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": "2",
"budget": 4433
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002192",
"normalized_example_id": "ex_002192",
"source_idx": 2192,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4433,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\frac{7}{15} \\text{ or } \\frac{4}{5}",
"budget": 2215
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002193",
"normalized_example_id": "ex_002193",
"source_idx": 2193,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3691,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\frac{7}{15} \\text{ or } \\frac{4}{5}",
"budget": 2953
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002193",
"normalized_example_id": "ex_002193",
"source_idx": 2193,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3691,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\frac{7}{15} \\text{ or } \\frac{4}{5}",
"budget": 3691
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002193",
"normalized_example_id": "ex_002193",
"source_idx": 2193,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3691,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{11}{20}",
"budget": 1973
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002194",
"normalized_example_id": "ex_002194",
"source_idx": 2194,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{11}{20}",
"budget": 2630
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002194",
"normalized_example_id": "ex_002194",
"source_idx": 2194,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{11}{20}",
"budget": 3288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002194",
"normalized_example_id": "ex_002194",
"source_idx": 2194,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12090",
"budget": 3079
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002195",
"normalized_example_id": "ex_002195",
"source_idx": 2195,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12090",
"budget": 4105
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002195",
"normalized_example_id": "ex_002195",
"source_idx": 2195,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12090",
"budget": 5131
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002195",
"normalized_example_id": "ex_002195",
"source_idx": 2195,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1095
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002197",
"normalized_example_id": "ex_002197",
"source_idx": 2197,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1825,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1460
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002197",
"normalized_example_id": "ex_002197",
"source_idx": 2197,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1825,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1825
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002197",
"normalized_example_id": "ex_002197",
"source_idx": 2197,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1825,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{9}{2}",
"budget": 2839
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002205",
"normalized_example_id": "ex_002205",
"source_idx": 2205,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4732,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{9}{2}",
"budget": 3786
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002205",
"normalized_example_id": "ex_002205",
"source_idx": 2205,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4732,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{9}{2}",
"budget": 4732
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002205",
"normalized_example_id": "ex_002205",
"source_idx": 2205,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4732,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p \\equiv 1 \\pmod{4}",
"budget": 4265
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002206",
"normalized_example_id": "ex_002206",
"source_idx": 2206,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7109,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p \\equiv 1 \\pmod{4}",
"budget": 5687
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002206",
"normalized_example_id": "ex_002206",
"source_idx": 2206,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7109,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "p \\equiv 1 \\pmod{4}",
"budget": 7109
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002206",
"normalized_example_id": "ex_002206",
"source_idx": 2206,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7109,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}",
"budget": 2812
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002207",
"normalized_example_id": "ex_002207",
"source_idx": 2207,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}",
"budget": 3749
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002207",
"normalized_example_id": "ex_002207",
"source_idx": 2207,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}",
"budget": 4686
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002207",
"normalized_example_id": "ex_002207",
"source_idx": 2207,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2122
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002208",
"normalized_example_id": "ex_002208",
"source_idx": 2208,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3536,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2829
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002208",
"normalized_example_id": "ex_002208",
"source_idx": 2208,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3536,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3536
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002208",
"normalized_example_id": "ex_002208",
"source_idx": 2208,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3536,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{k+1} n(n+1) \\cdots(n+k)",
"budget": 4684
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002209",
"normalized_example_id": "ex_002209",
"source_idx": 2209,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7806,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{k+1} n(n+1) \\cdots(n+k)",
"budget": 6245
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002209",
"normalized_example_id": "ex_002209",
"source_idx": 2209,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7806,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{k+1} n(n+1) \\cdots(n+k)",
"budget": 7806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002209",
"normalized_example_id": "ex_002209",
"source_idx": 2209,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7806,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y(x)=C_{1}+C_{2}e^{-x}+(2x^{2}-6x+7)e^{x}",
"budget": 1283
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002210",
"normalized_example_id": "ex_002210",
"source_idx": 2210,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2139,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y(x)=C_{1}+C_{2}e^{-x}+(2x^{2}-6x+7)e^{x}",
"budget": 1711
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002210",
"normalized_example_id": "ex_002210",
"source_idx": 2210,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2139,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "y(x)=C_{1}+C_{2}e^{-x}+(2x^{2}-6x+7)e^{x}",
"budget": 2139
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002210",
"normalized_example_id": "ex_002210",
"source_idx": 2210,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2139,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4211
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002212",
"normalized_example_id": "ex_002212",
"source_idx": 2212,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7019,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5615
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002212",
"normalized_example_id": "ex_002212",
"source_idx": 2212,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7019,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7019
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002212",
