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": "13",
"budget": 2717
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000256",
"normalized_example_id": "ex_000256",
"source_idx": 256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3396,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 3396
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000256",
"normalized_example_id": "ex_000256",
"source_idx": 256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3396,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "155",
"budget": 3641
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000259",
"normalized_example_id": "ex_000259",
"source_idx": 259,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6068,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "155",
"budget": 4854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000259",
"normalized_example_id": "ex_000259",
"source_idx": 259,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6068,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "155",
"budget": 6068
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000259",
"normalized_example_id": "ex_000259",
"source_idx": 259,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6068,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2507
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000260",
"normalized_example_id": "ex_000260",
"source_idx": 260,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4178,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3342
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000260",
"normalized_example_id": "ex_000260",
"source_idx": 260,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4178,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4178
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000260",
"normalized_example_id": "ex_000260",
"source_idx": 260,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4178,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=\\frac{a-b}{2}, x_{2}=\\frac{a-4b}{5}",
"budget": 2182
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000265",
"normalized_example_id": "ex_000265",
"source_idx": 265,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3636,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=\\frac{a-b}{2}, x_{2}=\\frac{a-4b}{5}",
"budget": 2909
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000265",
"normalized_example_id": "ex_000265",
"source_idx": 265,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3636,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=\\frac{a-b}{2}, x_{2}=\\frac{a-4b}{5}",
"budget": 3636
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000265",
"normalized_example_id": "ex_000265",
"source_idx": 265,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3636,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{5}}{2}",
"budget": 3707
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000267",
"normalized_example_id": "ex_000267",
"source_idx": 267,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6178,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{5}}{2}",
"budget": 4942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000267",
"normalized_example_id": "ex_000267",
"source_idx": 267,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6178,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{5}}{2}",
"budget": 6178
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000267",
"normalized_example_id": "ex_000267",
"source_idx": 267,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6178,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x) = 0 \\text{ or } f(x) = \\frac{1}{2}",
"budget": 3620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000268",
"normalized_example_id": "ex_000268",
"source_idx": 268,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6033,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x) = 0 \\text{ or } f(x) = \\frac{1}{2}",
"budget": 4826
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000268",
"normalized_example_id": "ex_000268",
"source_idx": 268,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6033,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x) = 0 \\text{ or } f(x) = \\frac{1}{2}",
"budget": 6033
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000268",
"normalized_example_id": "ex_000268",
"source_idx": 268,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6033,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\geqslant \\sqrt{3}+1",
"budget": 4307
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000269",
"normalized_example_id": "ex_000269",
"source_idx": 269,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7179,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\geqslant \\sqrt{3}+1",
"budget": 5743
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000269",
"normalized_example_id": "ex_000269",
"source_idx": 269,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7179,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\geqslant \\sqrt{3}+1",
"budget": 7179
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000269",
"normalized_example_id": "ex_000269",
"source_idx": 269,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7179,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3000",
"budget": 3098
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000272",
"normalized_example_id": "ex_000272",
"source_idx": 272,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5164,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3000",
"budget": 4131
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000272",
"normalized_example_id": "ex_000272",
"source_idx": 272,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5164,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3000",
"budget": 5164
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000272",
"normalized_example_id": "ex_000272",
"source_idx": 272,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5164,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 3080
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000273",
"normalized_example_id": "ex_000273",
"source_idx": 273,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5134,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 4107
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000273",
"normalized_example_id": "ex_000273",
"source_idx": 273,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5134,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 5134
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000273",
"normalized_example_id": "ex_000273",
"source_idx": 273,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5134,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{12}",
"budget": 5030
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000274",
"normalized_example_id": "ex_000274",
"source_idx": 274,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8383,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{12}",
"budget": 6706
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000274",
"normalized_example_id": "ex_000274",
"source_idx": 274,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8383,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{12}",
"budget": 8383
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000274",
"normalized_example_id": "ex_000274",
"source_idx": 274,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8383,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "206",
"budget": 803
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000275",
"normalized_example_id": "ex_000275",
"source_idx": 275,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1338,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "206",
"budget": 1070
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000275",
"normalized_example_id": "ex_000275",
"source_idx": 275,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1338,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "206",
"budget": 1338
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000275",
"normalized_example_id": "ex_000275",
"source_idx": 275,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1338,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4:3",
"budget": 3718
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000276",
"normalized_example_id": "ex_000276",
"source_idx": 276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6196,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4:3",
"budget": 4957
