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": "1895",
"budget": 6620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002996",
"normalized_example_id": "ex_002996",
"source_idx": 2996,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6620,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 1673
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002997",
"normalized_example_id": "ex_002997",
"source_idx": 2997,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2789,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 2231
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002997",
"normalized_example_id": "ex_002997",
"source_idx": 2997,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2789,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 2789
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002997",
"normalized_example_id": "ex_002997",
"source_idx": 2997,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2789,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1213
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002998",
"normalized_example_id": "ex_002998",
"source_idx": 2998,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1618
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002998",
"normalized_example_id": "ex_002998",
"source_idx": 2998,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2022
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002998",
"normalized_example_id": "ex_002998",
"source_idx": 2998,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)=x",
"budget": 4940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003000",
"normalized_example_id": "ex_003000",
"source_idx": 3000,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8234,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)=x",
"budget": 6587
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003000",
"normalized_example_id": "ex_003000",
"source_idx": 3000,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8234,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)=x",
"budget": 8234
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003000",
"normalized_example_id": "ex_003000",
"source_idx": 3000,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8234,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2 \\sqrt{2}",
"budget": 3172
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003002",
"normalized_example_id": "ex_003002",
"source_idx": 3002,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5287,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2 \\sqrt{2}",
"budget": 4230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003002",
"normalized_example_id": "ex_003002",
"source_idx": 3002,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5287,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2 \\sqrt{2}",
"budget": 5287
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003002",
"normalized_example_id": "ex_003002",
"source_idx": 3002,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5287,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{9}{2}",
"budget": 4769
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003003",
"normalized_example_id": "ex_003003",
"source_idx": 3003,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7949,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{9}{2}",
"budget": 6359
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003003",
"normalized_example_id": "ex_003003",
"source_idx": 3003,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7949,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{9}{2}",
"budget": 7949
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003003",
"normalized_example_id": "ex_003003",
"source_idx": 3003,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7949,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003005",
"normalized_example_id": "ex_003005",
"source_idx": 3005,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003005",
"normalized_example_id": "ex_003005",
"source_idx": 3005,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8472
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003005",
"normalized_example_id": "ex_003005",
"source_idx": 3005,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8472,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "63",
"budget": 1565
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003006",
"normalized_example_id": "ex_003006",
"source_idx": 3006,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2608,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "63",
"budget": 2086
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003006",
"normalized_example_id": "ex_003006",
"source_idx": 3006,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2608,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "63",
"budget": 2608
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003006",
"normalized_example_id": "ex_003006",
"source_idx": 3006,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2608,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{16}",
"budget": 3488
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003011",
"normalized_example_id": "ex_003011",
"source_idx": 3011,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5814,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{16}",
"budget": 4651
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003011",
"normalized_example_id": "ex_003011",
"source_idx": 3011,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5814,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{16}",
"budget": 5814
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003011",
"normalized_example_id": "ex_003011",
"source_idx": 3011,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5814,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-3,6),(6,3)",
"budget": 1633
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003016",
"normalized_example_id": "ex_003016",
"source_idx": 3016,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2721,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-3,6),(6,3)",
"budget": 2177
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003016",
"normalized_example_id": "ex_003016",
"source_idx": 3016,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2721,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-3,6),(6,3)",
"budget": 2721
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003016",
"normalized_example_id": "ex_003016",
"source_idx": 3016,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2721,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17",
"budget": 2528
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003018",
"normalized_example_id": "ex_003018",
"source_idx": 3018,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4213,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17",
"budget": 3370
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003018",
"normalized_example_id": "ex_003018",
"source_idx": 3018,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4213,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "17",
"budget": 4213
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003018",
"normalized_example_id": "ex_003018",
"source_idx": 3018,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4213,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "337",
"budget": 1299
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003024",
"normalized_example_id": "ex_003024",
"source_idx": 3024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2165,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "337",
"budget": 1732
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003024",
"normalized_example_id": "ex_003024",
"source_idx": 3024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2165,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "337",
"budget": 2165
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003024",
"normalized_example_id": "ex_003024",
"source_idx": 3024,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2165,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003028",
