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": "(0, k^2 + u)",
"budget": 8569
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002370",
"normalized_example_id": "ex_002370",
"source_idx": 2370,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8569,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(4,9),(10,33)",
"budget": 3133
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002372",
"normalized_example_id": "ex_002372",
"source_idx": 2372,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5222,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(4,9),(10,33)",
"budget": 4178
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002372",
"normalized_example_id": "ex_002372",
"source_idx": 2372,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5222,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(4,9),(10,33)",
"budget": 5222
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002372",
"normalized_example_id": "ex_002372",
"source_idx": 2372,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5222,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+2",
"budget": 3991
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002374",
"normalized_example_id": "ex_002374",
"source_idx": 2374,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6652,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+2",
"budget": 5322
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002374",
"normalized_example_id": "ex_002374",
"source_idx": 2374,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6652,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+2",
"budget": 6652
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002374",
"normalized_example_id": "ex_002374",
"source_idx": 2374,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6652,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3176
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002377",
"normalized_example_id": "ex_002377",
"source_idx": 2377,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5294,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4235
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002377",
"normalized_example_id": "ex_002377",
"source_idx": 2377,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5294,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5294
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002377",
"normalized_example_id": "ex_002377",
"source_idx": 2377,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5294,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1225",
"budget": 4276
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002379",
"normalized_example_id": "ex_002379",
"source_idx": 2379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7127,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1225",
"budget": 5702
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002379",
"normalized_example_id": "ex_002379",
"source_idx": 2379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7127,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1225",
"budget": 7127
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002379",
"normalized_example_id": "ex_002379",
"source_idx": 2379,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7127,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(m, n) = (11, 1), (12, 2), (15, 5), (20, 10)",
"budget": 1390
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002382",
"normalized_example_id": "ex_002382",
"source_idx": 2382,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(m, n) = (11, 1), (12, 2), (15, 5), (20, 10)",
"budget": 1854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002382",
"normalized_example_id": "ex_002382",
"source_idx": 2382,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(m, n) = (11, 1), (12, 2), (15, 5), (20, 10)",
"budget": 2317
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002382",
"normalized_example_id": "ex_002382",
"source_idx": 2382,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "540",
"budget": 2807
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002384",
"normalized_example_id": "ex_002384",
"source_idx": 2384,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "540",
"budget": 3742
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002384",
"normalized_example_id": "ex_002384",
"source_idx": 2384,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "540",
"budget": 4678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002384",
"normalized_example_id": "ex_002384",
"source_idx": 2384,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2676
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002386",
"normalized_example_id": "ex_002386",
"source_idx": 2386,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4460,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3568
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002386",
"normalized_example_id": "ex_002386",
"source_idx": 2386,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4460,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4460
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002386",
"normalized_example_id": "ex_002386",
"source_idx": 2386,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4460,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "106",
"budget": 3919
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002390",
"normalized_example_id": "ex_002390",
"source_idx": 2390,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6531,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "106",
"budget": 5225
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002390",
"normalized_example_id": "ex_002390",
"source_idx": 2390,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6531,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "106",
"budget": 6531
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002390",
"normalized_example_id": "ex_002390",
"source_idx": 2390,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6531,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{x^{2}}{4}+y^{2}=1",
"budget": 3148
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002391",
"normalized_example_id": "ex_002391",
"source_idx": 2391,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5246,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{x^{2}}{4}+y^{2}=1",
"budget": 4197
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002391",
"normalized_example_id": "ex_002391",
"source_idx": 2391,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5246,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{x^{2}}{4}+y^{2}=1",
"budget": 5246
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002391",
"normalized_example_id": "ex_002391",
"source_idx": 2391,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5246,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5358
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002394",
"normalized_example_id": "ex_002394",
"source_idx": 2394,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7144
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002394",
"normalized_example_id": "ex_002394",
"source_idx": 2394,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8930
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002394",
"normalized_example_id": "ex_002394",
"source_idx": 2394,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2473
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002397",
"normalized_example_id": "ex_002397",
"source_idx": 2397,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4121,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3297
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002397",
"normalized_example_id": "ex_002397",
"source_idx": 2397,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4121,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4121
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002397",
"normalized_example_id": "ex_002397",
"source_idx": 2397,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4121,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{V}{U}=4",
"budget": 4990
