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": "47",
"budget": 1453
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000121",
"normalized_example_id": "ex_000121",
"source_idx": 121,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1453,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "42",
"budget": 5481
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000123",
"normalized_example_id": "ex_000123",
"source_idx": 123,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9135,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "42",
"budget": 7308
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000123",
"normalized_example_id": "ex_000123",
"source_idx": 123,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9135,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "42",
"budget": 9135
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000123",
"normalized_example_id": "ex_000123",
"source_idx": 123,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9135,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\leqslant-\\frac{2}{3} \\text{ and } x \\neq-1 \\text{ or } x>-\\frac{1}{2} \\text{ and } x \\neq 0",
"budget": 3547
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000125",
"normalized_example_id": "ex_000125",
"source_idx": 125,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5912,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\leqslant-\\frac{2}{3} \\text{ and } x \\neq-1 \\text{ or } x>-\\frac{1}{2} \\text{ and } x \\neq 0",
"budget": 4730
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000125",
"normalized_example_id": "ex_000125",
"source_idx": 125,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5912,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\leqslant-\\frac{2}{3} \\text{ and } x \\neq-1 \\text{ or } x>-\\frac{1}{2} \\text{ and } x \\neq 0",
"budget": 5912
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000125",
"normalized_example_id": "ex_000125",
"source_idx": 125,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5912,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{15\\sqrt{15}}{4}",
"budget": 3230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000126",
"normalized_example_id": "ex_000126",
"source_idx": 126,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5384,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{15\\sqrt{15}}{4}",
"budget": 4307
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000126",
"normalized_example_id": "ex_000126",
"source_idx": 126,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5384,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{15\\sqrt{15}}{4}",
"budget": 5384
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000126",
"normalized_example_id": "ex_000126",
"source_idx": 126,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5384,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n-1)",
"budget": 2972
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000128",
"normalized_example_id": "ex_000128",
"source_idx": 128,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4953,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n-1)",
"budget": 3962
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000128",
"normalized_example_id": "ex_000128",
"source_idx": 128,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4953,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n-1)",
"budget": 4953
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000128",
"normalized_example_id": "ex_000128",
"source_idx": 128,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4953,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34",
"budget": 941
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000130",
"normalized_example_id": "ex_000130",
"source_idx": 130,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1568,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34",
"budget": 1254
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000130",
"normalized_example_id": "ex_000130",
"source_idx": 130,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1568,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "34",
"budget": 1568
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000130",
"normalized_example_id": "ex_000130",
"source_idx": 130,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1568,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 4241
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000131",
"normalized_example_id": "ex_000131",
"source_idx": 131,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7068,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 5654
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000131",
"normalized_example_id": "ex_000131",
"source_idx": 131,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7068,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 7068
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000131",
"normalized_example_id": "ex_000131",
"source_idx": 131,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7068,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1024",
"budget": 3052
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000132",
"normalized_example_id": "ex_000132",
"source_idx": 132,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5087,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1024",
"budget": 4070
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000132",
"normalized_example_id": "ex_000132",
"source_idx": 132,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5087,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1024",
"budget": 5087
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000132",
"normalized_example_id": "ex_000132",
"source_idx": 132,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5087,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2451
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000133",
"normalized_example_id": "ex_000133",
"source_idx": 133,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4085,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3268
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000133",
"normalized_example_id": "ex_000133",
"source_idx": 133,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4085,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4085
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000133",
"normalized_example_id": "ex_000133",
"source_idx": 133,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4085,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "119282",
"budget": 2623
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000137",
"normalized_example_id": "ex_000137",
"source_idx": 137,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4371,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "119282",
"budget": 3497
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000137",
"normalized_example_id": "ex_000137",
"source_idx": 137,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4371,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "119282",
"budget": 4371
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000137",
"normalized_example_id": "ex_000137",
"source_idx": 137,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4371,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{1}=2,x_{2}=-9/2",
"budget": 2170
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000138",
"normalized_example_id": "ex_000138",
"source_idx": 138,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3616,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{1}=2,x_{2}=-9/2",
"budget": 2893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000138",
"normalized_example_id": "ex_000138",
"source_idx": 138,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3616,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{1}=2,x_{2}=-9/2",
"budget": 3616
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000138",
"normalized_example_id": "ex_000138",
"source_idx": 138,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3616,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\sqrt{2}}, \\frac{1}{\\sqrt{2}} \\right)",
"budget": 1684
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000140",
"normalized_example_id": "ex_000140",
"source_idx": 140,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2807,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\sqrt{2}}, \\frac{1}{\\sqrt{2}} \\right)",
"budget": 2246
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000140",
"normalized_example_id": "ex_000140",
"source_idx": 140,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2807,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{\\sqrt{2}}, \\frac{1}{\\sqrt{2}} \\right)",
"budget": 2807
