prompt listlengths 2 2 | label dict | metadata dict |
|---|---|---|
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e",
"budget": 4261
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007379",
"normalized_example_id": "ex_007379",
"source_idx": 7379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7102,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e",
"budget": 5682
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007379",
"normalized_example_id": "ex_007379",
"source_idx": 7379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7102,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e",
"budget": 7102
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007379",
"normalized_example_id": "ex_007379",
"source_idx": 7379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7102,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{2}}{6}",
"budget": 5500
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007380",
"normalized_example_id": "ex_007380",
"source_idx": 7380,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9166,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{2}}{6}",
"budget": 7333
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007380",
"normalized_example_id": "ex_007380",
"source_idx": 7380,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9166,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{2}}{6}",
"budget": 9166
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007380",
"normalized_example_id": "ex_007380",
"source_idx": 7380,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9166,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 2915
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007384",
"normalized_example_id": "ex_007384",
"source_idx": 7384,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4858,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 3886
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007384",
"normalized_example_id": "ex_007384",
"source_idx": 7384,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4858,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 4858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007384",
"normalized_example_id": "ex_007384",
"source_idx": 7384,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4858,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\leqslant b \\leqslant -1",
"budget": 1063
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007386",
"normalized_example_id": "ex_007386",
"source_idx": 7386,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1771,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\leqslant b \\leqslant -1",
"budget": 1417
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007386",
"normalized_example_id": "ex_007386",
"source_idx": 7386,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1771,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\leqslant b \\leqslant -1",
"budget": 1771
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007386",
"normalized_example_id": "ex_007386",
"source_idx": 7386,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1771,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1805
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007388",
"normalized_example_id": "ex_007388",
"source_idx": 7388,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3008,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2406
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007388",
"normalized_example_id": "ex_007388",
"source_idx": 7388,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3008,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3008
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007388",
"normalized_example_id": "ex_007388",
"source_idx": 7388,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3008,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 2192
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007390",
"normalized_example_id": "ex_007390",
"source_idx": 7390,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3654,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 2923
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007390",
"normalized_example_id": "ex_007390",
"source_idx": 7390,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3654,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 3654
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007390",
"normalized_example_id": "ex_007390",
"source_idx": 7390,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3654,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{15}{2}",
"budget": 1845
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007392",
"normalized_example_id": "ex_007392",
"source_idx": 7392,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{15}{2}",
"budget": 2460
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007392",
"normalized_example_id": "ex_007392",
"source_idx": 7392,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{15}{2}",
"budget": 3075
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007392",
"normalized_example_id": "ex_007392",
"source_idx": 7392,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38",
"budget": 665
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007393",
"normalized_example_id": "ex_007393",
"source_idx": 7393,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1109,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38",
"budget": 887
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007393",
"normalized_example_id": "ex_007393",
"source_idx": 7393,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1109,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38",
"budget": 1109
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007393",
"normalized_example_id": "ex_007393",
"source_idx": 7393,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1109,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2224
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007395",
"normalized_example_id": "ex_007395",
"source_idx": 7395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3706,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2965
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007395",
"normalized_example_id": "ex_007395",
"source_idx": 7395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3706,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3706
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007395",
"normalized_example_id": "ex_007395",
"source_idx": 7395,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3706,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2or4",
"budget": 4749
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007397",
"normalized_example_id": "ex_007397",
"source_idx": 7397,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7915,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2or4",
"budget": 6332
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007397",
"normalized_example_id": "ex_007397",
"source_idx": 7397,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7915,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2or4",
"budget": 7915
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007397",
"normalized_example_id": "ex_007397",
"source_idx": 7397,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7915,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(2 n-4)!}{(n-1)!(n-2)!}",
"budget": 1913
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007399",
"normalized_example_id": "ex_007399",
"source_idx": 7399,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3189,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(2 n-4)!}{(n-1)!(n-2)!}",
"budget": 2551
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007399",
"normalized_example_id": "ex_007399",
"source_idx": 7399,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3189,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(2 n-4)!}{(n-1)!(n-2)!}",
"budget": 3189
