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": "No",
"budget": 5225
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001211",
"normalized_example_id": "ex_001211",
"source_idx": 1211,
"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": "No",
"budget": 6531
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001211",
"normalized_example_id": "ex_001211",
"source_idx": 1211,
"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": "165",
"budget": 3212
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001212",
"normalized_example_id": "ex_001212",
"source_idx": 1212,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5354,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "165",
"budget": 4283
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001212",
"normalized_example_id": "ex_001212",
"source_idx": 1212,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5354,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "165",
"budget": 5354
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001212",
"normalized_example_id": "ex_001212",
"source_idx": 1212,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5354,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2299
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001216",
"normalized_example_id": "ex_001216",
"source_idx": 1216,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3831,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3065
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001216",
"normalized_example_id": "ex_001216",
"source_idx": 1216,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3831,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3831
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001216",
"normalized_example_id": "ex_001216",
"source_idx": 1216,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3831,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2036",
"budget": 1232
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001217",
"normalized_example_id": "ex_001217",
"source_idx": 1217,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2053,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2036",
"budget": 1642
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001217",
"normalized_example_id": "ex_001217",
"source_idx": 1217,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2053,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2036",
"budget": 2053
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001217",
"normalized_example_id": "ex_001217",
"source_idx": 1217,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2053,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2603
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001219",
"normalized_example_id": "ex_001219",
"source_idx": 1219,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4339,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3471
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001219",
"normalized_example_id": "ex_001219",
"source_idx": 1219,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4339,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4339
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001219",
"normalized_example_id": "ex_001219",
"source_idx": 1219,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4339,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 2794
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001220",
"normalized_example_id": "ex_001220",
"source_idx": 1220,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4656,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 3725
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001220",
"normalized_example_id": "ex_001220",
"source_idx": 1220,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4656,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 4656
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001220",
"normalized_example_id": "ex_001220",
"source_idx": 1220,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4656,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001221",
"normalized_example_id": "ex_001221",
"source_idx": 1221,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2335,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1868
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001221",
"normalized_example_id": "ex_001221",
"source_idx": 1221,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2335,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2335
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001221",
"normalized_example_id": "ex_001221",
"source_idx": 1221,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2335,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8\\ln2}{5}",
"budget": 5099
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001222",
"normalized_example_id": "ex_001222",
"source_idx": 1222,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8498,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8\\ln2}{5}",
"budget": 6798
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001222",
"normalized_example_id": "ex_001222",
"source_idx": 1222,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8498,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8\\ln2}{5}",
"budget": 8498
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001222",
"normalized_example_id": "ex_001222",
"source_idx": 1222,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8498,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{272}{15}\\pi",
"budget": 2827
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001223",
"normalized_example_id": "ex_001223",
"source_idx": 1223,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4712,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{272}{15}\\pi",
"budget": 3770
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001223",
"normalized_example_id": "ex_001223",
"source_idx": 1223,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4712,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{272}{15}\\pi",
"budget": 4712
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001223",
"normalized_example_id": "ex_001223",
"source_idx": 1223,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4712,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}}{2},\\frac{\\sqrt{5}}{2}}",
"budget": 2668
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001224",
"normalized_example_id": "ex_001224",
"source_idx": 1224,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4446,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}}{2},\\frac{\\sqrt{5}}{2}}",
"budget": 3557
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001224",
"normalized_example_id": "ex_001224",
"source_idx": 1224,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4446,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}}{2},\\frac{\\sqrt{5}}{2}}",
"budget": 4446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001224",
"normalized_example_id": "ex_001224",
"source_idx": 1224,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4446,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+2\\sqrt{2}",
"budget": 2759
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001225",
"normalized_example_id": "ex_001225",
"source_idx": 1225,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4599,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+2\\sqrt{2}",
"budget": 3679
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001225",
"normalized_example_id": "ex_001225",
"source_idx": 1225,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4599,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+2\\sqrt{2}",
"budget": 4599
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001225",
"normalized_example_id": "ex_001225",
"source_idx": 1225,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4599,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x=y=\\pi/4",
"budget": 2768
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001228",