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000276",
"normalized_example_id": "ex_000276",
"source_idx": 276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6196,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4:3",
"budget": 6196
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000276",
"normalized_example_id": "ex_000276",
"source_idx": 276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6196,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(5,4)",
"budget": 2380
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000278",
"normalized_example_id": "ex_000278",
"source_idx": 278,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3966,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(5,4)",
"budget": 3173
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000278",
"normalized_example_id": "ex_000278",
"source_idx": 278,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3966,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(5,4)",
"budget": 3966
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000278",
"normalized_example_id": "ex_000278",
"source_idx": 278,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3966,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,-2",
"budget": 5302
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000281",
"normalized_example_id": "ex_000281",
"source_idx": 281,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8836,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,-2",
"budget": 7069
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000281",
"normalized_example_id": "ex_000281",
"source_idx": 281,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8836,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,-2",
"budget": 8836
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000281",
"normalized_example_id": "ex_000281",
"source_idx": 281,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8836,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "169.5\\,",
"budget": 2893
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000283",
"normalized_example_id": "ex_000283",
"source_idx": 283,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4821,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "169.5\\,",
"budget": 3857
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000283",
"normalized_example_id": "ex_000283",
"source_idx": 283,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4821,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "169.5\\,",
"budget": 4821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000283",
"normalized_example_id": "ex_000283",
"source_idx": 283,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4821,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5512
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000284",
"normalized_example_id": "ex_000284",
"source_idx": 284,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9186,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7349
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000284",
"normalized_example_id": "ex_000284",
"source_idx": 284,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9186,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 9186
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000284",
"normalized_example_id": "ex_000284",
"source_idx": 284,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9186,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{3}\\sqrt{39}",
"budget": 2648
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000287",
"normalized_example_id": "ex_000287",
"source_idx": 287,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4414,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{3}\\sqrt{39}",
"budget": 3531
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000287",
"normalized_example_id": "ex_000287",
"source_idx": 287,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4414,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{3}\\sqrt{39}",
"budget": 4414
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000287",
"normalized_example_id": "ex_000287",
"source_idx": 287,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4414,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2r,\\frac{4r}{3},\\frac{10r}{3},4r",
"budget": 2162
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000288",
"normalized_example_id": "ex_000288",
"source_idx": 288,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3604,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2r,\\frac{4r}{3},\\frac{10r}{3},4r",
"budget": 2883
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000288",
"normalized_example_id": "ex_000288",
"source_idx": 288,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3604,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2r,\\frac{4r}{3},\\frac{10r}{3},4r",
"budget": 3604
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000288",
"normalized_example_id": "ex_000288",
"source_idx": 288,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3604,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x) = x",
"budget": 3023
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000290",
"normalized_example_id": "ex_000290",
"source_idx": 290,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5039,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x) = x",
"budget": 4031
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000290",
"normalized_example_id": "ex_000290",
"source_idx": 290,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5039,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(x) = x",
"budget": 5039
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000290",
"normalized_example_id": "ex_000290",
"source_idx": 290,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5039,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 5162
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000292",
"normalized_example_id": "ex_000292",
"source_idx": 292,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8604,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 6883
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000292",
"normalized_example_id": "ex_000292",
"source_idx": 292,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8604,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15",
"budget": 8604
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000292",
"normalized_example_id": "ex_000292",
"source_idx": 292,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8604,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 2722
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000293",
"normalized_example_id": "ex_000293",
"source_idx": 293,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4537,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 3630
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000293",
"normalized_example_id": "ex_000293",
"source_idx": 293,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4537,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 4537
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000293",
"normalized_example_id": "ex_000293",
"source_idx": 293,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4537,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-\\infty,2]\\cup[6,\\infty)",
"budget": 622
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000295",
"normalized_example_id": "ex_000295",
"source_idx": 295,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1036,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-\\infty,2]\\cup[6,\\infty)",
"budget": 829
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000295",
"normalized_example_id": "ex_000295",
"source_idx": 295,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1036,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-\\infty,2]\\cup[6,\\infty)",
"budget": 1036
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000295",
"normalized_example_id": "ex_000295",
"source_idx": 295,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1036,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1342
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000296",
"normalized_example_id": "ex_000296",
"source_idx": 296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2236,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1789
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000296",
"normalized_example_id": "ex_000296",
"source_idx": 296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2236,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2236
