411
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004967",
"normalized_example_id": "ex_004967",
"source_idx": 4967,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7351,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 5881
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004967",
"normalized_example_id": "ex_004967",
"source_idx": 4967,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7351,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 7351
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004967",
"normalized_example_id": "ex_004967",
"source_idx": 4967,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7351,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{129}",
"budget": 2189
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004969",
"normalized_example_id": "ex_004969",
"source_idx": 4969,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3648,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{129}",
"budget": 2918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004969",
"normalized_example_id": "ex_004969",
"source_idx": 4969,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3648,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{129}",
"budget": 3648
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004969",
"normalized_example_id": "ex_004969",
"source_idx": 4969,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3648,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3206
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004970",
"normalized_example_id": "ex_004970",
"source_idx": 4970,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5343,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4274
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004970",
"normalized_example_id": "ex_004970",
"source_idx": 4970,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5343,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5343
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004970",
"normalized_example_id": "ex_004970",
"source_idx": 4970,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5343,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{4}{3}",
"budget": 864
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004972",
"normalized_example_id": "ex_004972",
"source_idx": 4972,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1440,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{4}{3}",
"budget": 1152
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004972",
"normalized_example_id": "ex_004972",
"source_idx": 4972,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1440,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{4}{3}",
"budget": 1440
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004972",
"normalized_example_id": "ex_004972",
"source_idx": 4972,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1440,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6039}{8}",
"budget": 1329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004973",
"normalized_example_id": "ex_004973",
"source_idx": 4973,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2215,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6039}{8}",
"budget": 1772
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004973",
"normalized_example_id": "ex_004973",
"source_idx": 4973,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2215,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6039}{8}",
"budget": 2215
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004973",
"normalized_example_id": "ex_004973",
"source_idx": 4973,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2215,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "P(I) = \\left[ \\frac{1}{2} \\sinh\\left(\\frac{\\pi}{2}\\right), \\frac{1}{4} e^{\\frac{\\pi}{2}} \\right]",
"budget": 5248
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004975",
"normalized_example_id": "ex_004975",
"source_idx": 4975,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8747,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "P(I) = \\left[ \\frac{1}{2} \\sinh\\left(\\frac{\\pi}{2}\\right), \\frac{1}{4} e^{\\frac{\\pi}{2}} \\right]",
"budget": 6998
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004975",
"normalized_example_id": "ex_004975",
"source_idx": 4975,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8747,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "P(I) = \\left[ \\frac{1}{2} \\sinh\\left(\\frac{\\pi}{2}\\right), \\frac{1}{4} e^{\\frac{\\pi}{2}} \\right]",
"budget": 8747
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004975",
"normalized_example_id": "ex_004975",
"source_idx": 4975,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8747,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 3666
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004976",
"normalized_example_id": "ex_004976",
"source_idx": 4976,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 4888
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004976",
"normalized_example_id": "ex_004976",
"source_idx": 4976,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 6110
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004976",
"normalized_example_id": "ex_004976",
"source_idx": 4976,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "M(Z)=3,\\,D(Z)=0.52",
"budget": 1675
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004979",
"normalized_example_id": "ex_004979",
"source_idx": 4979,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2791,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "M(Z)=3,\\,D(Z)=0.52",
"budget": 2233
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004979",
"normalized_example_id": "ex_004979",
"source_idx": 4979,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2791,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "M(Z)=3,\\,D(Z)=0.52",
"budget": 2791
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004979",
"normalized_example_id": "ex_004979",
"source_idx": 4979,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2791,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "383",
"budget": 4982
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004981",
"normalized_example_id": "ex_004981",
"source_idx": 4981,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8303,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "383",
"budget": 6642
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004981",
"normalized_example_id": "ex_004981",
"source_idx": 4981,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8303,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "383",
"budget": 8303
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004981",
"normalized_example_id": "ex_004981",
"source_idx": 4981,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8303,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,13,43,91,157",
"budget": 1936
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004985",
"normalized_example_id": "ex_004985",
"source_idx": 4985,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3226,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,13,43,91,157",
"budget": 2581
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004985",
"normalized_example_id": "ex_004985",
"source_idx": 4985,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3226,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,13,43,91,157",
"budget": 3226
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004985",
"normalized_example_id": "ex_004985",
"source_idx": 4985,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3226,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "ChristineNaumann",
"budget": 6116
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004987",
"normalized_example_id": "ex_004987",
"source_idx": 4987,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10194,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "ChristineNaumann",
"budget": 8155
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004987",
"normalized_example_id": "ex_004987",
"source_idx": 4987,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10194,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "ChristineNaumann",
"budget": 10194
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004987",
"normalized_example_id": "ex_004987",
"source_idx": 4987,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10194,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;2\\sqrt{3}),(-4;0),(2;-2\\sqrt{3})",
"budget": 3889
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004989",
"normalized_example_id": "ex_004989",
"source_idx": 4989,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6481,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;2\\sqrt{3}),(-4;0),(2;-2\\sqrt{3})",
"budget": 5185
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004989",
"normalized_example_id": "ex_004989",
"source_idx": 4989,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6481,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;2\\sqrt{3}),(-4;0),(2;-2\\sqrt{3})",
"budget": 6481
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004989",
"normalized_example_id": "ex_004989",
"source_idx": 4989,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6481,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 1441
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004994",
"normalized_example_id": "ex_004994",
"source_idx": 4994,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2401,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 1921
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004994",
"normalized_example_id": "ex_004994",
"source_idx": 4994,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2401,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 2401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004994",
"normalized_example_id": "ex_004994",
"source_idx": 4994,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2401,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5989
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004996",
"normalized_example_id": "ex_004996",
"source_idx": 4996,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9982,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7986
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004996",
"normalized_example_id": "ex_004996",
"source_idx": 4996,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9982,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.