"normalized_example_id": "ex_001228",
"source_idx": 1228,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x=y=\\pi/4",
"budget": 3691
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001228",
"normalized_example_id": "ex_001228",
"source_idx": 1228,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x=y=\\pi/4",
"budget": 4614
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001228",
"normalized_example_id": "ex_001228",
"source_idx": 1228,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{5}",
"budget": 2002
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001229",
"normalized_example_id": "ex_001229",
"source_idx": 1229,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{5}",
"budget": 2670
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001229",
"normalized_example_id": "ex_001229",
"source_idx": 1229,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{5}",
"budget": 3337
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001229",
"normalized_example_id": "ex_001229",
"source_idx": 1229,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{2020} = a_1",
"budget": 2432
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001230",
"normalized_example_id": "ex_001230",
"source_idx": 1230,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4053,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{2020} = a_1",
"budget": 3242
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001230",
"normalized_example_id": "ex_001230",
"source_idx": 1230,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4053,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{2020} = a_1",
"budget": 4053
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001230",
"normalized_example_id": "ex_001230",
"source_idx": 1230,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4053,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11}{15}",
"budget": 3854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001231",
"normalized_example_id": "ex_001231",
"source_idx": 1231,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6424,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11}{15}",
"budget": 5139
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001231",
"normalized_example_id": "ex_001231",
"source_idx": 1231,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6424,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{11}{15}",
"budget": 6424
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001231",
"normalized_example_id": "ex_001231",
"source_idx": 1231,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6424,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1194
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001235",
"normalized_example_id": "ex_001235",
"source_idx": 1235,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1990,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1592
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001235",
"normalized_example_id": "ex_001235",
"source_idx": 1235,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1990,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1990
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001235",
"normalized_example_id": "ex_001235",
"source_idx": 1235,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1990,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,1)",
"budget": 2271
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001236",
"normalized_example_id": "ex_001236",
"source_idx": 1236,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,1)",
"budget": 3028
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001236",
"normalized_example_id": "ex_001236",
"source_idx": 1236,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,1)",
"budget": 3785
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001236",
"normalized_example_id": "ex_001236",
"source_idx": 1236,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3785,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "111",
"budget": 2789
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001239",
"normalized_example_id": "ex_001239",
"source_idx": 1239,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4648,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "111",
"budget": 3718
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001239",
"normalized_example_id": "ex_001239",
"source_idx": 1239,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4648,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "111",
"budget": 4648
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001239",
"normalized_example_id": "ex_001239",
"source_idx": 1239,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4648,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 2857
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001240",
"normalized_example_id": "ex_001240",
"source_idx": 1240,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4762,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 3810
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001240",
"normalized_example_id": "ex_001240",
"source_idx": 1240,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4762,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 4762
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001240",
"normalized_example_id": "ex_001240",
"source_idx": 1240,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4762,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3}}{3}",
"budget": 2466
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001241",
"normalized_example_id": "ex_001241",
"source_idx": 1241,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3}}{3}",
"budget": 3288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001241",
"normalized_example_id": "ex_001241",
"source_idx": 1241,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3}}{3}",
"budget": 4110
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001241",
"normalized_example_id": "ex_001241",
"source_idx": 1241,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1392
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001242",
"normalized_example_id": "ex_001242",
"source_idx": 1242,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2320,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1856
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001242",
"normalized_example_id": "ex_001242",
"source_idx": 1242,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2320,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2320
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001242",
"normalized_example_id": "ex_001242",
"source_idx": 1242,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2320,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(\\frac{10}{3}, 0\\right)",
"budget": 5393
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001243",
"normalized_example_id": "ex_001243",
"source_idx": 1243,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8988,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(\\frac{10}{3}, 0\\right)",
"budget": 7190
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001243",
"normalized_example_id": "ex_001243",
"source_idx": 1243,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8988,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(\\frac{10}{3}, 0\\right)",
"budget": 8988
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001243",
"normalized_example_id": "ex_001243",
"source_idx": 1243,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8988,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(\\frac{1}{2},+\\infty\\right)",
"budget": 3524
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001244",
"normalized_example_id": "ex_001244",
"source_idx": 1244,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(\\frac{1}{2},+\\infty\\right)",
"budget": 4699
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001244",
"normalized_example_id": "ex_001244",
"source_idx": 1244,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(\\frac{1}{2},+\\infty\\right)",
