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": "BC",
"budget": 4651
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000058",
"normalized_example_id": "ex_000058",
"source_idx": 58,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5814,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "BC",
"budget": 5814
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000058",
"normalized_example_id": "ex_000058",
"source_idx": 58,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5814,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=3",
"budget": 1830
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000059",
"normalized_example_id": "ex_000059",
"source_idx": 59,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3050,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=3",
"budget": 2440
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000059",
"normalized_example_id": "ex_000059",
"source_idx": 59,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3050,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=3",
"budget": 3050
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000059",
"normalized_example_id": "ex_000059",
"source_idx": 59,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3050,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(\\sqrt{k+\\frac{4}{k}+5}+n-3)^{2}",
"budget": 5269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000064",
"normalized_example_id": "ex_000064",
"source_idx": 64,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8781,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(\\sqrt{k+\\frac{4}{k}+5}+n-3)^{2}",
"budget": 7025
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000064",
"normalized_example_id": "ex_000064",
"source_idx": 64,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8781,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(\\sqrt{k+\\frac{4}{k}+5}+n-3)^{2}",
"budget": 8781
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000064",
"normalized_example_id": "ex_000064",
"source_idx": 64,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8781,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 5168
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000065",
"normalized_example_id": "ex_000065",
"source_idx": 65,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8613,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 6890
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000065",
"normalized_example_id": "ex_000065",
"source_idx": 65,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8613,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 8613
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000065",
"normalized_example_id": "ex_000065",
"source_idx": 65,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8613,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1962
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000066",
"normalized_example_id": "ex_000066",
"source_idx": 66,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3270,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2616
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000066",
"normalized_example_id": "ex_000066",
"source_idx": 66,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3270,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3270
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000066",
"normalized_example_id": "ex_000066",
"source_idx": 66,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3270,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{25}{4}",
"budget": 1940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000067",
"normalized_example_id": "ex_000067",
"source_idx": 67,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3233,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{25}{4}",
"budget": 2586
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000067",
"normalized_example_id": "ex_000067",
"source_idx": 67,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3233,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{25}{4}",
"budget": 3233
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000067",
"normalized_example_id": "ex_000067",
"source_idx": 67,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3233,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1511
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000068",
"normalized_example_id": "ex_000068",
"source_idx": 68,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2518,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2014
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000068",
"normalized_example_id": "ex_000068",
"source_idx": 68,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2518,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2518
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000068",
"normalized_example_id": "ex_000068",
"source_idx": 68,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2518,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 646
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000069",
"normalized_example_id": "ex_000069",
"source_idx": 69,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1076,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 861
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000069",
"normalized_example_id": "ex_000069",
"source_idx": 69,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1076,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1076
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000069",
"normalized_example_id": "ex_000069",
"source_idx": 69,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1076,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "77",
"budget": 3147
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000070",
"normalized_example_id": "ex_000070",
"source_idx": 70,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5245,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "77",
"budget": 4196
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000070",
"normalized_example_id": "ex_000070",
"source_idx": 70,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5245,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "77",
"budget": 5245
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000070",
"normalized_example_id": "ex_000070",
"source_idx": 70,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5245,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2227
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000071",
"normalized_example_id": "ex_000071",
"source_idx": 71,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3711,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2969
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000071",
"normalized_example_id": "ex_000071",
"source_idx": 71,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3711,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3711
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000071",
"normalized_example_id": "ex_000071",
"source_idx": 71,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3711,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "k = 4",
"budget": 5143
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000072",
"normalized_example_id": "ex_000072",
"source_idx": 72,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8572,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "k = 4",
"budget": 6858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000072",
"normalized_example_id": "ex_000072",
"source_idx": 72,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8572,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "k = 4",
"budget": 8572
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000072",
"normalized_example_id": "ex_000072",
"source_idx": 72,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8572,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "107",
"budget": 3145
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000073",
"normalized_example_id": "ex_000073",
"source_idx": 73,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5241,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "107",