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000296",
"normalized_example_id": "ex_000296",
"source_idx": 296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2236,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7860.201",
"budget": 4101
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000299",
"normalized_example_id": "ex_000299",
"source_idx": 299,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6835,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7860.201",
"budget": 5468
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000299",
"normalized_example_id": "ex_000299",
"source_idx": 299,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6835,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7860.201",
"budget": 6835
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000299",
"normalized_example_id": "ex_000299",
"source_idx": 299,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6835,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\times10^{2017}",
"budget": 1265
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000300",
"normalized_example_id": "ex_000300",
"source_idx": 300,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2108,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\times10^{2017}",
"budget": 1686
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000300",
"normalized_example_id": "ex_000300",
"source_idx": 300,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2108,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\times10^{2017}",
"budget": 2108
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000300",
"normalized_example_id": "ex_000300",
"source_idx": 300,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2108,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, b) = (-2, 1)",
"budget": 1822
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000301",
"normalized_example_id": "ex_000301",
"source_idx": 301,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3036,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, b) = (-2, 1)",
"budget": 2429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000301",
"normalized_example_id": "ex_000301",
"source_idx": 301,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3036,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, b) = (-2, 1)",
"budget": 3036
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000301",
"normalized_example_id": "ex_000301",
"source_idx": 301,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3036,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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==-1",
"budget": 2734
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000302",
"normalized_example_id": "ex_000302",
"source_idx": 302,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4557,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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==-1",
"budget": 3646
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000302",
"normalized_example_id": "ex_000302",
"source_idx": 302,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4557,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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==-1",
"budget": 4557
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000302",
"normalized_example_id": "ex_000302",
"source_idx": 302,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4557,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "198",
"budget": 3424
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000304",
"normalized_example_id": "ex_000304",
"source_idx": 304,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5706,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "198",
"budget": 4565
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000304",
"normalized_example_id": "ex_000304",
"source_idx": 304,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5706,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "198",
"budget": 5706
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000304",
"normalized_example_id": "ex_000304",
"source_idx": 304,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5706,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{32}{65}",
"budget": 2022
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000313",
"normalized_example_id": "ex_000313",
"source_idx": 313,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3370,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{32}{65}",
"budget": 2696
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000313",
"normalized_example_id": "ex_000313",
"source_idx": 313,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3370,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{32}{65}",
"budget": 3370
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000313",
"normalized_example_id": "ex_000313",
"source_idx": 313,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3370,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 4842
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000315",
"normalized_example_id": "ex_000315",
"source_idx": 315,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8070,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 6456
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000315",
"normalized_example_id": "ex_000315",
"source_idx": 315,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8070,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 8070
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000315",
"normalized_example_id": "ex_000315",
"source_idx": 315,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8070,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\in \\{1, 2, \\dots, N+1\\}",
"budget": 5621
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000318",
"normalized_example_id": "ex_000318",
"source_idx": 318,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9368,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\in \\{1, 2, \\dots, N+1\\}",
"budget": 7494
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000318",
"normalized_example_id": "ex_000318",
"source_idx": 318,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9368,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\in \\{1, 2, \\dots, N+1\\}",
"budget": 9368
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000318",
"normalized_example_id": "ex_000318",
"source_idx": 318,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9368,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3467
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000319",
"normalized_example_id": "ex_000319",
"source_idx": 319,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5779,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4623
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000319",
"normalized_example_id": "ex_000319",
"source_idx": 319,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5779,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5779
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000319",
"normalized_example_id": "ex_000319",
"source_idx": 319,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5779,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60^\\circ",
"budget": 5879
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000326",
"normalized_example_id": "ex_000326",
"source_idx": 326,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9798,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60^\\circ",
"budget": 7838
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000326",
"normalized_example_id": "ex_000326",
"source_idx": 326,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9798,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "60^\\circ",
"budget": 9798
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000326",
"normalized_example_id": "ex_000326",
"source_idx": 326,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9798,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1090",
"budget": 964
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000327",
"normalized_example_id": "ex_000327",
"source_idx": 327,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1607,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1090",
"budget": 1286
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000327",
"normalized_example_id": "ex_000327",
"source_idx": 327,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1607,
"... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.