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007399",
"normalized_example_id": "ex_007399",
"source_idx": 7399,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3189,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "74",
"budget": 3214
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007400",
"normalized_example_id": "ex_007400",
"source_idx": 7400,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5357,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "74",
"budget": 4286
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007400",
"normalized_example_id": "ex_007400",
"source_idx": 7400,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5357,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "74",
"budget": 5357
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007400",
"normalized_example_id": "ex_007400",
"source_idx": 7400,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5357,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "420",
"budget": 3247
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007401",
"normalized_example_id": "ex_007401",
"source_idx": 7401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "420",
"budget": 4329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007401",
"normalized_example_id": "ex_007401",
"source_idx": 7401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "420",
"budget": 5411
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007401",
"normalized_example_id": "ex_007401",
"source_idx": 7401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4951",
"budget": 1255
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007405",
"normalized_example_id": "ex_007405",
"source_idx": 7405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2092,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4951",
"budget": 1674
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007405",
"normalized_example_id": "ex_007405",
"source_idx": 7405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2092,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4951",
"budget": 2092
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007405",
"normalized_example_id": "ex_007405",
"source_idx": 7405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2092,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2012^{2012}",
"budget": 2241
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007408",
"normalized_example_id": "ex_007408",
"source_idx": 7408,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3735,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2012^{2012}",
"budget": 2988
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007408",
"normalized_example_id": "ex_007408",
"source_idx": 7408,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3735,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2012^{2012}",
"budget": 3735
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007408",
"normalized_example_id": "ex_007408",
"source_idx": 7408,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3735,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 1996
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007409",
"normalized_example_id": "ex_007409",
"source_idx": 7409,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 2662
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007409",
"normalized_example_id": "ex_007409",
"source_idx": 7409,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 3327
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007409",
"normalized_example_id": "ex_007409",
"source_idx": 7409,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "143",
"budget": 4993
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007410",
"normalized_example_id": "ex_007410",
"source_idx": 7410,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8321,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "143",
"budget": 6657
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007410",
"normalized_example_id": "ex_007410",
"source_idx": 7410,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8321,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "143",
"budget": 8321
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007410",
"normalized_example_id": "ex_007410",
"source_idx": 7410,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8321,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "690",
"budget": 4102
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007411",
"normalized_example_id": "ex_007411",
"source_idx": 7411,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6837,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "690",
"budget": 5470
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007411",
"normalized_example_id": "ex_007411",
"source_idx": 7411,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6837,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "690",
"budget": 6837
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007411",
"normalized_example_id": "ex_007411",
"source_idx": 7411,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6837,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1324
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007412",
"normalized_example_id": "ex_007412",
"source_idx": 7412,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2207,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1766
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007412",
"normalized_example_id": "ex_007412",
"source_idx": 7412,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2207,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2207
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007412",
"normalized_example_id": "ex_007412",
"source_idx": 7412,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2207,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2+3\\sqrt{2}",
"budget": 3695
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007413",
"normalized_example_id": "ex_007413",
"source_idx": 7413,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2+3\\sqrt{2}",
"budget": 4927
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007413",
"normalized_example_id": "ex_007413",
"source_idx": 7413,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2+3\\sqrt{2}",
"budget": 6159
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007413",
"normalized_example_id": "ex_007413",
"source_idx": 7413,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "130",
"budget": 2856
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007414",
"normalized_example_id": "ex_007414",
"source_idx": 7414,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4760,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "130",
"budget": 3808
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007414",
"normalized_example_id": "ex_007414",
"source_idx": 7414,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4760,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "130",
"budget": 4760
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007414",
"normalized_example_id": "ex_007414",
"source_idx": 7414,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4760,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\frac{43}{57}",
"budget": 1394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007415",
"normalized_example_id": "ex_007415",
"source_idx": 7415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2323,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\frac{43}{57}",
"budget": 1858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007415",
"normalized_example_id": "ex_007415",
"source_idx": 7415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2323,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\frac{43}{57}",
"budget": 2323
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007415",
"normalized_example_id": "ex_007415",
"source_idx": 7415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2323,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "97",