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000140",
"normalized_example_id": "ex_000140",
"source_idx": 140,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2807,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}\\left[(1+\\sqrt{2})^{n+1}+(1-\\sqrt{2})^{n+1}\\right]",
"budget": 4253
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000144",
"normalized_example_id": "ex_000144",
"source_idx": 144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7089,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}\\left[(1+\\sqrt{2})^{n+1}+(1-\\sqrt{2})^{n+1}\\right]",
"budget": 5671
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000144",
"normalized_example_id": "ex_000144",
"source_idx": 144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7089,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2}\\left[(1+\\sqrt{2})^{n+1}+(1-\\sqrt{2})^{n+1}\\right]",
"budget": 7089
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000144",
"normalized_example_id": "ex_000144",
"source_idx": 144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7089,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 2573
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000146",
"normalized_example_id": "ex_000146",
"source_idx": 146,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4288,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 3430
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000146",
"normalized_example_id": "ex_000146",
"source_idx": 146,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4288,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 4288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000146",
"normalized_example_id": "ex_000146",
"source_idx": 146,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4288,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:3:5:7",
"budget": 3530
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000147",
"normalized_example_id": "ex_000147",
"source_idx": 147,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5884,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:3:5:7",
"budget": 4707
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000147",
"normalized_example_id": "ex_000147",
"source_idx": 147,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5884,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:3:5:7",
"budget": 5884
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000147",
"normalized_example_id": "ex_000147",
"source_idx": 147,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5884,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 4301
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000148",
"normalized_example_id": "ex_000148",
"source_idx": 148,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7169,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 5735
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000148",
"normalized_example_id": "ex_000148",
"source_idx": 148,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7169,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 7169
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000148",
"normalized_example_id": "ex_000148",
"source_idx": 148,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7169,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1835",
"budget": 2948
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000149",
"normalized_example_id": "ex_000149",
"source_idx": 149,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4914,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1835",
"budget": 3931
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000149",
"normalized_example_id": "ex_000149",
"source_idx": 149,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4914,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1835",
"budget": 4914
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000149",
"normalized_example_id": "ex_000149",
"source_idx": 149,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4914,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2007, 1116, 1996, 2887, 3778, 4669",
"budget": 2651
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000152",
"normalized_example_id": "ex_000152",
"source_idx": 152,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4418,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2007, 1116, 1996, 2887, 3778, 4669",
"budget": 3534
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000152",
"normalized_example_id": "ex_000152",
"source_idx": 152,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4418,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2007, 1116, 1996, 2887, 3778, 4669",
"budget": 4418
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000152",
"normalized_example_id": "ex_000152",
"source_idx": 152,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4418,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5:3",
"budget": 4007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000153",
"normalized_example_id": "ex_000153",
"source_idx": 153,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6678,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5:3",
"budget": 5342
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000153",
"normalized_example_id": "ex_000153",
"source_idx": 153,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6678,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5:3",
"budget": 6678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000153",
"normalized_example_id": "ex_000153",
"source_idx": 153,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6678,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7,4;26,15;97,56",
"budget": 3422
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000157",
"normalized_example_id": "ex_000157",
"source_idx": 157,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5704,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7,4;26,15;97,56",
"budget": 4563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000157",
"normalized_example_id": "ex_000157",
"source_idx": 157,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5704,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7,4;26,15;97,56",
"budget": 5704
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000157",
"normalized_example_id": "ex_000157",
"source_idx": 157,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5704,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4102
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000159",
"normalized_example_id": "ex_000159",
"source_idx": 159,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6836,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5469
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000159",
"normalized_example_id": "ex_000159",
"source_idx": 159,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6836,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6836
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000159",
"normalized_example_id": "ex_000159",
"source_idx": 159,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6836,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{7}",
"budget": 1249
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000162",
"normalized_example_id": "ex_000162",
"source_idx": 162,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2081,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{7}",
"budget": 1665
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000162",
"normalized_example_id": "ex_000162",
"source_idx": 162,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2081,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{7}",
"budget": 2081
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000162",
"normalized_example_id": "ex_000162",
"source_idx": 162,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2081,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "647",
"budget": 5836
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000164",
"normalized_example_id": "ex_000164",
"source_idx": 164,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9726,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "647",
"budget": 7781
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000164",
"normalized_example_id": "ex_000164",
"source_idx": 164,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9726,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "647",
"budget": 9726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000164",
"normalized_example_id": "ex_000164",
"source_idx": 164,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9726,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23,65,34,86",
"budget": 3007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000167",
