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": "7",
"budget": 9982
} | {
"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": "\\frac{m}{n}",
"budget": 3349
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005000",
"normalized_example_id": "ex_005000",
"source_idx": 5000,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5581,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{m}{n}",
"budget": 4465
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005000",
"normalized_example_id": "ex_005000",
"source_idx": 5000,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5581,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{m}{n}",
"budget": 5581
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005000",
"normalized_example_id": "ex_005000",
"source_idx": 5000,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5581,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+2(n+1)n",
"budget": 4562
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005001",
"normalized_example_id": "ex_005001",
"source_idx": 5001,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7603,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+2(n+1)n",
"budget": 6082
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005001",
"normalized_example_id": "ex_005001",
"source_idx": 5001,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7603,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+2(n+1)n",
"budget": 7603
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005001",
"normalized_example_id": "ex_005001",
"source_idx": 5001,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7603,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{135}{49}\\sqrt{3}",
"budget": 3576
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005002",
"normalized_example_id": "ex_005002",
"source_idx": 5002,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5960,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{135}{49}\\sqrt{3}",
"budget": 4768
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005002",
"normalized_example_id": "ex_005002",
"source_idx": 5002,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5960,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{135}{49}\\sqrt{3}",
"budget": 5960
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005002",
"normalized_example_id": "ex_005002",
"source_idx": 5002,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5960,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 4736
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005003",
"normalized_example_id": "ex_005003",
"source_idx": 5003,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 6314
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005003",
"normalized_example_id": "ex_005003",
"source_idx": 5003,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 7893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005003",
"normalized_example_id": "ex_005003",
"source_idx": 5003,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7893,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4.86\\mathrm{~}^{2}",
"budget": 1357
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005006",
"normalized_example_id": "ex_005006",
"source_idx": 5006,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2262,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4.86\\mathrm{~}^{2}",
"budget": 1810
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005006",
"normalized_example_id": "ex_005006",
"source_idx": 5006,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2262,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4.86\\mathrm{~}^{2}",
"budget": 2262
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005006",
"normalized_example_id": "ex_005006",
"source_idx": 5006,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2262,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(m+n+1)!}{(m+1) \\cdot n!}",
"budget": 4323
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005007",
"normalized_example_id": "ex_005007",
"source_idx": 5007,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7205,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(m+n+1)!}{(m+1) \\cdot n!}",
"budget": 5764
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005007",
"normalized_example_id": "ex_005007",
"source_idx": 5007,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7205,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(m+n+1)!}{(m+1) \\cdot n!}",
"budget": 7205
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005007",
"normalized_example_id": "ex_005007",
"source_idx": 5007,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7205,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14",
"budget": 3580
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005008",
"normalized_example_id": "ex_005008",
"source_idx": 5008,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5967,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14",
"budget": 4774
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005008",
"normalized_example_id": "ex_005008",
"source_idx": 5008,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5967,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14",
"budget": 5967
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005008",
"normalized_example_id": "ex_005008",
"source_idx": 5008,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5967,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2816
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005013",
"normalized_example_id": "ex_005013",
"source_idx": 5013,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4693,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3754
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005013",
"normalized_example_id": "ex_005013",
"source_idx": 5013,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4693,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4693
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005013",
"normalized_example_id": "ex_005013",
"source_idx": 5013,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4693,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1006",
"budget": 3995
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005016",
"normalized_example_id": "ex_005016",
"source_idx": 5016,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6658,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1006",
"budget": 5326
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005016",
"normalized_example_id": "ex_005016",
"source_idx": 5016,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6658,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1006",
"budget": 6658
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005016",
"normalized_example_id": "ex_005016",
"source_idx": 5016,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6658,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1",
"budget": 1047
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005018",
"normalized_example_id": "ex_005018",
"source_idx": 5018,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1745,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1",
"budget": 1396
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005018",
"normalized_example_id": "ex_005018",
"source_idx": 5018,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1745,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1",
"budget": 1745
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005018",
"normalized_example_id": "ex_005018",
"source_idx": 5018,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1745,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4807
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005020",
"normalized_example_id": "ex_005020",
"source_idx": 5020,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8011,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 6409
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005020",
"normalized_example_id": "ex_005020",
"source_idx": 5020,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8011,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 8011
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005020",