"budget": 4193
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000073",
"normalized_example_id": "ex_000073",
"source_idx": 73,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5241,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "107",
"budget": 5241
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000073",
"normalized_example_id": "ex_000073",
"source_idx": 73,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5241,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=\\frac{1}{n(n+1)}",
"budget": 1390
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000075",
"normalized_example_id": "ex_000075",
"source_idx": 75,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2316,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=\\frac{1}{n(n+1)}",
"budget": 1853
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000075",
"normalized_example_id": "ex_000075",
"source_idx": 75,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2316,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=\\frac{1}{n(n+1)}",
"budget": 2316
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000075",
"normalized_example_id": "ex_000075",
"source_idx": 75,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2316,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0,2,3",
"budget": 5663
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000076",
"normalized_example_id": "ex_000076",
"source_idx": 76,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9438,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0,2,3",
"budget": 7550
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000076",
"normalized_example_id": "ex_000076",
"source_idx": 76,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9438,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0,2,3",
"budget": 9438
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000076",
"normalized_example_id": "ex_000076",
"source_idx": 76,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9438,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{41}{42}",
"budget": 3157
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000077",
"normalized_example_id": "ex_000077",
"source_idx": 77,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5261,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{41}{42}",
"budget": 4209
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000077",
"normalized_example_id": "ex_000077",
"source_idx": 77,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5261,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{41}{42}",
"budget": 5261
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000077",
"normalized_example_id": "ex_000077",
"source_idx": 77,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5261,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 5009
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000078",
"normalized_example_id": "ex_000078",
"source_idx": 78,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8348,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 6678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000078",
"normalized_example_id": "ex_000078",
"source_idx": 78,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8348,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 8348
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000078",
"normalized_example_id": "ex_000078",
"source_idx": 78,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8348,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1633
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000079",
"normalized_example_id": "ex_000079",
"source_idx": 79,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2722,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2178
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000079",
"normalized_example_id": "ex_000079",
"source_idx": 79,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2722,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2722
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000079",
"normalized_example_id": "ex_000079",
"source_idx": 79,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2722,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000084",
"normalized_example_id": "ex_000084",
"source_idx": 84,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1297,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 1038
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000084",
"normalized_example_id": "ex_000084",
"source_idx": 84,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1297,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 1297
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000084",
"normalized_example_id": "ex_000084",
"source_idx": 84,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1297,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2009",
"budget": 4057
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000085",
"normalized_example_id": "ex_000085",
"source_idx": 85,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6761,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2009",
"budget": 5409
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000085",
"normalized_example_id": "ex_000085",
"source_idx": 85,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6761,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2009",
"budget": 6761
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000085",
"normalized_example_id": "ex_000085",
"source_idx": 85,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6761,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3352
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000086",
"normalized_example_id": "ex_000086",
"source_idx": 86,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5587,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4470
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000086",
"normalized_example_id": "ex_000086",
"source_idx": 86,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5587,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 5587
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000086",
"normalized_example_id": "ex_000086",
"source_idx": 86,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5587,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2381
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000087",
"normalized_example_id": "ex_000087",
"source_idx": 87,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3968,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3174
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000087",
"normalized_example_id": "ex_000087",
"source_idx": 87,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3968,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3968
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000087",
"normalized_example_id": "ex_000087",
"source_idx": 87,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3968,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4b^{2}\\sin2\\beta\\cos^{2}\\frac{\\alpha}{2}",
"budget": 2454
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000090",
"normalized_example_id": "ex_000090",
"source_idx": 90,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4090,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4b^{2}\\sin2\\beta\\cos^{2}\\frac{\\alpha}{2}",
"budget": 3272
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000090",
"normalized_example_id": "ex_000090",
"source_idx": 90,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4090,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4b^{2}\\sin2\\beta\\cos^{2}\\frac{\\alpha}{2}",
"budget": 4090
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000090",
"normalized_example_id": "ex_000090",
"source_idx": 90,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4090,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1594
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000091",
"normalized_example_id": "ex_000091",
"source_idx": 91,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2656,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2125