"normalized_example_id": "ex_003028",
"source_idx": 3028,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4923,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3938
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003028",
"normalized_example_id": "ex_003028",
"source_idx": 3028,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4923,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4923
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003028",
"normalized_example_id": "ex_003028",
"source_idx": 3028,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4923,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\varphi(x)=2x^{2}",
"budget": 4446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003029",
"normalized_example_id": "ex_003029",
"source_idx": 3029,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7410,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\varphi(x)=2x^{2}",
"budget": 5928
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003029",
"normalized_example_id": "ex_003029",
"source_idx": 3029,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7410,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\varphi(x)=2x^{2}",
"budget": 7410
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003029",
"normalized_example_id": "ex_003029",
"source_idx": 3029,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7410,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2n-2",
"budget": 2602
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003030",
"normalized_example_id": "ex_003030",
"source_idx": 3030,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2n-2",
"budget": 3470
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003030",
"normalized_example_id": "ex_003030",
"source_idx": 3030,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2n-2",
"budget": 4337
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003030",
"normalized_example_id": "ex_003030",
"source_idx": 3030,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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), (6, 2)\\}",
"budget": 3880
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003031",
"normalized_example_id": "ex_003031",
"source_idx": 3031,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6466,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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), (6, 2)\\}",
"budget": 5173
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003031",
"normalized_example_id": "ex_003031",
"source_idx": 3031,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6466,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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), (6, 2)\\}",
"budget": 6466
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003031",
"normalized_example_id": "ex_003031",
"source_idx": 3031,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6466,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 2251
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003034",
"normalized_example_id": "ex_003034",
"source_idx": 3034,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3751,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 3001
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003034",
"normalized_example_id": "ex_003034",
"source_idx": 3034,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3751,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 3751
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003034",
"normalized_example_id": "ex_003034",
"source_idx": 3034,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3751,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\sqrt{5}}{2}",
"budget": 2723
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003036",
"normalized_example_id": "ex_003036",
"source_idx": 3036,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4539,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\sqrt{5}}{2}",
"budget": 3631
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003036",
"normalized_example_id": "ex_003036",
"source_idx": 3036,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4539,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\sqrt{5}}{2}",
"budget": 4539
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003036",
"normalized_example_id": "ex_003036",
"source_idx": 3036,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4539,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y)\\in{(0,0),(1,1)}",
"budget": 1381
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003038",
"normalized_example_id": "ex_003038",
"source_idx": 3038,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2302,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y)\\in{(0,0),(1,1)}",
"budget": 1842
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003038",
"normalized_example_id": "ex_003038",
"source_idx": 3038,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2302,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y)\\in{(0,0),(1,1)}",
"budget": 2302
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003038",
"normalized_example_id": "ex_003038",
"source_idx": 3038,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2302,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4886
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003039",
"normalized_example_id": "ex_003039",
"source_idx": 3039,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8144,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6515
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003039",
"normalized_example_id": "ex_003039",
"source_idx": 3039,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8144,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8144
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003039",
"normalized_example_id": "ex_003039",
"source_idx": 3039,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8144,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "82369",
"budget": 3464
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003043",
"normalized_example_id": "ex_003043",
"source_idx": 3043,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5774,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "82369",
"budget": 4619
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003043",
"normalized_example_id": "ex_003043",
"source_idx": 3043,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5774,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "82369",
"budget": 5774
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003043",
"normalized_example_id": "ex_003043",
"source_idx": 3043,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5774,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 2, 2)",
"budget": 2174
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003044",
"normalized_example_id": "ex_003044",
"source_idx": 3044,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 2, 2)",
"budget": 2898
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003044",
"normalized_example_id": "ex_003044",
"source_idx": 3044,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 2, 2)",
"budget": 3623
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003044",
"normalized_example_id": "ex_003044",
"source_idx": 3044,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}:2",
"budget": 3476
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003047",
"normalized_example_id": "ex_003047",
"source_idx": 3047,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5793,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}:2",
"budget": 4634
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003047",
"normalized_example_id": "ex_003047",
"source_idx": 3047,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5793,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}:2",
"budget": 5793
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003047",
"normalized_example_id": "ex_003047",
"source_idx": 3047,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5793,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 5768