"normalized_example_id": "ex_005020",
"source_idx": 5020,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8011,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 5141
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005024",
"normalized_example_id": "ex_005024",
"source_idx": 5024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8568,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 6854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005024",
"normalized_example_id": "ex_005024",
"source_idx": 5024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8568,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 8568
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005024",
"normalized_example_id": "ex_005024",
"source_idx": 5024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8568,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{256}{17}",
"budget": 4561
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005027",
"normalized_example_id": "ex_005027",
"source_idx": 5027,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7601,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{256}{17}",
"budget": 6081
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005027",
"normalized_example_id": "ex_005027",
"source_idx": 5027,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7601,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{256}{17}",
"budget": 7601
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005027",
"normalized_example_id": "ex_005027",
"source_idx": 5027,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7601,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{1+9x^{2}}",
"budget": 3329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005028",
"normalized_example_id": "ex_005028",
"source_idx": 5028,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5549,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{1+9x^{2}}",
"budget": 4439
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005028",
"normalized_example_id": "ex_005028",
"source_idx": 5028,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5549,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{1+9x^{2}}",
"budget": 5549
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005028",
"normalized_example_id": "ex_005028",
"source_idx": 5028,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5549,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1359
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005035",
"normalized_example_id": "ex_005035",
"source_idx": 5035,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2265,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1812
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005035",
"normalized_example_id": "ex_005035",
"source_idx": 5035,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2265,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2265
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005035",
"normalized_example_id": "ex_005035",
"source_idx": 5035,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2265,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "584",
"budget": 3195
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005040",
"normalized_example_id": "ex_005040",
"source_idx": 5040,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5325,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "584",
"budget": 4260
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005040",
"normalized_example_id": "ex_005040",
"source_idx": 5040,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5325,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "584",
"budget": 5325
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005040",
"normalized_example_id": "ex_005040",
"source_idx": 5040,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5325,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1742",
"budget": 5311
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005041",
"normalized_example_id": "ex_005041",
"source_idx": 5041,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8852,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1742",
"budget": 7082
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005041",
"normalized_example_id": "ex_005041",
"source_idx": 5041,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8852,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1742",
"budget": 8852
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005041",
"normalized_example_id": "ex_005041",
"source_idx": 5041,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8852,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{12}",
"budget": 3891
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005045",
"normalized_example_id": "ex_005045",
"source_idx": 5045,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6485,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{12}",
"budget": 5188
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005045",
"normalized_example_id": "ex_005045",
"source_idx": 5045,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6485,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{12}",
"budget": 6485
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005045",
"normalized_example_id": "ex_005045",
"source_idx": 5045,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6485,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3322
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005046",
"normalized_example_id": "ex_005046",
"source_idx": 5046,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5536,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005046",
"normalized_example_id": "ex_005046",
"source_idx": 5046,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5536,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5536
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005046",
"normalized_example_id": "ex_005046",
"source_idx": 5046,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5536,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3255
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005047",
"normalized_example_id": "ex_005047",
"source_idx": 5047,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4340
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005047",
"normalized_example_id": "ex_005047",
"source_idx": 5047,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5425
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005047",
"normalized_example_id": "ex_005047",
"source_idx": 5047,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14.4",
"budget": 1049
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005049",
"normalized_example_id": "ex_005049",
"source_idx": 5049,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1749,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14.4",
"budget": 1399
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005049",
"normalized_example_id": "ex_005049",
"source_idx": 5049,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1749,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14.4",
"budget": 1749
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005049",
"normalized_example_id": "ex_005049",
"source_idx": 5049,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1749,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "324",
"budget": 3860
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005050",
"normalized_example_id": "ex_005050",
"source_idx": 5050,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6433,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "324",
"budget": 5146
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005050",
"normalized_example_id": "ex_005050",
"source_idx": 5050,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6433,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "324",
"budget": 6433
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005050",
"normalized_example_id": "ex_005050",
"source_idx": 5050,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6433,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "r_{2}=2r_{1}",
"budget": 620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005052",
"normalized_example_id": "ex_005052",