"normalized_example_id": "ex_002212",
"source_idx": 2212,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7019,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5669
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002214",
"normalized_example_id": "ex_002214",
"source_idx": 2214,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9448,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7558
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002214",
"normalized_example_id": "ex_002214",
"source_idx": 2214,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9448,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 9448
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002214",
"normalized_example_id": "ex_002214",
"source_idx": 2214,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9448,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 731
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002219",
"normalized_example_id": "ex_002219",
"source_idx": 2219,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 975
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002219",
"normalized_example_id": "ex_002219",
"source_idx": 2219,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1219
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002219",
"normalized_example_id": "ex_002219",
"source_idx": 2219,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\cos\\angleA}{\\cos\\angleB\\cdot\\cos\\angleC}",
"budget": 4076
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002220",
"normalized_example_id": "ex_002220",
"source_idx": 2220,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6793,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\cos\\angleA}{\\cos\\angleB\\cdot\\cos\\angleC}",
"budget": 5434
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002220",
"normalized_example_id": "ex_002220",
"source_idx": 2220,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6793,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\cos\\angleA}{\\cos\\angleB\\cdot\\cos\\angleC}",
"budget": 6793
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002220",
"normalized_example_id": "ex_002220",
"source_idx": 2220,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6793,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2566
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002221",
"normalized_example_id": "ex_002221",
"source_idx": 2221,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4276,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3421
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002221",
"normalized_example_id": "ex_002221",
"source_idx": 2221,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4276,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4276
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002221",
"normalized_example_id": "ex_002221",
"source_idx": 2221,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4276,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{n(n-1)}{4}",
"budget": 1308
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002222",
"normalized_example_id": "ex_002222",
"source_idx": 2222,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2180,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{n(n-1)}{4}",
"budget": 1744
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002222",
"normalized_example_id": "ex_002222",
"source_idx": 2222,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2180,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{n(n-1)}{4}",
"budget": 2180
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002222",
"normalized_example_id": "ex_002222",
"source_idx": 2222,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2180,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45,45,90",
"budget": 4406
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002223",
"normalized_example_id": "ex_002223",
"source_idx": 2223,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7344,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45,45,90",
"budget": 5875
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002223",
"normalized_example_id": "ex_002223",
"source_idx": 2223,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7344,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45,45,90",
"budget": 7344
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002223",
"normalized_example_id": "ex_002223",
"source_idx": 2223,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7344,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\pi}}{2}",
"budget": 3569
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002225",
"normalized_example_id": "ex_002225",
"source_idx": 2225,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5948,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\pi}}{2}",
"budget": 4758
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002225",
"normalized_example_id": "ex_002225",
"source_idx": 2225,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5948,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\pi}}{2}",
"budget": 5948
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002225",
"normalized_example_id": "ex_002225",
"source_idx": 2225,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5948,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{3}}{3}",
"budget": 1036
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002226",
"normalized_example_id": "ex_002226",
"source_idx": 2226,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1726,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{3}}{3}",
"budget": 1381
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002226",
"normalized_example_id": "ex_002226",
"source_idx": 2226,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1726,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{3}}{3}",
"budget": 1726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002226",
"normalized_example_id": "ex_002226",
"source_idx": 2226,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1726,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=2\\mathbf{Z}, B=2\\mathbf{Z}+1",
"budget": 5036
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002227",
"normalized_example_id": "ex_002227",
"source_idx": 2227,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=2\\mathbf{Z}, B=2\\mathbf{Z}+1",
"budget": 6715
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002227",
"normalized_example_id": "ex_002227",
"source_idx": 2227,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=2\\mathbf{Z}, B=2\\mathbf{Z}+1",
"budget": 8394
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002227",
"normalized_example_id": "ex_002227",
"source_idx": 2227,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8394,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13530",
"budget": 3620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002228",
"normalized_example_id": "ex_002228",
"source_idx": 2228,
"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": "13530",
"budget": 4826
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002228",
"normalized_example_id": "ex_002228",
"source_idx": 2228,
"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": "13530",
"budget": 6033
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002228",
"normalized_example_id": "ex_002228",
"source_idx": 2228,
"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": "16",
"budget": 2500
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002229",
"normalized_example_id": "ex_002229",
"source_idx": 2229,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4167,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 3334
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002229",
"normalized_example_id": "ex_002229",
"source_idx": 2229,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4167,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 4167
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002229",
"normalized_example_id": "ex_002229",
"source_idx": 2229,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4167,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "58",