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003048",
"normalized_example_id": "ex_003048",
"source_idx": 3048,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 7691
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003048",
"normalized_example_id": "ex_003048",
"source_idx": 3048,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 9614
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003048",
"normalized_example_id": "ex_003048",
"source_idx": 3048,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70",
"budget": 1106
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003049",
"normalized_example_id": "ex_003049",
"source_idx": 3049,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1843,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70",
"budget": 1474
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003049",
"normalized_example_id": "ex_003049",
"source_idx": 3049,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1843,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70",
"budget": 1843
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003049",
"normalized_example_id": "ex_003049",
"source_idx": 3049,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1843,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{5}",
"budget": 2171
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003051",
"normalized_example_id": "ex_003051",
"source_idx": 3051,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3619,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{5}",
"budget": 2895
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003051",
"normalized_example_id": "ex_003051",
"source_idx": 3051,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3619,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{5}",
"budget": 3619
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003051",
"normalized_example_id": "ex_003051",
"source_idx": 3051,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3619,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n}=\\frac{1}{n+1}\\mathrm{C}_{2n}^{n}",
"budget": 1369
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003052",
"normalized_example_id": "ex_003052",
"source_idx": 3052,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2281,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n}=\\frac{1}{n+1}\\mathrm{C}_{2n}^{n}",
"budget": 1825
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003052",
"normalized_example_id": "ex_003052",
"source_idx": 3052,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2281,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n}=\\frac{1}{n+1}\\mathrm{C}_{2n}^{n}",
"budget": 2281
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003052",
"normalized_example_id": "ex_003052",
"source_idx": 3052,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2281,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "k",
"budget": 889
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003053",
"normalized_example_id": "ex_003053",
"source_idx": 3053,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1482,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "k",
"budget": 1186
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003053",
"normalized_example_id": "ex_003053",
"source_idx": 3053,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1482,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "k",
"budget": 1482
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003053",
"normalized_example_id": "ex_003053",
"source_idx": 3053,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1482,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(8,2),(\\frac{1}{4},64)",
"budget": 2036
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003055",
"normalized_example_id": "ex_003055",
"source_idx": 3055,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3393,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(8,2),(\\frac{1}{4},64)",
"budget": 2714
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003055",
"normalized_example_id": "ex_003055",
"source_idx": 3055,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3393,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(8,2),(\\frac{1}{4},64)",
"budget": 3393
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003055",
"normalized_example_id": "ex_003055",
"source_idx": 3055,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3393,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 3640
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003058",
"normalized_example_id": "ex_003058",
"source_idx": 3058,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6067,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 4854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003058",
"normalized_example_id": "ex_003058",
"source_idx": 3058,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6067,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 6067
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003058",
"normalized_example_id": "ex_003058",
"source_idx": 3058,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6067,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3\\times2^{2015}-6",
"budget": 3761
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003062",
"normalized_example_id": "ex_003062",
"source_idx": 3062,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6268,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3\\times2^{2015}-6",
"budget": 5014
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003062",
"normalized_example_id": "ex_003062",
"source_idx": 3062,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6268,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3\\times2^{2015}-6",
"budget": 6268
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003062",
"normalized_example_id": "ex_003062",
"source_idx": 3062,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6268,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "760",
"budget": 1989
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003063",
"normalized_example_id": "ex_003063",
"source_idx": 3063,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3315,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "760",
"budget": 2652
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003063",
"normalized_example_id": "ex_003063",
"source_idx": 3063,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3315,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "760",
"budget": 3315
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003063",
"normalized_example_id": "ex_003063",
"source_idx": 3063,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3315,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)=x+1",
"budget": 3836
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003065",
"normalized_example_id": "ex_003065",
"source_idx": 3065,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)=x+1",
"budget": 5115
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003065",
"normalized_example_id": "ex_003065",
"source_idx": 3065,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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)=x+1",
"budget": 6394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003065",
"normalized_example_id": "ex_003065",
"source_idx": 3065,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 1457
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003070",
"normalized_example_id": "ex_003070",
"source_idx": 3070,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 1943
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003070",
"normalized_example_id": "ex_003070",
"source_idx": 3070,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2429,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 2429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003070",
"normalized_example_id": "ex_003070",
"source_idx": 3070,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2429,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.