"source_idx": 5052,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "r_{2}=2r_{1}",
"budget": 827
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005052",
"normalized_example_id": "ex_005052",
"source_idx": 5052,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "r_{2}=2r_{1}",
"budget": 1034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005052",
"normalized_example_id": "ex_005052",
"source_idx": 5052,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1034,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=52-8 \\sqrt{39}",
"budget": 2555
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005057",
"normalized_example_id": "ex_005057",
"source_idx": 5057,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4259,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=52-8 \\sqrt{39}",
"budget": 3407
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005057",
"normalized_example_id": "ex_005057",
"source_idx": 5057,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4259,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=52-8 \\sqrt{39}",
"budget": 4259
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005057",
"normalized_example_id": "ex_005057",
"source_idx": 5057,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4259,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50",
"budget": 5939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005058",
"normalized_example_id": "ex_005058",
"source_idx": 5058,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9898,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50",
"budget": 7918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005058",
"normalized_example_id": "ex_005058",
"source_idx": 5058,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9898,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50",
"budget": 9898
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005058",
"normalized_example_id": "ex_005058",
"source_idx": 5058,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9898,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\piR^{3}\\sqrt{15}}{3}",
"budget": 678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005063",
"normalized_example_id": "ex_005063",
"source_idx": 5063,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1130,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\piR^{3}\\sqrt{15}}{3}",
"budget": 904
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005063",
"normalized_example_id": "ex_005063",
"source_idx": 5063,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1130,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\piR^{3}\\sqrt{15}}{3}",
"budget": 1130
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005063",
"normalized_example_id": "ex_005063",
"source_idx": 5063,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1130,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "196",
"budget": 3853
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005064",
"normalized_example_id": "ex_005064",
"source_idx": 5064,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6422,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "196",
"budget": 5138
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005064",
"normalized_example_id": "ex_005064",
"source_idx": 5064,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6422,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "196",
"budget": 6422
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005064",
"normalized_example_id": "ex_005064",
"source_idx": 5064,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6422,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-\\infty,-1]\\cup{1}",
"budget": 2694
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005067",
"normalized_example_id": "ex_005067",
"source_idx": 5067,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4490,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-\\infty,-1]\\cup{1}",
"budget": 3592
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005067",
"normalized_example_id": "ex_005067",
"source_idx": 5067,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4490,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-\\infty,-1]\\cup{1}",
"budget": 4490
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005067",
"normalized_example_id": "ex_005067",
"source_idx": 5067,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4490,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2004",
"budget": 4891
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005068",
"normalized_example_id": "ex_005068",
"source_idx": 5068,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8151,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2004",
"budget": 6521
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005068",
"normalized_example_id": "ex_005068",
"source_idx": 5068,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8151,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2004",
"budget": 8151
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005068",
"normalized_example_id": "ex_005068",
"source_idx": 5068,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8151,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{p^2}{2}",
"budget": 2339
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005069",
"normalized_example_id": "ex_005069",
"source_idx": 5069,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3899,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{p^2}{2}",
"budget": 3119
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005069",
"normalized_example_id": "ex_005069",
"source_idx": 5069,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3899,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{p^2}{2}",
"budget": 3899
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005069",
"normalized_example_id": "ex_005069",
"source_idx": 5069,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3899,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "320",
"budget": 767
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005070",
"normalized_example_id": "ex_005070",
"source_idx": 5070,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1279,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "320",
"budget": 1023
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005070",
"normalized_example_id": "ex_005070",
"source_idx": 5070,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1279,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "320",
"budget": 1279
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005070",
"normalized_example_id": "ex_005070",
"source_idx": 5070,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1279,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1276
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005071",
"normalized_example_id": "ex_005071",
"source_idx": 5071,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2127,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1702
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005071",
"normalized_example_id": "ex_005071",
"source_idx": 5071,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2127,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2127
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005071",
"normalized_example_id": "ex_005071",
"source_idx": 5071,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2127,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.8",
"budget": 2827
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005072",
"normalized_example_id": "ex_005072",
"source_idx": 5072,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4711,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.8",
"budget": 3769
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005072",
"normalized_example_id": "ex_005072",
"source_idx": 5072,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4711,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1.8",
"budget": 4711
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005072",
"normalized_example_id": "ex_005072",
"source_idx": 5072,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4711,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.