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002401",
"normalized_example_id": "ex_002401",
"source_idx": 2401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8316,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{V}{U}=4",
"budget": 6653
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002401",
"normalized_example_id": "ex_002401",
"source_idx": 2401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8316,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{V}{U}=4",
"budget": 8316
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002401",
"normalized_example_id": "ex_002401",
"source_idx": 2401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8316,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4},\\frac{3}{4}]",
"budget": 6005
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002405",
"normalized_example_id": "ex_002405",
"source_idx": 2405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10009,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4},\\frac{3}{4}]",
"budget": 8007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002405",
"normalized_example_id": "ex_002405",
"source_idx": 2405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10009,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4},\\frac{3}{4}]",
"budget": 10009
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002405",
"normalized_example_id": "ex_002405",
"source_idx": 2405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10009,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 5417
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002406",
"normalized_example_id": "ex_002406",
"source_idx": 2406,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9028,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 7222
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002406",
"normalized_example_id": "ex_002406",
"source_idx": 2406,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9028,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\pi",
"budget": 9028
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002406",
"normalized_example_id": "ex_002406",
"source_idx": 2406,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9028,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,2,3)",
"budget": 2207
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002407",
"normalized_example_id": "ex_002407",
"source_idx": 2407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,2,3)",
"budget": 2942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002407",
"normalized_example_id": "ex_002407",
"source_idx": 2407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,2,3)",
"budget": 3678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002407",
"normalized_example_id": "ex_002407",
"source_idx": 2407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3678,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "S_{n}=3-\\frac{n+3}{2^{n}}",
"budget": 4501
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002409",
"normalized_example_id": "ex_002409",
"source_idx": 2409,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7502,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "S_{n}=3-\\frac{n+3}{2^{n}}",
"budget": 6002
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002409",
"normalized_example_id": "ex_002409",
"source_idx": 2409,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7502,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "S_{n}=3-\\frac{n+3}{2^{n}}",
"budget": 7502
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002409",
"normalized_example_id": "ex_002409",
"source_idx": 2409,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7502,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14",
"budget": 994
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002413",
"normalized_example_id": "ex_002413",
"source_idx": 2413,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14",
"budget": 1326
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002413",
"normalized_example_id": "ex_002413",
"source_idx": 2413,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14",
"budget": 1657
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002413",
"normalized_example_id": "ex_002413",
"source_idx": 2413,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "33",
"budget": 2910
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002415",
"normalized_example_id": "ex_002415",
"source_idx": 2415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4850,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "33",
"budget": 3880
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002415",
"normalized_example_id": "ex_002415",
"source_idx": 2415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4850,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "33",
"budget": 4850
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002415",
"normalized_example_id": "ex_002415",
"source_idx": 2415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4850,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1921
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002416",
"normalized_example_id": "ex_002416",
"source_idx": 2416,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3201,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2561
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002416",
"normalized_example_id": "ex_002416",
"source_idx": 2416,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3201,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3201
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002416",
"normalized_example_id": "ex_002416",
"source_idx": 2416,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3201,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3179
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002420",
"normalized_example_id": "ex_002420",
"source_idx": 2420,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5298,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4238
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002420",
"normalized_example_id": "ex_002420",
"source_idx": 2420,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5298,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5298
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002420",
"normalized_example_id": "ex_002420",
"source_idx": 2420,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5298,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "929",
"budget": 2832
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002424",
"normalized_example_id": "ex_002424",
"source_idx": 2424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4720,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "929",
"budget": 3776
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002424",
"normalized_example_id": "ex_002424",
"source_idx": 2424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4720,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "929",
"budget": 4720
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002424",
"normalized_example_id": "ex_002424",
"source_idx": 2424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4720,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11111111100",
"budget": 3276
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002425",
"normalized_example_id": "ex_002425",
"source_idx": 2425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5460,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11111111100",
"budget": 4368
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002425",
"normalized_example_id": "ex_002425",
"source_idx": 2425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5460,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11111111100",
"budget": 5460
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002425",
"normalized_example_id": "ex_002425",
"source_idx": 2425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5460,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+y^{2}-\\frac{9}{2}px=0",
"budget": 2275
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002426",
"normalized_example_id": "ex_002426",