"budget": 1708
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002231",
"normalized_example_id": "ex_002231",
"source_idx": 2231,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2846,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "58",
"budget": 2277
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002231",
"normalized_example_id": "ex_002231",
"source_idx": 2231,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2846,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "58",
"budget": 2846
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002231",
"normalized_example_id": "ex_002231",
"source_idx": 2231,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2846,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{x^{2}}{a^{2}}-\\frac{y^{2}}{b^{2}}=1",
"budget": 3059
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002233",
"normalized_example_id": "ex_002233",
"source_idx": 2233,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{x^{2}}{a^{2}}-\\frac{y^{2}}{b^{2}}=1",
"budget": 4079
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002233",
"normalized_example_id": "ex_002233",
"source_idx": 2233,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{x^{2}}{a^{2}}-\\frac{y^{2}}{b^{2}}=1",
"budget": 5099
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002233",
"normalized_example_id": "ex_002233",
"source_idx": 2233,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9801",
"budget": 1821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002234",
"normalized_example_id": "ex_002234",
"source_idx": 2234,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3035,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9801",
"budget": 2428
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002234",
"normalized_example_id": "ex_002234",
"source_idx": 2234,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3035,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9801",
"budget": 3035
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002234",
"normalized_example_id": "ex_002234",
"source_idx": 2234,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3035,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 1735
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002235",
"normalized_example_id": "ex_002235",
"source_idx": 2235,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 2314
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002235",
"normalized_example_id": "ex_002235",
"source_idx": 2235,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 2892
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002235",
"normalized_example_id": "ex_002235",
"source_idx": 2235,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2892,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e^{-1}\\approx0.368",
"budget": 1215
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002237",
"normalized_example_id": "ex_002237",
"source_idx": 2237,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2025,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e^{-1}\\approx0.368",
"budget": 1620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002237",
"normalized_example_id": "ex_002237",
"source_idx": 2237,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2025,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e^{-1}\\approx0.368",
"budget": 2025
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002237",
"normalized_example_id": "ex_002237",
"source_idx": 2237,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2025,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 3807
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002238",
"normalized_example_id": "ex_002238",
"source_idx": 2238,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6345,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 5076
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002238",
"normalized_example_id": "ex_002238",
"source_idx": 2238,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6345,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 6345
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002238",
"normalized_example_id": "ex_002238",
"source_idx": 2238,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6345,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "29,38,47,56,65,74,83,92",
"budget": 1534
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002240",
"normalized_example_id": "ex_002240",
"source_idx": 2240,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2557,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "29,38,47,56,65,74,83,92",
"budget": 2046
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002240",
"normalized_example_id": "ex_002240",
"source_idx": 2240,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2557,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "29,38,47,56,65,74,83,92",
"budget": 2557
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002240",
"normalized_example_id": "ex_002240",
"source_idx": 2240,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2557,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3:4",
"budget": 2985
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002242",
"normalized_example_id": "ex_002242",
"source_idx": 2242,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4975,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3:4",
"budget": 3980
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002242",
"normalized_example_id": "ex_002242",
"source_idx": 2242,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4975,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3:4",
"budget": 4975
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002242",
"normalized_example_id": "ex_002242",
"source_idx": 2242,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4975,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5098
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002243",
"normalized_example_id": "ex_002243",
"source_idx": 2243,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8497,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6798
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002243",
"normalized_example_id": "ex_002243",
"source_idx": 2243,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8497,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8497
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002243",
"normalized_example_id": "ex_002243",
"source_idx": 2243,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8497,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 1147
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002245",
"normalized_example_id": "ex_002245",
"source_idx": 2245,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1911,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 1529
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002245",
"normalized_example_id": "ex_002245",
"source_idx": 2245,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1911,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 1911
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002245",
"normalized_example_id": "ex_002245",
"source_idx": 2245,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1911,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}-1}{2}<q<\\frac{\\sqrt{5}+1}{2}",
"budget": 1855
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002247",
"normalized_example_id": "ex_002247",
"source_idx": 2247,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3091,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}-1}{2}<q<\\frac{\\sqrt{5}+1}{2}",
"budget": 2473
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002247",
"normalized_example_id": "ex_002247",
"source_idx": 2247,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3091,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}-1}{2}<q<\\frac{\\sqrt{5}+1}{2}",
"budget": 3091
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002247",
"normalized_example_id": "ex_002247",
"source_idx": 2247,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3091,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.