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000091",
"normalized_example_id": "ex_000091",
"source_idx": 91,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2656,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2656
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000091",
"normalized_example_id": "ex_000091",
"source_idx": 91,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2656,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,6) \\text{ or } (4,18)",
"budget": 4418
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000093",
"normalized_example_id": "ex_000093",
"source_idx": 93,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7363,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,6) \\text{ or } (4,18)",
"budget": 5890
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000093",
"normalized_example_id": "ex_000093",
"source_idx": 93,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7363,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,6) \\text{ or } (4,18)",
"budget": 7363
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000093",
"normalized_example_id": "ex_000093",
"source_idx": 93,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7363,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 3476
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000096",
"normalized_example_id": "ex_000096",
"source_idx": 96,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5793,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 4634
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000096",
"normalized_example_id": "ex_000096",
"source_idx": 96,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5793,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 5793
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000096",
"normalized_example_id": "ex_000096",
"source_idx": 96,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5793,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n}-1",
"budget": 1465
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000097",
"normalized_example_id": "ex_000097",
"source_idx": 97,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2442,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n}-1",
"budget": 1954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000097",
"normalized_example_id": "ex_000097",
"source_idx": 97,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2442,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n}-1",
"budget": 2442
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000097",
"normalized_example_id": "ex_000097",
"source_idx": 97,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2442,
"c... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70;90;20",
"budget": 2974
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000101",
"normalized_example_id": "ex_000101",
"source_idx": 101,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4957,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70;90;20",
"budget": 3966
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000101",
"normalized_example_id": "ex_000101",
"source_idx": 101,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4957,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70;90;20",
"budget": 4957
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000101",
"normalized_example_id": "ex_000101",
"source_idx": 101,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4957,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38",
"budget": 2071
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000103",
"normalized_example_id": "ex_000103",
"source_idx": 103,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3452,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38",
"budget": 2762
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000103",
"normalized_example_id": "ex_000103",
"source_idx": 103,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3452,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38",
"budget": 3452
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000103",
"normalized_example_id": "ex_000103",
"source_idx": 103,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3452,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 654
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000105",
"normalized_example_id": "ex_000105",
"source_idx": 105,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1090,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 872
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000105",
"normalized_example_id": "ex_000105",
"source_idx": 105,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1090,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1090
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000105",
"normalized_example_id": "ex_000105",
"source_idx": 105,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1090,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "750",
"budget": 737
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000110",
"normalized_example_id": "ex_000110",
"source_idx": 110,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1229,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "750",
"budget": 983
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000110",
"normalized_example_id": "ex_000110",
"source_idx": 110,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1229,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "750",
"budget": 1229
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000110",
"normalized_example_id": "ex_000110",
"source_idx": 110,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1229,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4685
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000113",
"normalized_example_id": "ex_000113",
"source_idx": 113,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7809,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6247
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000113",
"normalized_example_id": "ex_000113",
"source_idx": 113,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7809,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7809
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000113",
"normalized_example_id": "ex_000113",
"source_idx": 113,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7809,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}{17}",
"budget": 1802
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000115",
"normalized_example_id": "ex_000115",
"source_idx": 115,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3003,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}{17}",
"budget": 2402
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000115",
"normalized_example_id": "ex_000115",
"source_idx": 115,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3003,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}{17}",
"budget": 3003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000115",
"normalized_example_id": "ex_000115",
"source_idx": 115,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3003,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4708
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000119",
"normalized_example_id": "ex_000119",
"source_idx": 119,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7847,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 6278
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000119",
"normalized_example_id": "ex_000119",
"source_idx": 119,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7847,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 7847
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000119",
"normalized_example_id": "ex_000119",
"source_idx": 119,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7847,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 872
} | {
"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": "47",
"budget": 1162
} | {
"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,
"... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.