"source_idx": 2426,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3792,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+y^{2}-\\frac{9}{2}px=0",
"budget": 3034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002426",
"normalized_example_id": "ex_002426",
"source_idx": 2426,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3792,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+y^{2}-\\frac{9}{2}px=0",
"budget": 3792
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002426",
"normalized_example_id": "ex_002426",
"source_idx": 2426,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3792,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "28",
"budget": 2921
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002428",
"normalized_example_id": "ex_002428",
"source_idx": 2428,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4869,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "28",
"budget": 3895
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002428",
"normalized_example_id": "ex_002428",
"source_idx": 2428,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4869,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "28",
"budget": 4869
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002428",
"normalized_example_id": "ex_002428",
"source_idx": 2428,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4869,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 1154
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002433",
"normalized_example_id": "ex_002433",
"source_idx": 2433,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1924,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 1539
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002433",
"normalized_example_id": "ex_002433",
"source_idx": 2433,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1924,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 1924
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002433",
"normalized_example_id": "ex_002433",
"source_idx": 2433,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1924,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.24",
"budget": 1421
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002435",
"normalized_example_id": "ex_002435",
"source_idx": 2435,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2368,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.24",
"budget": 1894
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002435",
"normalized_example_id": "ex_002435",
"source_idx": 2435,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2368,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.24",
"budget": 2368
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002435",
"normalized_example_id": "ex_002435",
"source_idx": 2435,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2368,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 < a < 1",
"budget": 1525
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002436",
"normalized_example_id": "ex_002436",
"source_idx": 2436,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2541,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 < a < 1",
"budget": 2033
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002436",
"normalized_example_id": "ex_002436",
"source_idx": 2436,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2541,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 < a < 1",
"budget": 2541
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002436",
"normalized_example_id": "ex_002436",
"source_idx": 2436,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2541,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 2385
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002440",
"normalized_example_id": "ex_002440",
"source_idx": 2440,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3975,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 3180
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002440",
"normalized_example_id": "ex_002440",
"source_idx": 2440,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3975,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 3975
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002440",
"normalized_example_id": "ex_002440",
"source_idx": 2440,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3975,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "77",
"budget": 1750
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002441",
"normalized_example_id": "ex_002441",
"source_idx": 2441,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2916,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "77",
"budget": 2333
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002441",
"normalized_example_id": "ex_002441",
"source_idx": 2441,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2916,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "77",
"budget": 2916
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002441",
"normalized_example_id": "ex_002441",
"source_idx": 2441,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2916,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "204",
"budget": 856
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002446",
"normalized_example_id": "ex_002446",
"source_idx": 2446,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1426,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "204",
"budget": 1141
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002446",
"normalized_example_id": "ex_002446",
"source_idx": 2446,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1426,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "204",
"budget": 1426
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002446",
"normalized_example_id": "ex_002446",
"source_idx": 2446,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1426,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "R\\sqrt{\\frac{2\\pi}{\\sqrt{3}}}",
"budget": 2588
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002447",
"normalized_example_id": "ex_002447",
"source_idx": 2447,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4314,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "R\\sqrt{\\frac{2\\pi}{\\sqrt{3}}}",
"budget": 3451
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002447",
"normalized_example_id": "ex_002447",
"source_idx": 2447,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4314,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "R\\sqrt{\\frac{2\\pi}{\\sqrt{3}}}",
"budget": 4314
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002447",
"normalized_example_id": "ex_002447",
"source_idx": 2447,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4314,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9060099",
"budget": 2276
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002449",
"normalized_example_id": "ex_002449",
"source_idx": 2449,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3793,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9060099",
"budget": 3034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002449",
"normalized_example_id": "ex_002449",
"source_idx": 2449,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3793,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9060099",
"budget": 3793
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002449",
"normalized_example_id": "ex_002449",
"source_idx": 2449,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3793,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3107
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002450",
"normalized_example_id": "ex_002450",
"source_idx": 2450,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5178,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4142
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002450",
"normalized_example_id": "ex_002450",
"source_idx": 2450,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5178,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 5178
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002450",
"normalized_example_id": "ex_002450",
"source_idx": 2450,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5178,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.