"normalized_example_id": "ex_000167",
"source_idx": 167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5012,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23,65,34,86",
"budget": 4010
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000167",
"normalized_example_id": "ex_000167",
"source_idx": 167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5012,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23,65,34,86",
"budget": 5012
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000167",
"normalized_example_id": "ex_000167",
"source_idx": 167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5012,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3456
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000171",
"normalized_example_id": "ex_000171",
"source_idx": 171,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5760,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4608
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000171",
"normalized_example_id": "ex_000171",
"source_idx": 171,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5760,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5760
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000171",
"normalized_example_id": "ex_000171",
"source_idx": 171,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5760,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.1",
"budget": 947
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000173",
"normalized_example_id": "ex_000173",
"source_idx": 173,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1579,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.1",
"budget": 1263
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000173",
"normalized_example_id": "ex_000173",
"source_idx": 173,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1579,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.1",
"budget": 1579
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000173",
"normalized_example_id": "ex_000173",
"source_idx": 173,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1579,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n}=4n-3",
"budget": 762
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000176",
"normalized_example_id": "ex_000176",
"source_idx": 176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1270,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n}=4n-3",
"budget": 1016
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000176",
"normalized_example_id": "ex_000176",
"source_idx": 176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1270,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n}=4n-3",
"budget": 1270
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000176",
"normalized_example_id": "ex_000176",
"source_idx": 176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1270,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 223, 9)",
"budget": 2731
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000177",
"normalized_example_id": "ex_000177",
"source_idx": 177,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4551,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 223, 9)",
"budget": 3641
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000177",
"normalized_example_id": "ex_000177",
"source_idx": 177,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4551,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, 223, 9)",
"budget": 4551
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000177",
"normalized_example_id": "ex_000177",
"source_idx": 177,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4551,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\ln\\sqrt{\\frac{2}{3}}",
"budget": 2150
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000179",
"normalized_example_id": "ex_000179",
"source_idx": 179,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3584,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\ln\\sqrt{\\frac{2}{3}}",
"budget": 2867
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000179",
"normalized_example_id": "ex_000179",
"source_idx": 179,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3584,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\ln\\sqrt{\\frac{2}{3}}",
"budget": 3584
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000179",
"normalized_example_id": "ex_000179",
"source_idx": 179,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3584,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(n+2)=(n+3)f(n+1)-(n+2)f(n)",
"budget": 1293
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000181",
"normalized_example_id": "ex_000181",
"source_idx": 181,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2155,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(n+2)=(n+3)f(n+1)-(n+2)f(n)",
"budget": 1724
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000181",
"normalized_example_id": "ex_000181",
"source_idx": 181,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2155,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(n+2)=(n+3)f(n+1)-(n+2)f(n)",
"budget": 2155
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000181",
"normalized_example_id": "ex_000181",
"source_idx": 181,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2155,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(-4, \\frac{24}{5}\\right),\\left(3, \\frac{3}{5}\\right)",
"budget": 1724
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000186",
"normalized_example_id": "ex_000186",
"source_idx": 186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2874,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(-4, \\frac{24}{5}\\right),\\left(3, \\frac{3}{5}\\right)",
"budget": 2299
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000186",
"normalized_example_id": "ex_000186",
"source_idx": 186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2874,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(-4, \\frac{24}{5}\\right),\\left(3, \\frac{3}{5}\\right)",
"budget": 2874
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000186",
"normalized_example_id": "ex_000186",
"source_idx": 186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2874,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:5",
"budget": 4343
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000188",
"normalized_example_id": "ex_000188",
"source_idx": 188,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7238,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:5",
"budget": 5790
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000188",
"normalized_example_id": "ex_000188",
"source_idx": 188,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7238,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:5",
"budget": 7238
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000188",
"normalized_example_id": "ex_000188",
"source_idx": 188,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7238,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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) = (0, 0) \\text{ and } \\left(\\frac{1}{2}, \\frac{1}{2}\\right)",
"budget": 5044
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000190",
"normalized_example_id": "ex_000190",
"source_idx": 190,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8406,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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) = (0, 0) \\text{ and } \\left(\\frac{1}{2}, \\frac{1}{2}\\right)",
"budget": 6725
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000190",
"normalized_example_id": "ex_000190",
"source_idx": 190,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8406,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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) = (0, 0) \\text{ and } \\left(\\frac{1}{2}, \\frac{1}{2}\\right)",
"budget": 8406
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000190",
"normalized_example_id": "ex_000190",
"source_idx": 190,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8406,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 3563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000191",
"normalized_example_id": "ex_000191",
"source_idx": 191,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5939,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 4751
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000191",
"normalized_example_id": "ex_000191",
"source_idx": 191,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5939,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 5939
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000191",
"normalized_example_id": "ex_000191",
"source_idx": 191,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5939,
"... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.