"budget": 1666
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007416",
"normalized_example_id": "ex_007416",
"source_idx": 7416,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2777,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "97",
"budget": 2222
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007416",
"normalized_example_id": "ex_007416",
"source_idx": 7416,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2777,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "97",
"budget": 2777
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007416",
"normalized_example_id": "ex_007416",
"source_idx": 7416,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2777,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2022^{3}-1011^{3}",
"budget": 3173
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007419",
"normalized_example_id": "ex_007419",
"source_idx": 7419,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2022^{3}-1011^{3}",
"budget": 4230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007419",
"normalized_example_id": "ex_007419",
"source_idx": 7419,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2022^{3}-1011^{3}",
"budget": 5288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007419",
"normalized_example_id": "ex_007419",
"source_idx": 7419,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 721
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007420",
"normalized_example_id": "ex_007420",
"source_idx": 7420,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1202,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 962
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007420",
"normalized_example_id": "ex_007420",
"source_idx": 7420,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1202,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1202
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007420",
"normalized_example_id": "ex_007420",
"source_idx": 7420,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1202,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{2}",
"budget": 3685
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007421",
"normalized_example_id": "ex_007421",
"source_idx": 7421,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6142,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{2}",
"budget": 4914
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007421",
"normalized_example_id": "ex_007421",
"source_idx": 7421,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6142,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{2}",
"budget": 6142
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007421",
"normalized_example_id": "ex_007421",
"source_idx": 7421,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6142,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-58",
"budget": 1652
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007423",
"normalized_example_id": "ex_007423",
"source_idx": 7423,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2754,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-58",
"budget": 2203
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007423",
"normalized_example_id": "ex_007423",
"source_idx": 7423,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2754,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-58",
"budget": 2754
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007423",
"normalized_example_id": "ex_007423",
"source_idx": 7423,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2754,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2479
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007424",
"normalized_example_id": "ex_007424",
"source_idx": 7424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3305
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007424",
"normalized_example_id": "ex_007424",
"source_idx": 7424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4131
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007424",
"normalized_example_id": "ex_007424",
"source_idx": 7424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "303369",
"budget": 3429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007425",
"normalized_example_id": "ex_007425",
"source_idx": 7425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "303369",
"budget": 4572
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007425",
"normalized_example_id": "ex_007425",
"source_idx": 7425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "303369",
"budget": 5715
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007425",
"normalized_example_id": "ex_007425",
"source_idx": 7425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "660",
"budget": 5920
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007429",
"normalized_example_id": "ex_007429",
"source_idx": 7429,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9866,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "660",
"budget": 7893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007429",
"normalized_example_id": "ex_007429",
"source_idx": 7429,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9866,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "660",
"budget": 9866
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007429",
"normalized_example_id": "ex_007429",
"source_idx": 7429,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9866,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 3713
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007433",
"normalized_example_id": "ex_007433",
"source_idx": 7433,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6189,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 4951
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007433",
"normalized_example_id": "ex_007433",
"source_idx": 7433,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6189,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 6189
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007433",
"normalized_example_id": "ex_007433",
"source_idx": 7433,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6189,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5400",
"budget": 2927
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007435",
"normalized_example_id": "ex_007435",
"source_idx": 7435,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4879,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5400",
"budget": 3903
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007435",
"normalized_example_id": "ex_007435",
"source_idx": 7435,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4879,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5400",
"budget": 4879
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007435",
"normalized_example_id": "ex_007435",
"source_idx": 7435,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4879,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "900",
"budget": 2977
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007436",
"normalized_example_id": "ex_007436",
"source_idx": 7436,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4962,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "900",
"budget": 3970
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007436",
"normalized_example_id": "ex_007436",
"source_idx": 7436,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4962,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "900",
"budget": 4962
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007436",
"normalized_example_id": "ex_007436",
"source_idx": 7436,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4962,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "83",
"budget": 2258
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007437",
"normalized_example_id": "ex_007437",
"source_idx": 7437,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3763,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.