"budget": 5874
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001244",
"normalized_example_id": "ex_001244",
"source_idx": 1244,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1061
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001245",
"normalized_example_id": "ex_001245",
"source_idx": 1245,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1768,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1414
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001245",
"normalized_example_id": "ex_001245",
"source_idx": 1245,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1768,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1768
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001245",
"normalized_example_id": "ex_001245",
"source_idx": 1245,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1768,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 3716
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001248",
"normalized_example_id": "ex_001248",
"source_idx": 1248,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6194,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 4955
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001248",
"normalized_example_id": "ex_001248",
"source_idx": 1248,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6194,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 6194
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001248",
"normalized_example_id": "ex_001248",
"source_idx": 1248,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6194,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13.5",
"budget": 1183
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001249",
"normalized_example_id": "ex_001249",
"source_idx": 1249,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1971,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13.5",
"budget": 1577
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001249",
"normalized_example_id": "ex_001249",
"source_idx": 1249,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1971,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13.5",
"budget": 1971
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001249",
"normalized_example_id": "ex_001249",
"source_idx": 1249,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1971,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "unstablenode",
"budget": 640
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001251",
"normalized_example_id": "ex_001251",
"source_idx": 1251,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1067,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "unstablenode",
"budget": 854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001251",
"normalized_example_id": "ex_001251",
"source_idx": 1251,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1067,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "unstablenode",
"budget": 1067
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001251",
"normalized_example_id": "ex_001251",
"source_idx": 1251,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1067,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "101",
"budget": 1546
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001253",
"normalized_example_id": "ex_001253",
"source_idx": 1253,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2577,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "101",
"budget": 2062
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001253",
"normalized_example_id": "ex_001253",
"source_idx": 1253,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2577,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "101",
"budget": 2577
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001253",
"normalized_example_id": "ex_001253",
"source_idx": 1253,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2577,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-1,0)\\cup(\\sqrt{3},2)",
"budget": 4883
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001256",
"normalized_example_id": "ex_001256",
"source_idx": 1256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8139,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-1,0)\\cup(\\sqrt{3},2)",
"budget": 6511
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001256",
"normalized_example_id": "ex_001256",
"source_idx": 1256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8139,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-1,0)\\cup(\\sqrt{3},2)",
"budget": 8139
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001256",
"normalized_example_id": "ex_001256",
"source_idx": 1256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8139,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 3279
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001260",
"normalized_example_id": "ex_001260",
"source_idx": 1260,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5465,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 4372
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001260",
"normalized_example_id": "ex_001260",
"source_idx": 1260,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5465,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60",
"budget": 5465
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001260",
"normalized_example_id": "ex_001260",
"source_idx": 1260,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5465,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2798
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001262",
"normalized_example_id": "ex_001262",
"source_idx": 1262,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4663,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3730
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001262",
"normalized_example_id": "ex_001262",
"source_idx": 1262,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4663,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4663
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001262",
"normalized_example_id": "ex_001262",
"source_idx": 1262,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4663,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1051
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001264",
"normalized_example_id": "ex_001264",
"source_idx": 1264,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1751,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001264",
"normalized_example_id": "ex_001264",
"source_idx": 1264,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1751,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1751
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001264",
"normalized_example_id": "ex_001264",
"source_idx": 1264,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1751,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 4400
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001266",
"normalized_example_id": "ex_001266",
"source_idx": 1266,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7334,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 5867
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001266",
"normalized_example_id": "ex_001266",
"source_idx": 1266,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7334,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 7334
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001266",
"normalized_example_id": "ex_001266",
"source_idx": 1266,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7334,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30^\\circ",
"budget": 1421
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001268",
"normalized_example_id": "ex_001268",
"source_idx": 1268,
"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": "30^\\circ",
"budget": 1894
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001268",
"normalized_example_id": "ex_001268",
"source_idx": 1268,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2368,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.